Several outbreak prediction models for COVID-19 are being used by officials around the world to make informed-decisions and enforce relevant control measures. Among the standard models for COVID-19 global pandemic prediction, simple epidemiological and statistical models have received more attention by authorities, and they are popular in the media. Due to a high level of uncertainty and lack of essential data, standard models have shown low accuracy for long-term prediction. Although the literature includes several attempts to address this issue, the essential generalization and robustness abilities of existing models need to be improved. This paper presents a comparative analysis of machine learning and soft computing models to predict the COVID-19 outbreak. Among a wide range of machine learning models investigated, two models showed promising results (i.e., multi-layered perceptron, MLP, and adaptive network-based fuzzy inference system, ANFIS). Based on the results reported here, and due to the highly complex nature of the COVID-19 outbreak and variation in its behavior from nation-to-nation, this study suggests machine learning as an effective tool to model the outbreak.

Transfer learning has proven to be a valuable technique for deploying machine learning models on edge devices and embedded systems. By leveraging pre-trained models and fine-tuning them on specific tasks, practitioners can effectively adapt existing models to the constraints and requirements of their application. In the process of adapting an existing model, a practitioner may make adjustments to the model architecture, including the input layers, output layers, and intermediate layers. In this study, we examine the effects of these adjustments on the runtime and energy performance of an edge processor performing inferences. Based on our observations, we make recommendations for how to adjust convolutional neural networks during transfer learning to maintain runtime performance. We observe that the Edge TPU is generally more efficient than a CPU at performing inferences on convolutional neural networks, and continues to outperform a CPU as the depth and width of the convolutional network increases. We explore multiple strategies for adjusting the input and output layers of an existing model and demonstrate important performance cliffs for practitioners to consider when modifying a convolutional neural network model.

Multiple sclerosis (MS) is a debilitating disease of the brain and spinal cord (central nervous system). In MS, the immune system attacks the protective sheath (myelin) that covers the nerve fibers, causing communication problems between the brain and the rest of the body. Eventually the disease can cause permanent damage or nerve damage. The signs and symptoms of MS are very different and depend on the extent of the nerve damage and which nerves are affected. Some people with severe MS may lose the ability to walk independently or completely, while others may experience a long recovery period without any new symptoms. Most people with MS have a relapsing-remitting illness. They experience periods of new symptoms or recurrences that occur over days or weeks and usually improve somewhat or completely. Following these recurrences, there are periods of recovery that can last for months or even years. In this Project, we used some methods of machine learning in order to evaluate the precision and accuracy of Methods to Predict and classification of Multiple Sclerosis with different stages. In order to calculate accuracy, precision, recall Fscore we used some different method such as Art Fuzzy, SVM, Decision tree to compare the classes two by two. To improve the results we used the method of Adaptive fuzzy optimization. we used two options Genetic algorithm and particle swarm optimization.

In this paper we propose a novel self-supervised approach of keywords and keyphrases retrieval and extraction by an end-to-end deep learning approach, which is trained by contextually self-labelled corpus. Our proposed approach is novel to use contextual and semantic features to extract the keywords and has outperformed the state of the art. Through the experiment the proposed approach has been proved to be better in both semantic meaning and quality than the existing popular algorithms of keyword extraction. In addition, we propose to use contextual features from bidirectional transformers to automatically label short-sentence corpus with keywords and keyphrases to build the ground truth. This process avoids the human time to label the keywords and do not need any prior knowledge. To the best of our knowledge, our published dataset in this paper is a fine domain-independent corpus of short sentences with labelled keywords and keyphrases in the NLP community.

It is crucial to select the right machine learning classifier for image classification and face recog-nition. This study examines the effectiveness of four different face recognition classifiers - Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Neural Networks. An analysis of the Large Faces in the Wild (LFW) dataset was carried out using Principal Component Analysis (PCA). Classifiers are rigorously trained and evaluated based on the extracted features. Comparison of classifier performance is an insightful way to figure out their strengths and weaknesses. Having a visual representation of the classifier's performance gives a complete understanding of its capabilities. Through the selection of the most appropriate classifier, study results contribute to advancements in image classification, recognition, and biometric identification. The comparison study demonstrated that the Neural Network classifier was exceptionally accurate and proficient in recognizing faces from the LFW dataset when used in conjunction with PCA for feature extraction. According to the comparative analysis, the Neural Network classifier proved exceptionally accurate and proficient at identifying faces from the LFW dataset when combined with PCA for feature extraction.

Most machine learning and deep learning algorithms can only use low-dimensional data as input, but the data that must be processed in practical applications is diverse and irregular. There are two main problems with big dynamic data. (1) The size of the embedding table grows linearly with the vocabulary size, resulting in massive memory consumption. (2) For different newly added vocabularies. To solve these two problems, this paper proposes a novel embedding algorithm that can learn attribute associations with entities based on deep and hash algorithms. Taking movie data as an example, the encoding method and the specific flow of the algorithm are presented in detail, and the effect of dynamic reuse of data models is realized. Compared with the four existing embedding algorithms which can fuse entity attribute information, the deep hash embedding algorithm proposed in this paper has obvious optimization of time and space complexity.

Estimation of breeding values through Best Linear Unbiased Prediction (BLUP) using pedigree-based kinship and Marker-Assisted Selection (MAS) are the two fundamental breeding methods used before and after the introduction of genetic markers, respectively. The emergence of high-density genome-wide markers has led to the development of two parallel series of approaches inspired by BLUP and MAS, which are collectively referred to as Genomic Selection (GS). The first series of GS methods alters pedigree-based BLUP by replacing pedigree-based kinship with marker-based kinship in a variety of ways, including weighting markers by their effects in genome-wide association study (GWAS), joining both pedigree and marker-based kinship together in a single-step BLUP, and substituting individuals with groups in a compressed BLUP. The second series of GS methods estimates the effects for all genetic markers simultaneously. For the second series methods, the marker effects are summed together regardless of their individual significance. Instead of fitting individuals as random effects like in the BLUP series, the second series fits markers as random effects. Differing assumptions regarding the underlying distribution of these marker effects have resulted in the development of many Bayesian-based GS methods. This review highlights critical concept developments for both of these series and explores ongoing GS developments in machine learning, multiple trait selection, and adaptation for hybrid breeding. Furthermore, considering the increasing use and variety of GS methods in plant breeding programs, this review addresses important concerns for future GS development and application, such as the use of GWAS-assisted GS, the long-term effectiveness of GS methods, and the valid assessment of prediction accuracy.

Despite UAV multi-target detection exhibits considerable developmental potential worldwide, it suffers distinct challenges compared with traditional tasks in this field. These challenges include insufficient feature extraction capabilities for small targets, limited capabilities for multi-dimensional feature fusion, as well as constraints on hardware computation parameters. Especially in mission scenarios such as disaster detection, these challenges will be further amplified. Consequently, this paper introduces SSE-YOLO, an innovative YOLO framework algorithm specially designed to address these challenges. To enhance the model's feature extraction capability, we employ the SPDConv module to replace the original Conv in the backbone section, utilizing depth-separable convolution instead of traditional convolution pooling. Concurrently, we eliminate the SPPF module at the bottom and address a new Separate Kernel Attention Pyramid Pooling (SKAPP) module, substantially enhancing the feature fusion capability at the model's core. Moreover, to address the challenge of multi-dimensional feature fusion, we replace the Concat module of the neck and head with E-BiFPN, transmitting feature information from the backbone to the lower network through four CBS blocks, which effectively resolves the issue of lost contextual information in the model. Meanwhile, SSE-YOLO undergoes ablation experiments on the VisDrone2019 dataset to evaluate its effectiveness against alternative methods, and experimental results illustrate the model's exceptional precision in detecting UAV targets. In comparison to models with comparable experimental accuracy, SSE-YOLO requires remarkably fewer parameters. On the VisDrone2019-DET-test-dev dataset, SSE-YOLO enhances mAP by 17.3%, with a 42.5% reduction in the parameter amounts. Therefore, the proposed method effectively tackles the challenge of reconciling low parameters and high accuracy, presenting a novel pathway for deep learning-based UAV multi-target detection.

Educational institutions worldwide have adopted e-learning due to the COVID-19 pandemic. While this shift to online learning (OL) has presented challenges for students and teachers, it has also sparked innovative educational approaches. This study investigates college students' perceptions regarding OL, specifically focusing on gender differences in the experience with OL A quantitative survey gathered information from distinct college students in Gulf Cooperation Council (GCC) nations who experienced OL during the pandemic. The survey included questions related to satisfaction with OL and specific aspects such as course content delivery, interaction with instructors, behavioral changes, and challenges with OL. Male and female student OL experience was compared statistically. The results conclude that male students are more satisfied than female students. Students struggled with internet connection, OL adaptation, focus, and workload during OL. Understanding these gender differences in students' satisfaction with OL is crucial for educators and institutions as they strive to optimize the effectiveness of e-learning strategies. By recognizing and addressing male and female students' unique needs and challenges, educational institutions can enhance the overall educational experience during times of crisis and beyond.

Crop breeding is as ancient as the invention of cultivation. In essence, the objective of crop breeding is to improve plant fitness under human cultivation conditions, making crops more productive while maintaining consistency in life cycle and quality. The applications of predictive breeding has been gaining momentum in agricultural industry and public breeding programs for the last decade, in the aftermath of genomic selection being recognized and widely applied for accelerating genetic gain in breeding programs. The massive amounts of data that has been generated by industry and farmers year after year through several decades has finally been recognized as an asset. A wide range of analytical methods such as machine learning, deep learning and artificial intelligence that were initially developed for diverse quantitative disciplines are now being adopted to crop breeding decision making processes. New technologies are currently being developed that would enable integration of data from various domains such as geospatial variables and a multitude of phenotypic responses as well as genetic information, in order to identify, develop and improve crop faster via partial or full automation of the decisions that pertain to variety development. Here we will discuss and summarize efforts from public and private domains for predictive analytics, and its applications to crop breeding and agricultural product development, and provide suggestions for future research.

We developed a novel machine learning algorithm to augment clinical diagnosis of prostate cancer utilizing first and second-order texture analysis metrics and novel application of machine learning radiomics analysis. We successfully discriminated between significant prostate cancers versus non-tumor regions and provided accurate prediction between Gleason score cohorts with statistical sensitivity of greater than 0.91 sensitivity across three separate cohorts. Tumor heterogeneity and prediction between GS cohorts were quantified using two feature selection approaches and two classifiers with tuned hyperparameters (including grid search and randomized search). There was a total of 71 patients analyzed in this study. Multiparametric MRI, incorporating T2WI and the ADC maps, were used to derive radiomics features. Recursive feature elimination (RFE), the least absolute shrinkage and selection operator (LASSO), and two classification approaches, including a support vector machine (SVM) (with grid search) and random forest (RF) (with randomized search), were utilized to differentiate between non-tumor regions versus significant cancer and prediction among Gleason score groups. In T2WI images, the RFE feature selection approach combined with RF and SVM classifiers outperformed LASSO with SVM and RF classifiers regarding performance. The detection precision of the radiomics framework depending on multiple imaging modalities was lower than the diagnostic accuracy of single imaging modality model with every machine learning approach assessed. The best performance was achieved by combining LASSO and SVM into a model that used both T2WI and ADC. This model had an area under the curve (AUC) of 0.91. Radiomic features computed from ADC and T2WI images were used to predict three groups of Gleason score using two kinds of feature selection methods (RFE and LASSO), RF and SVM classifier models with tuned hyperparameters. Using combined sequences (T2WI and ADC map images) and combined radiomics (1st and GLCM features), LASSO, with a feature selection method with RF, was able to predict G3 with the highest sensitivity at a level AUC of 0.92. To predict G3 for single sequence (T2WI images) using GLCM features, LASSO with SVM achieved the highest sensitivity with an AUC of 0.92.

In addition to identifying and prosecuting cyber attackers, attack attribution activities can provide valuable information guiding the defenders’ security procedures and giving them greater confidence in incident response and remediation. However, technical analysis involved in cyberattack attribution requires high skills, experience, access to up-to-date Cyber Threat Intelligence, and significant investigators’ effort. Attribution results are not always reliable, and skilful attackers often work hard to cover their traces and mislead or confuse investigators. In this article, we present a tool designed to support technical attack attribution and implemented as a machine learning model extending the OpenCTI platform. We also discuss the tool’s performance in the investigation of a recent cyberattack.

Pipeline integrity is an important area of concern for the oil and gas, refining, chemical, hydrogen, carbon sequestration, and electric-power industries, due to the safety risks associated with pipeline failures. Regular monitoring, inspection, and maintenance of these facilities is therefore required for safe operation. Large standoff magnetometry (LSM) is a non-intrusive, passive magnetometer-based mea- surement technology that has shown promise in detecting defects (anomalies) in regions of elevated mechanical stresses. However, analyzing the noisy multi-sensor LSM data to clearly identify regions of anomalies is a significant challenge. This is mainly due to the high frequency of the data collection, mis-alignment between consecutive inspections and sensors, as well as the number of sensor measurements recorded. In this paper we present LSM defect identification approach based on ma- chine learning (ML). We show that this ML approach is able to successfully detect anomalous readings using a series of methods with increasing model complexity and capacity. The methods start from unsupervised learning with "point" methods and eventually increase complexity to supervised learning with sequence methods and multi-output predictions. We observe data leakage issues for some methods with randomized train/test splitting and resolve them by specific non-randomized splitting of training and validation data. We also achieve a 200x acceleration of support-vector classifier (SVC) method by porting computations from CPU to GPU leveraging the cuML RAPIDS AI library. For sequence methods, we develop a customized Convolutional Neural Network (CNN) architecture based on 1D convolutional filters to identify and characterize multiple properties of these defects. In the end, we report the scalability of the best-performing methods and compare them, for viability in field trials.

Rationale: Major depressive disorder (MDD) is characterized by signaling aberrations in interleukin (IL)-6, IL-10, beta-endorphins as well as mu (MOR) and kappa (KOR) opioid receptors. Here we examined whether these biomarkers may aid in the classification of unknown subjects into the target class MDD.Methods: The aforementioned biomarkers were assayed in 60 first-episode, drug-naïve depressed patients and 30 controls. We analyzed the data using joint principal component analysis (PCA) performed on all subjects to check whether subjects cluster by classes; support vector machine (SVM) with 10-fold validation; and linear discriminant analysis (LDA) and SIMCA performed on calibration and validation sets and we computed the figures of merit and learnt from the data. Results: PCA shows that both groups were well separated using the first three PCs, while correlation loadings show that all 5 biomarkers have discriminatory value. SVM and LDA yielded an accuracy of 100% in validation samples. Using SIMCA there was a highly significant discrimination of both groups (model-to-model distance=87.5); all biomarkers showed a significant discrimination and modeling power, while 10% of the patients were identified as outsiders and no aliens could be identified.Discussion: We have delineated that MDD is a distinct class with respect to neuro-immune and opioid biomarkers and that future unknown subjects can be authenticated as having MDD using this SIMCA fingerprint. Precision psychiatry should employ SIMCA a) to authenticate patients as belonging to the claimed target class and identify other subjects as outsiders, members of another class or aliens; and b) to acquire knowledge through learning from the data by constructing a biomarker fingerprint of the target class.

The goal was to create a novel machine learning (ML) model which can predict the magnitude and direction of pubertal mandibular growth in males with Class II malocclusion. Lateral cephalometric radiographs of 123 males at three time points (T1: 12, T2: 14, T3: 16 years old) were collected from an online database of longitudinal growth studies. Each radiograph was traced, and 7 different ML models were trained using 38 data points obtained from 92 subjects. 31 subjects were used as a test group, to predict post-pubertal mandibular length and Y-axis using input data from T1 and T2 combined (2-year prediction), and T1 alone (4-year prediction). Mean absolute errors (MAEs) were used to evaluate the accuracy of each model. For all ML methods tested using the 2-year prediction, the MAEs for post-pubertal mandibular length ranged from 2.11-6.07mm and 0.85-2.74° for the Y-axis. For all ML methods tested with 4-year prediction, the MAEs for post-pubertal mandibular length ranged from 2.32-5.28 mm and 1.25-1.72° for the Y-axis. Besides its initial length, the most predictive factors for mandibular length were found to be chronological age, upper and lower face heights, upper and lower incisor positions and inclinations. For the Y-axis, the most predictive factors were found to be Y-axis at earlier time points, SN-MP, SN-Pog, SNB and SNA. Whilst the potential of ML techniques to accurately forecast future mandibular growth in Class II cases is promising, a requirement for more substantial sample sizes exists to further enhance the precision of these predictions.

This paper proposes a forecast-centric adaptive learning model that engages with the past studies on the order book and high-frequency data, with applications to hypothesis testing. In line with the past literature, we produce brackets of summaries of statistics from the high-frequency bid and ask data in the CSI 300 Index Futures market and aim to forecast the one-step-ahead prices. Traditional time series issues, e.g. ARIMA order selection, stationarity, together with potential financial applications are covered in the exploratory data analysis, which pave paths to the adaptive learning model. By designing and running the learning model, we found it to perform well compared to the top fixed models, and some could improve the forecasting accuracy by being more stable and resilient to non-stationarity. Applications to hypothesis testing are shown with a rolling window, and further potential applications to finance and statistics are outlined.

The research of object classification and part segmentation is a hot topic in computer vision. A considerable number of studies have been carried out about deep learning on 3D point clouds. However,it is challenging to achieve effective feature learning due to sparsity of point clouds. Recently, a variety of Transformers have been adopted to improve point cloud processing and display great potential. Nevertheless, large numbers of Transformer layers tend to incur huge computational and memory costs. PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks, this does not mean that PointNet++ has no potential.Thus, this paper offer two major contributions that significantly improve PointNet++ performance. Firstly, we introduce a novel contextual feature extraction (CFE) block that significantly enhances the feature extraction capabilities of PointNet++ networks. Secondly, to further enhance feature fusion, we seamlessly integrate a mutual learning (ML) block into the network architecture. By embedding these two innovative blocks within each layer of the network, we not only enrich the network's functionality but also impart it with greater robustness and adaptability. The specific experiments were conducted on the S3DIS (6-fold cross-validation) and Modelnet40 datasets with 86.5% and 92.7% accuracy, respectively, which proved that our model is comparable or even better than most existing methods for classification and segmentation tasks.

Scaffoldings play a critical role as temporary structures in supporting construction processes. Accidents at construction sites frequently stem from issues related to scaffoldings, including insufficient support caused by deviations from the construction design, insecure rod connections, or absence of cross bracing, which result in uneven loading and potential collapse, leading to casualties. In this study, we introduce a deep-learning-based, augmented reality (AR)-enabled system called scaffolding assembly deficiency detection system (SADDS) to assist field inspectors in identifying deficiencies in scaffolding assemblies. Inspectors have the flexibility to utilize SADDS through various devices, such as video cameras, mobile phones, or AR goggles (i.e., Microsoft HoloLens 2), for automated detection of deficiencies in scaffolding assemblies. The training test yielded satisfactory results, with a mean average precision of 0.89 and individual precision values of 0.96, 0.82, 0.90, and 0.89 for “qualified” frames and frames with the “missing cross-tie rod,” “missing lower-tie rod,” and “missing footboard” deficiencies, respectively. Field tests conducted at two construction sites demonstrated improved system performance compared to that in the training test. However, these field tests also revealed certain limitations of the SADDS system.

We introduce a novel microscopic image dataset augmented with segmentation and detection labels specifically designed for microplastic analysis in sewage environments. Recognizing the increasing concern over microplastics — particles of synthetic polymers smaller than 5mm — and their detrimental effects on marine ecosystems and human health, our research focuses on enhancing detection and analytical methodologies through advanced computer vision and deep learning techniques. The dataset comprises high-resolution microscopic images of microplastics collected from sewage, meticulously labeled for both segmentation and detection tasks, aiming to facilitate accurate and efficient identification and quantification of microplastic pollution. In addition to dataset development, we present example deep learning models optimized for segmentation and detection of microplastics within complex sewage samples. The models demonstrate significant potential in automating the analysis of microplastic contamination, offering a scalable solution to environmental monitoring challenges. Furthermore, we ensure the accessibility and reproducibility of our research by making the dataset and model codes publicly available, accompanied by detailed documentation on GitHub and LabelBox. The dataset and example deep learning models are publicly available at the following GitHub link. https://anonymous.4open.science/r/Microplastics-in-Sewage-1BEF

The aim was to assess the precision and accuracy of cephalometric analyses performed by artificial intelligence (AI) with and without human augmentation. Four dental professionals with varying experience levels and AI identified 31 landmarks on 30 cephalometric radiographs twice. These landmarks were re-identified by all examiners with the aid of AI. Precision and accuracy were assessed by using intraclass correlation coefficients (ICCs) and mean absolute errors (MAEs). AI revealed the highest precision with a mean ICC of 0.97, while the dental student had the lowest (mean ICC: 0.77). AI/human augmentation method significantly improved precision of the orthodontist, resident, dentist, and dental student by 3.26%, 2.17%, 19.75%, and 23.38%, respectively. The orthodontist demonstrated the highest accuracy with a MAE of 1.57 mm/˚. AI/human augmentation method improved the accuracy of the orthodontist, resident, dentist, and dental student by 12.74%, 19.10%, 35.69%, and 33.96%, respectively. AI demonstrated excellent precision and good accuracy in automated cephalometric analysis. The precision and accuracy of the examiners with the aid of AI improved by 10.47% and 27.27%, respectively. The AI/human augmentation method significantly improved the precision and accuracy of less experienced dental professionals to that of an experienced orthodontist.

In this paper, we focus on developing a novel method to extract sea ice cover (i.e., discrimination/classification of sea ice and open water) using Sentinel-1 (S1) cross-polarization (vertical-horizontal, VH or horizontal-vertical, HV) data in extra wide (EW) swath mode based on the machine learning algorithm support vector machine (SVM). The classification basis includes the S1 radar backscatter coefficients and texture features that are calculated from S1 data using the gray level co-occurrence matrix (GLCM). Different from previous methods where appropriate samples are manually selected to train the SVM to classify sea ice and open water, we proposed a method of unsupervised generation of the training samples based on two GLCM texture features, i.e. entropy and homogeneity, that have contrasting characteristics on sea ice and open water. We eliminate the most uncertainty of selecting training samples in machine learning and achieve automatic classification of sea ice and open water by using S1 EW data. The comparison shows good agreement between the SAR-derived sea ice cover using the proposed method and a visual inspection, of which the accuracy reaches approximately 90% - 95% based on a few cases. Besides this, compared with the analyzed sea ice cover data Ice Mapping System (IMS) based on 728 S1 EW images, the accuracy of extracted sea ice cover by using S1 data is more than 80%.

In response to the growing challenges in drone security and airspace management, this study introduces an advanced drone classifier, capable of detecting and categorizing Unmanned Aerial Vehicles (UAVs) based on acoustic signatures. Utilizing a comprehensive database of drone sounds across EU-defined classes (C0 to C3), this research leverages machine learning (ML) techniques for effective UAV identification. The study primarily focuses on the impact of data augmentation methods—pitch shifting, time delays, harmonic distortion, and ambient noise integration—on classifier performance. These techniques aim to mimic real-world acoustic variations, thus enhancing the classifier's robustness and practical applicability. Results indicate that moderate levels of augmentation significantly improve classification accuracy. However, excessive application of these methods can negatively affect performance. The study concludes that sophisticated acoustic data augmentation can substantially enhance ML-driven drone detection, providing a versatile and efficient tool for managing drone-related security risks. This research contributes to UAV detection technology, presenting a model that not only identifies but also categorizes drones, underscoring its potential for diverse operational environments.

Foveal vision loss has been shown to reduce efficient visual search guidance due to contextual cueing by incidentally learned contexts. However, previous studies used artificial (T among L-shape) search paradigms that prevent the memorization of a target in a semantically meaningful scene. Here, we investigated contextual cueing in real-life scenes that allow explicit memory of target locations in semantically rich scenes. In contrast to the contextual cueing deficits in artificial scenes, contextual cueing in patients with age-related macular degeneration (AMD) did not differ from age-matched normal-sighted controls. We discuss this in the context of visuospatial working memory demands for which both eye-movement control in the presence of central vision loss and for memory-guided search may compete. Memory-guided search in semantically rich scenes may depend less on visuospatial working memory than search in abstract displays, potentially explaining intact contextual cueing in the former but not the latter. In a practical sense, our findings may indicate that Patients with AMD are less deficient than expected after previous lab experiments. This shows the usefulness of realistic stimuli in experimental clinical research.

One of the main challenges for autonomous learning in virtual environments is finding the right material that fits students’ needs and supports their learning process. Personalized recommender systems partially solve this problem by suggesting online educational resources to students based on their preferences. However, in educational environments (which need a proper characterization of both users and educational resources), most existing recommendation algorithms either fail to include all the available information or use hybrid processes that do not exploit possible relationships between users and item features. This article presents a personalized recommender system for educational resources aimed at combining user and item information into a single mathematical model based on matrix factorization. As a result, estimated latent factors can provide insight into possible interactions between users and item features, improving the quality of the information retrieval process. We validated the proposed model on a real dataset that contains the ratings assigned by students from Universidad Nacional de Colombia and Universidade Feevale to educational resources in the Colombian Federation of Learning Object Repositories (FROAC in Spanish). User characterization included learning style and educational level, whereas item characterization (obtained from the objects’ metadata), included interactivity level, aggregation level and type, and resource format. These results, compared to those obtained when not all the available information is included, show that our method can improve the recommendation process.

Accurate short-term solar irradiance forecasting is crucial for the efficient operation of solar energy driven photovoltaic (PV) power plants. In this research, we introduce a novel hybrid ensemble forecasting model that amalgamates the strengths of machine learning tree-based models and deep learning neuron-based models. The hybrid ensemble model integrates the interpretability of tree-based models with the capacity of neuron-based models to capture complex temporal dependencies within solar irradiance data. Furthermore, stacking and voting ensemble strategies are employed to harness the collective strengths of these models, significantly enhancing prediction accuracy. This integrated methodology is enhanced by incorporating pixels from satellite images provided by the European Organization for the Exploitation of Meteorological Satellites (EUMETSAT). These pixels are converted into structured data arrays and employed as exogenous inputs in the algorithm. The primary objective of this study is to improve the accuracy of short-term solar irradiance predictions, spanning a forecast horizon up to 6 hours ahead. The incorporation of EUMETSAT satellite image pixels data enables the model to extract valuable spatial and temporal information, thus enhancing the overall forecasting precision. This research also includes detailed analysis of the derivation of GHI using satellite images. The study was carried out and the models tested across three distinct locations in Austria. A detailed comparative analysis was carried out for traditional Satellite (SAT) and Numerical Weather Prediction (NWP) models with hybrid models. Our findings demonstrate a higher skill score for all of the approaches compared to smart persistent model and consistently highlight the superiority of the hybrid ensemble model for short-term prediction window of 1 to 6 hours. This research underscores the potential for enhanced accuracy of the hybrid approach to advance short-term solar irradiance forecasting, emphasizing its effectiveness at understanding the intricate interplay of the meteorological variables affecting solar energy generation worldwide. The results of this investigation carry noteworthy implications for advancing solar energy systems, thereby supporting the sustainable integration of renewable energy sources into the electrical grid.

Despite widespread vaccination, early treatments, and improved understanding of the disease, the effects of SARS-CoV-2 infection remain significant worldwide. Many patients still suffer from severe COVID-19, necessitating admission to intensive care units. Remdesivir is a primary treatment option among viral RNA polymerase inhibitors for hospitalized SARS-CoV-2 patients. However, there is a lack of studies examining factors influencing its effectiveness in this context. We conducted a retrospective study throughout 2022, analyzing clinical, laboratory, and sociodemographic data from 252 hospitalized COVID-19 patients treated with remdesivir. Six machine learning algorithms were compared and validated to predict factors associated with the loss of clinical benefit from remdesivir in terms of mortality and hospital stay. Data were extracted from electronic health records. The eXtreme Gradient Boost (XGB) method achieved the highest balanced accuracy for both mortality (95.45%) and hospital stay (94.24%). Factors associated with worse outcomes of remdesivir use in terms of mortality included limitation of life support treatment, need for ventilatory support (especially invasive mechanical ventilation) on day 14 after the first dose of remdesivir, lymphopenia, low levels of albumin and hemoglobin, presence of flu and/or coinfection, and cough. Factors associated with worse outcomes of remdesivir use in terms of hospital stay included the number of doses of the COVID-19 vaccine, patchy lung density, bilateral pulmonary radiological status, number of comorbidities, oxygen therapy, troponin and lactate dehydrogenase levels, and asthenia. These findings highlight the effectiveness of XGB as a strong candidate for accurately categorizing COVID-19 patients undergoing remdesivir treatment.

Many spatial decision support systems suffer from user adoption issues in practice due to lack of trust, technical expertise, and resources. Automated machine learning has recently allowed non-experts to explore and apply machine learning models in the industry without requiring abundant expert knowledge and resources. This paper reviews recent literature from 136 papers, and proposes a general framework for integrating spatial decision support systems with automated machine learning to lower major user adoption barriers. Challenges of data quality, model interpretability, and practical usefulness were discussed as general considerations for system implementation. Research opportunities related to spatially explicit models in AutoML, and resource-aware, collaborative/connected, and human-centered systems were also discussed to address these challenges. This paper argues that integrating spatial decision support systems with automated machine learning can not only encourage user adoption, but also mutually benefit research in both fields — bridging human-related and technical advancements for fostering future developments in spatial decision support systems and automated machine learning.

Ransomware is one of the most dangerous types of malware, which is frequently intended to spread through a network to damage the designated client by encrypting the client’s vulnerable data. Conventional signature-based ransomware detection technique falls behind because it can only detect known anomalies. When it comes to new and non-familiar ransomware traditional system unveils huge shortcomings. For detecting unknown patterns and sorts of new ransomware families,behavior-based anomaly detection approaches are likely to be the most efficient approach. In the wake of this alarming condition, this paper presents an ensemble classification model consisting of three widely used machine learning techniques that include Decision Tree (DT), RandomForest (RF), and K-nearest neighbor (KNN). To achieve the best outcome ensemble soft voting and hard voting techniques are used while classifying ransomware families based on attack attributes. Performance analysis is done by comparing our proposed ensemble models with standalone models on behavioral attributes based ransomware dataset..

Current stock market forecasting methods encompass fundamental, technical, emotional, and bargaining factors. Predominantly, price prediction hinges on order volume and price, although correlating these two within existing models proves challenging. This study employs Cycle Generative Adversarial Network (Cycle GAN) to unravel the intricate price-volume relationship, combining it with Bollinger Bands for trading signal analysis, overcoming hurdles in short-term forecasting prevalent in numerical analysis and AI. Focusing on TSMC (2330.TW) stock price, the research leverages Cycle GAN in deep learning to master the price-volume nexus, juxtaposed with LSTM and RNN. Historical TSMC closing prices and transaction counts are model inputs, scrutinizing their interconnectedness for predictions. This innovative approach aligns stock price, volume, market value, taxes, and prior changes via system engineering. By intertwining Bollinger Bands with stock price forecasts, trading signals are distilled, factoring in extended index %b for a comprehensive market picture.

GNSS time series prediction plays a significant role in monitoring crustal plate motion, landslide detection, and maintenance of the global coordinate framework. Long Short-Term Memory (LSTM), a deep learning model has been widely applied in the field of high-precision time series prediction especially when combined with Variational Mode Decomposition (VMD) to form the VMD-LSTM hybrid model. To further improve the prediction accuracy of the VMD-LSTM model, this paper proposes a dual variational modal decomposition long short-term memory (DVMD-LSTM) model to effectively handle the noise in GNSS time series prediction. This model extracts fluctuation features from the residual terms obtained after VMD decomposition to reduce the prediction errors associated with residual terms in the VMD-LSTM model. Daily E, N, and U coordinate data recorded at multiple GNSS stations between 2000 and 2022 are used to validate the performance of the proposed DVMD-LSTM model. The experimental results demonstrate that compared to the VMD-LSTM model, the DVMD-LSTM model achieves significant improvements in prediction performance across all measurement stations. The average RMSE is reduced by 9.86%, and the average MAE is reduced by 9.44%. Furthermore, the average accuracy of the optimal noise model for the predicted results is improved by 36.50%, and the average speed accuracy of the predicted results is enhanced by 33.02%. These findings collectively attest to the superior predictive capabilities of the DVMD-LSTM model, thereby enhancing the reliability of the predicted results.

There is a crucial need for advancement in the online educational system due to the unexpected, forced migration of classroom activities to a fully remote format, due to the coronavirus pandemic. Not only this, but online education is the future, and its infrastructure needs to be improved for an effective teaching-learning process. One of the major concerns with the current video call-based online classroom system is student engagement analysis. Teachers are often concerned about whether the students can perceive the teachings in a novel format. Such analysis was involuntarily done in the offline mode, however, is difficult in an online environment. This research presents an autonomous system for analyzing the students' engagement in the class by detecting the emotions exhibited by the students. This is done by capturing the video feed of the students and passing the detected faces to an emotion detection mode. The emotion detection model in the proposed architecture was designed by finetuning VGG16 pre-trained image classifier model. Lastly, the average student engagement index is calculated. We received considerable performance setting reliability of the use of the proposed system in real-time giving a future scope to this research.

Transition from primary to secondary school is more successful when students’ learning is consistent. Students are also more likely to enjoy the school, engage with learning, and have a high academic achievement in the secondary school when they feel motivated. This is a critical aspect especially in cases when global pandemics situations allow only the online schooling opportunity. Students that are away from school lack the traditional sources of motivation and self-regulated learning skills, thus research is needed to identify other important factors that can be developed in remote settings. The aim of this study was to find out how students perceive their experience with the transition from primary to secondary school and how such a transition influences students’ self-regulated learning (SRL) and motivation. Self-reported data were collected during the COVID-19 breakout from a total of N=80, 6th and 7th grade students aged 12-14 years old. Results showed that students had a successful transition, especially when they are supported by their parents and teachers. Next, Bivariate Pearson Correlation analysis indicated that students’ perceptions about their experience with the transition from primary to secondary school and their self-regulated learning and motivation are significantly correlated. No gender differences were found among all main study variables.

As an established and widely available infrastructure, wireless local area networks (WLANs) have emerged as a viable option for indoor localization of both mobile and stationary users. In planning a mobile communications network and radio system design, the critical role of coverage prediction becomes evident, empowering network operators to optimize cellular networks and elevate the overall customer experience. Moreover, WLANs present several challenges that must be fulfilled when it comes to localization based on Wi-Fi signals to get a proper coverage prediction map. This paper presents a study based on application of the extra trees regression (ETR) for indoor localization by using coverage prediction maps. The aim of the proposed method is to accurately estimate a user’s position within a radio environment map (REM) area using collected received signal strength indicator (RSSI) values. The proposed scheme investigates several machine learning (ML) regression algorithms for localization, where the training dataset is obtained from the REM by using the nearest neighbors method. Parameter tuning is conducted to optimize the performance of the ETR scheme by using 10-fold cross-validation. In the numerical results, we first demonstrate the effectiveness of utilizing ML regression techniques for generating coverage maps, which enables accurate estimation of the Wi-Fi signal strength in indoor environments. Then, we showcase the superior performance of the proposed ETR-based method compared to several other ML schemes for indoor localization using the REM. ML algorithms, including decision tree regression and the ETR, are compared to evaluate the system model. Based on error metrics, the proposed ETR-based approach exhibits the best performance among the evaluated techniques. The combination of coverage map generation and localization using regression techniques offers a powerful approach for analyzing the radio frequency (RF) environment in indoor spaces.

Neural networks require a large quantity of training spectra and detector responses in order to learn to solve the inverse problem of neutron spectrum unfolding. In addition, due to the under-determined nature of unfolding, non-physical spectra which would not be encountered in usage should not be included in the training set. While physically realistic training spectra are commonly determined experimentally or generated through Monte Carlo simulation, this can become prohibitively expensive when considering the quantity of spectra needed to effectively train an unfolding network. In this paper, we present three algorithms for the generation of large quantities of realistic and physically motivated neutron energy spectra. Using an IAEA compendium of 251 spectra, we compare the unfolding performance of neural networks trained on spectra from these algorithms, when unfolding real-world spectra, to two baselines. We also investigate general methods for evaluating the performance of and optimizing feature engineering algorithms.

Infrared thermography has already been proven to be a significant method in non-destructive evaluation since it gives information with immediacy, rapidity, and low cost. However, the thorniest issue for the wider application of IRT is quantification. In this work, we proposed a specific depth quantifying technique by employing the Gated Recurrent Units (GRU) in composite material samples via pulsed thermography (PT). Finite Element Method (FEM) modeling provides the economic examination of the response pulsed thermography. In this work, Carbon Fiber Reinforced Polymer (CFRP) specimens embedded with flat bottom holes are stimulated by a FEM modeling (COMSOL) with precisely controlled depth and geometrics of the defects. The GRU model automatically quantified the depth of defects presented in the stimulated CFRP material. The proposed method evaluated the accuracy and performance of synthetic CFRP data from FEM for defect depth predictions.

This paper addresses challenges and solutions in urban development and infrastructure resilience, particularly in the context of Japan's rapidly urbanizing landscape. It explores the integration of smart city concepts to combat land subsidence and liquefaction, phenomena highlighted by the 2011 Great East Japan Earthquake. Using advanced technologies such as smart sensing and predictive analytics through kriging and ensemble learning, the study aims to improve the accuracy of geotechnical investigations and urban planning. By analyzing data from 433 geotechnical surveys in Setagaya, Tokyo, it develops predictive models to accurately determine the depth of bearing layers critical to urban infrastructure. The results demonstrate the superiority of ensemble learning in predicting the depth of bearing layers, with significant implications for smart city development and the sustainability of urban environments. This interdisciplinary approach not only seeks to mitigate risks associated with geological disturbances, but also promotes sustainable urban growth that prioritizes safety and prosperity. Through advanced technology and comprehensive research, the study underscores the potential of smart cities to address urban complexities and ensure a resilient, sustainable future.

Diabetes becomes a life threatening non-communicable disease in the world, according to International Diabetic Federation (IDF) in 2023, an estimated 537 million adults (20-79 years) are living with diabetes, which is equivalent to 9.3% of the global adult population. This number is predicted to rise to 643 million by 2030 and 783 million by 2045. Over 3 in 4 adults with diabetes live in low- and middle-income countries. Diabetes is a persistent metabolic condition marked by increased levels of glucose in the bloodstream. It is a significant global health concern, affecting millions of individuals worldwide. It having the symptoms of drowsiness for the whole day if not properly examined or treated well. It is targeted to spread over the younger age community and the number is growing in the exponential fashion. Even day to day many advancements have come from the researcher to diagnose, to find solutions to prevent from newer entry. Authors have taken a dataset with 57 non diabetic and 20 diabetic patients with the total 28735 micro array gene to undergone pre-processing process and reduced up to 22960 gene data using Dimensionality Reduction (DR) such as Detrend Fluctuation Analysis (DFA), Chi square probability density function (Chi2PDF), Firefly algorithm Cuckoo search were used in this research. Meta heuristic algorithms like Particle swarm Optimization (PSO) and Harmonic Search (HS) are used for feature selection. Further seven classification techniques such as Non-Linear Regression (NLR), Linear Regression (LR), Logistics Regression (LoR), Gaussian Mixture Model (GMM), Bayesian Linear Discriminant Classifier (BLDC), Softmax Discriminant Classifier (SDC), Support Vector Machine – Radial Basis Function (SVM-RBF) are using to make a decision, predictive analysis and segregate the data according to the level of blood glucose as Diabetic Patient (DP) and Non-Diabetic Patient (NDP).

Stagnation at local optima represents a significant challenge in bio–inspired optimization algorithms, often leading to suboptimal solutions. This paper addresses this issue by proposing a hybrid model that combines the Orca Predator Algorithm with Deep Q–Learning. Orca Predator Algorithm is an optimization technique that mimics the hunting behavior of orcas. It solves complex optimization problems by exploring and exploiting search spaces efficiently. Deep Q–Learning is a reinforcement learning technique that combines Q–Learning with deep neural networks. This integration aims to turn the stagnation problem into an opportunity for more focused and effective exploitation, enhancing the optimization technique’s performance and accuracy. The proposed hybrid model leverages the biomimetic strengths of Orca Predator Algorithm to identify promising regions nearby in the search space, complemented by the fine–tuning capabilities of Deep Q–Learning to navigate these areas precisely. The practical application of this approach is evaluated using the high–dimensional Heartbeat Categorization Dataset, focusing on the feature selection problem. This dataset, comprising complex electrocardiogram signals, provided a robust platform for testing the feature selection capabilities of our hybrid model. Our experimental results are encouraging, showcasing the hybrid strategy capability to identify relevant features without significantly compromising the performance metrics of machine learning models. This analysis was performed by comparing the improved method of Orca Predator Algorithm against its native version and a set of state–of–the–art algorithms.

There is a noticeable absence of health education among college students. This study aimed to evaluate the extent of general nutrition knowledge among Chinese university students and explore its association with eating attitudes. Data were collected from a group of 273 students in Spring of 2023, using a valid and reliable research instrument consisting of three sections: demographic variables, the General Nutrition Knowledge Questionnaire (GNKQ), and the Eating Attitudes Test (EAT-26). The results were analyzed using SPSS, with correlations and t-tests to examine the relationships between nutritional knowledge and dietary attitudes. Furthermore, the present study employed the Random Forest (RF) algorithm, a machine learning technique, utilizing the Mean Decrease Impurity (MDI) method to investigate the influence of various features on participants' eating attitudes. The findings revealed that Chinese university students had an average accuracy of over 60% in their nutritional knowledge, but their understanding of the relationship between diet and disease still needs improvement. Moreover, male students had significantly lower nutritional knowledge than female students, and there was a positive correlation between nutritional knowledge and parents’ income. The study also found a significant correlation between the level of nutritional knowledge and eating attitudes. RF results indicated that family income level exhibited the most substantial impact on the eating attitudes of the participants. The study highlights the need for nutrition education curriculum developers to focus more on improving students' nutritional knowledge, with particular attention given to male students, low-income individuals, and those with an abnormal BMI.

There is no doubt that the COVID-19 pandemic has greatly affected the higher education sector in South Africa. However, academics and students’ preparedness and competencies have been considered a major conundrum concerning the integration of online learning in the classroom. The purpose of this paper is to examine the academics’ perspectives on a blend of a metaverse in the higher education sector in the post-COVID-19 era at one of the South African rural-based universities. A survey was administered in 2022 to ten (10) academics and the reports were consulted from four (4) E-learning practitioners to solicit their perceptions regarding the use of online learning and contact classes in the post-pandemic era. A qualitative research approach was employed to comprehend the challenges encountered in a historically disadvantaged rural-based university in Limpopo Province. The findings of this study show that there are major issues and challenges impeding the establishment of effective e-learning education. Consequently, technological continuity as a new normal in the post-COVID-19 era appears to be unattainable due to the challenges encountered by the students and lecturers. The use of Learning Management Systems among academics seems to have deteriorated due to the adjustments in COVID-19 rules and regulations. Furthermore, the findings revealed that most academics believed that contact learning remains irreplaceable throughout generations and ages as some are technophilic. This paper recommends that the incompetence and technological resistance and reluctance in adopting transformative pedagogies may not be used as a stumbling block to consider e-learning as a viable option to discontinue online education.

Training data for a deep learning (DL) neural network (NN) controller are obtained from the input and output signals of a conventional digital controller that is designed to provide the suitable control signal to a specified plant within a feedback digital control system. It is found that if the DL controller is sufficiently deep (four hidden layers), it can outperform the conventional controller in terms of settling time of the system output transient response to a unit-step reference signal. That is, the DL controller introduces a damping effect. Moreover, it does not need to be retrained to operate with a reference signal of different magnitude, or under system parameter change. Such properties make the DL control more attractive for applications that may undergo parameter variation, like sensor networks.

Scattering hyperspectral technology is a nondestructive testing method with many advantages. Here, we propose a method to improve the accuracy of egg freshness, research the influence of incident angles of light source on the accuracy and explain its mechanism. A variety of weak classifiers classify eggs based on the spectra after preprocessing and feature wavelength extraction to obtain three classifiers with the highest accuracy. The three classifiers are used as metamodels of stacking ensemble learning to improve the highest accuracy from 96.25% to 100%. Moreover, the highest accuracy of scattering, reflection, transmission and mixed hyperspectral of eggs are 100.00%, 88.75%, 95.00% and 96.25%, respectively, indicating that the scattering hyperspectral for egg freshness detection is better than that of the others. In addition, the accuracy is inversely proportional to the angle of incidence due that the smaller the incident angle, the camera collects a larger proportion of scattering light, which contains more biochemical parameters of an egg than that of reflection and transmission. These results are very important for improving the accuracy of non-destructive testing and selecting the incident angle of the light source, and have potential applications in online non-destructive testing.

Luminescence-based sensors for measuring oxygen concentration are widely used both in industry and research due to the practical advantages and sensitivity of this type of sensing. The measuring principle is the luminescence quenching by oxygen molecules, which results in a change of the luminescence decay time and intensity. In the standard approach, this change is related to an oxygen concentration using the Stern–Volmer equation. This equation, which in most of the cases is non-linear, is parametrized through device-specific constants. Therefore, to determine these parameters every sensor needs to be precisely calibrated at one or more known concentrations. This work explores an entirely new artificial intelligence approach and demonstrates the feasibility of oxygen sensing through machine learning. The specifically developed neural network learns very efficiently to relate the input quantities to the oxygen concentration. The results show a mean deviation of the predicted from the measured concentration of 0.5 % air, comparable to many commercial and low-cost sensors. Since the network was trained using synthetically generated data, the accuracy of the model predictions is limited by the ability of the generated data to describe the measured data, opening up future possibilities for significant improvement by using a large number of experimental measurements for training. The approach described in this work demonstrates the applicability of artificial intelligence to sensing technology and paves the road for the next generation of sensors.

The coronavirus disease 2019 (COVID-19) is the fastest transmittable virus caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The detection of COVID-19 using artificial intelligence techniques and especially deep learning will help to detect this virus in early stages which will reflect in increasing the opportunities of fast recovery of patients worldwide. This will lead to release the pressure off the healthcare system around the world. In this research, classical data augmentation techniques along with CGAN based on a deep transfer learning model for COVID-19 detection in chest CT scan images will be presented. The limited benchmark datasets for covid-19 especially in chest CT images is the main motivation of this research. The main idea is to collect all the possible images for covid-19 that exists until the very writing of this research and use the classical data augmentations along with CGAN to generate more images to help in the detection of the COVID-19. In this study, five different deep convolutional neural network-based models (AlexNet, VGGNet16, VGGNet19, GoogleNet, and ResNet50) have been selected for the investigation to detect the coronavirus infected patient using chest CT radiographs digital images. The classical data augmentations along with CGAN improve the performance of classification in all selected deep transfer models. The Outcomes show that ResNet50 is the most appropriate deep learning model to detect the COVID-19 from limited chest CT dataset using the classical data augmentation with testing accuracy of 82.91%.

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges such as low imaging quality and high variability. There is a critical need to develop advanced automatic US image analysis methods to enhance diagnostic accuracy and objectivity. Vision transformer, a recent innovation in machine learning, has demonstrated significant potential in various research fields, including general image analysis and computer vision, due to its capacity to process large datasets and learn complex patterns. Its suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformer and discusses its applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in its application in medical US image analysis. Vision transformer has shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and is expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

This paper presents an extension of the results obtained in previous work concerning the application of global optimization techniques to the design of finite strategic games with mixed strategies. In that publication the Fuzzy ASA global optimization method was applied to many examples of synthesis of strategic games with one previously specified Nash equilibrium, evidencing its ability in finding payoff functions whose respective games present those equilibria, possibly among others. That is to say, it was shown it is possible to establish in advance a Nash equilibrium for a generic finite state strategic game and to compute payoff functions that will make it feasible to reach the chosen equilibrium, allowing players to converge to the desired profile, con- sidering that it is an equilibrium of the game as well. Going beyond this state of affairs, the present article shows that it is possible to ”impose” multiple Nash equilibria to finite strategic games by following the same reasoning as before, but with a fundamental change: using the same fundamental theorem of Richard McKelvey, modifying the originally prescribed objective function and globally minimizing it. The proposed method, in principle, is able to find payoff functions that result in games featuring an arbitrary number of Nash equilibria, paving the way to a substantial number of potential applications.

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer’s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

This paper proposes a model based on gene expression programming for predicting discharge coefficient of triangular labyrinth weirs. The parameters influencing discharge coefficient prediction were first examined and presented as crest height ratio to the head over the crest of the weir (p/y), crest length of water to channel width (L/W), crest length of water to the head over the crest of the weir (L/y), Froude number (F=V/√(gy)) and vertex angle () dimensionless parameters. Different models were then presented using sensitivity analysis in order to examine each of the dimensionless parameters presented in this study. In addition, an equation was presented through the use of nonlinear regression (NLR) for the purpose of comparison with GEP. The results of the studies conducted by using different statistical indexes indicated that GEP is more capable than NLR. This is to the extent that GEP predicts the discharge coefficient with an average relative error of approximately 2.5% in such a manner that the predicted values have less than 5% relative error in the worst model.

On a global scale, food safety and security aspects entail to be considered throughout the farm to fork continuum considering food’s supply chain. Generally, the agri-food system is a multiplex network of interconnected features and processes, with a hard predictive rate, where maintaining the food’s safety is an indispensable element and is part of the Sustainable Development Goals (SDGs). It has led the scientific community to develop advanced applied analytical methods, such as Machine learning (ML) and Deep Learning (DL) techniques applied for assessing foodborne diseases. The main objective of this paper is to contribute to the development of the consensus version of ongoing research about the application of artificial intelligence tools in the domain of food-crops safety from an analytical point of view. Writing a comprehensive review for a more specific topic can also be challenging, especially when searching within the literature. To our knowledge, this review is the first to address this issue. This work consisted of conducting a unique and exhaustive study of the literature, using our TriScope Keywords-based Synthesis methodology. All available literature related to our topic was investigated according to our criteria of Inclusion and Exclusion. The final count of data papers was subject to deep reading and analysis to extract the necessary information to answer our research questions. Although many studies have been conducted, limited attention has been paid to outlining the applications of AI tools combined with analytical strategies for crop-based food safety specifically.

Background: Functional Movement Screening (FMS) allows for rapid assessment of an individual’s physical activity level and timely detection of sports injury risk. However, traditional functional movement screening often requires on-site assessment by experts, which is time-consuming and prone to subjective bias. Therefore, the study of automated functional movement screening has become increasingly important. Methods: In this study, we propose an automated assessment method for FMS based on the improved Gaussian Mixture Model (GMM). First, the oversampling of minority samples is conducted, the movement features are manually extracted from the FMS dataset collected with two Azure Kinect depth sensors, then we train the Gaussian mixture model with different scores (1 point, 2 points, 3 points) of feature data separately, finally, we conducted FMS assessment by the Maximum Likelihood estimation. Results: The improved GMM has a higher scoring accuracy (Improved GMM:0.8) compared to other models (Traditional GMM=0.38, Adaboost.M1=0.7, Naïve-Bayes=0.75), and the scoring results of improved GMM have a high level of agreement with the expert scoring (kappa=0.67). Conclusions: The results show that the proposed method based on the improved Gaussian mixture model can effectively perform the FMS assessment task and it is potentially feasible to use depth cameras for FMS assessment.

The prevalence of autism in children in the world is estimated as one per 62 children, higher levels reported in some countries. These children experience significant problems with the development of social, behavioural and verbal and non-verbal communication skills. The skills impairment levels varies from an individual to another and that made teaching autistics a challenge for caregivers such as teachers and relatives. Hence, there are quite a number of frameworks of a software learning systems which focus on gaining the children’s attention using representational visual illustration as a learning method instead of the textual form. However, majority of these tools are lacking the personalisation ability to suite everyone in the spectrum. Assistive technology offers an alternative way to attract children with autism. Therefore, this research is proposing an Adaptive Content Management Learning System (ACMLS) model to assist caregivers to produce, design and fine-tune or customise the learning materials appropriately so that the system interface and the materials are suitable for every individual in the spectrum according to each child personal profile aiming to make learning attractive and to contribute in improving their social, communication and behavioural skills and nonetheless, their attention level to the delivered educational topics. The ACMLS model design adopts four main components which are: (1) Design component: which covers the visual design, design principles and the mental model of the children with autism. (2) Technology component: which covers the assistive technology tools and the architecture of the ACMLS system. (3) Education component: Which covers the learning objectives, styles, strategies, methods and the cognitive model. (4) Participants component: which covers the main participants who’re playing a role in the ACMLS model such as: caregivers and children with autism.

The location and number data of individual fruit trees are critical for planting area investigation, fruit yield prediction, and smart orchard management and planning. These data are conventionally obtained through manual investigation and statistics with time-consuming and laborious effort. Object detection models in deep learning used widely in computer vision could provide an opportunity for accurate detection of individual fruit trees, which is essential for rapidly obtaining the data and reducing human operations errors. This study proposes an approach to detecting individual fruit trees and mapping their spatial distribution by integrating deep learning with unmanned aerial vehicle (UAV) remote sensing. UAV remote sensing collected high-resolution true-color images of fruit trees in the experimental pomelo tree orchards in Meizhou city, South China. An image dataset of deep learning samples of individual pomelo trees (IPTs) was constructed through visual interpretation and field investigation based on the fruit tree images captured by UAV remote sensing. Four different scales of YOLOv5 (YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) for object detection were selected to train, validate, and test on the image dataset of pomelo trees. The results show that the average precision (AP@0.5) of the four YOLOv5 models for validation reach 87.8%, 88.5%, 89.1%, and 90.7%, respectively. The larger the model scale, the higher the average accuracy of the detection result of validation. It suggests that YOLOv5x is a preferred high-accuracy model among the YOLOv5 family and is suitable to realize the detection of IPTs. The number of the IPTs in the study area was counted using YOLOv5x, and their spatial distribution map was made using the non-maximum suppression method and ArcGIS software. This study will provide primary data and technical support for smart orchard management in Meizhou city and other fruit-producing areas.

Well-being is one of the pillars of positive psychology, which is known to have positive effects not only on the personal and professional lives of individuals, but also on teams and organizations. Understanding and promoting individual well-being is essential for staff health and long-term success, but current tools for assessing subjective well-being rely on time-consuming surveys and questionnaires, which limit the possibility of providing the real-time feedback needed to raise awareness and change individual behavior. This paper proposes a framework for understanding the process of non-verbal communication in teamwork, using video data to identify significant predictors of individual well-being in teamwork. It relies on video acquisition technologies and state-of-the-art artificial intelligence tools to extract individual, relative, and environmental characteristics from panoramic video. Statistical analysis is applied to each time series, leading to the generation of a dataset of 125 features, which are then linked to PERMA (Positive Emotion, Engagement, Relationships, Meaning, and Accomplishments) surveys developed in the context of positive psychology. Each pillar of the PERMA model is evaluated as a regression or classification problem using machine learning algorithms. Our approach was applied to a case study, where 80 students collaborated in 20 teams for a week on a team task in a face-to-face setting. This enabled us to formulate several hypotheses identifying factors influencing individual well-being in teamwork. These promising results point to interesting avenues for research, for instance fusing different media for the analysis of individual well-being in teamwork.

Ransomware attacks have risen alarmingly, with encryption techniques becoming more complex. This paper introduces a novel detection model tailored for ransomware's distinctive characteristics. The Intel PIN tool extracts Windows API invocation sequences related to file operations. These sequences are used to construct n-grams, forming feature vectors enhanced by a new Class Feature Weighting (CFW) metric to improve malware detection. Preliminary results demonstrate elevated accuracy and precision versus existing methods. The major contributions are: (1) Introducing an innovative deep learning model for few-shot ransomware classification using entropy features and transfer learning. (2) Achieving high weighted F1-score in classifying ransomware variants into families with limited training data. (3) Demonstrating the potential of entropy-based features to capture intricacies lost in image-based approaches, improving detection of new strains.

In cotton cultivars, an insect that causes irreversible damage is the Spodoptera frugiperda, known as the fall armyworm. Since the visual detection of plants is a burdensome task for human inspection, the spectral information related to plant damage, registered on a spectral scale, can be useful. These measurements, associated with machine learning techniques, produce useful information for a rapid and non-invasive inspection method development. To contribute to this gap fulfillment, this paper proposes a machine learning framework to model the spectral response of cotton plants under the attack of the fall armyworm. Additionally, a theoretical model is presented, built from the results of the machine learning analysis, to infer this damage with up-to-date orbital sensors. The data was composed of the reflectance measurements collected at a cotton field with control plants and plants submitted to Spodoptera frugiperda damage. Their spectral response was recorded with a hand-held spectroradiometer ranging from 350 to 2,500 nm, for eight consecutive days. Different machine learning models were evaluated and the overall best model was defined by accuracies comparisons on a testing-set. A ranking approach was adopted based on the model accuracy, returning the most contributive wavelengths for the classification. Sequentially, an unsupervised neural network (Self-Organizing Map - SOM) was implemented to reduce data-dimensionality and assist in the definition of important spectral regions. The regions were associated with the spectral bands of the two sensors (OLI and MSI) and a theoretical model using a band simulation process with the overall best machine learning model was proposed. The results indicated that the Random Forest (RF) algorithm is the most suitable to predict cotton-plants damaged by insects and that the last day of analysis (8th day) was better to separate it, with F-measure equals 0.912. The ranking approach combined with the SOM method indicated the spectral regions at the red to near-infrared (650 to 1,350 nm) and shortwave infrared (1,570 to 1,640 nm) as the most important regions to the analysis. The proposed theoretical model simulated with the OLI and MSI sensor-bands returned an F-Measure of 0.865 and 0.886, respectively. In conclusion, this framework can be used to map cotton-plants under insect-attack. The theoretical model presents high accuracy to infer the insect-damaged on cotton plants based on multispectral bands from other sensors, being a useful tool for future research that intends to evaluate it in other areas and at different field scales.

Recent advances in artificial intelligence combined with behavioral sciences have led to the development of cutting-edge tools for recognizing human emotions based on text, video, audio, and physiological data. However, these data sources are expensive, intrusive, and regulated, unlike plants which have been shown to be sensitive to human steps and sounds. A methodology is proposed to use plants as human emotion detectors. Electrical signals from plants are tracked and labeled based on video data. Labeled data are then used for classification. MLP, biLSTM, MFCC-CNN, MFCC-ResNet, and additionally, Random Forests, 1-Dimensional CNN, and biLSTM without windowing models are set using a grid search algorithm with cross-validation. Finally, best-parameterized models are trained and used with the test set for classification. The performance of this methodology is measured with a case study with 54 participants, who were watching an emotionally charged video, as ground truth their facial emotions were simultaneously measured using face emotion analysis. The Random Forest model shows the best performance, particularly in recognizing high-arousal emotions, achieving an overall weighted accuracy of 55.2% and demonstrating high weighted recall in emotions such as fear 61.0% and happiness 60.4%. The MFCC-ResNet model offers decently balanced results, with Accuracy(MFCC-ResNet)=0.318 and Recall (MFCC-ResNet)=0.324. With the MFCC-ResNet model fear and anger are recognized with 75% and 50% recall respectively. Thus, using plants as an emotion recognition tool seems worth investigating, addressing both cost and privacy concerns.

In the present study, piecewise integrated composite (PIC) bumper beam for passenger cars was proposed and design optimisation process for composite bumper beam against IIHS test was carried out with the help of machine learning. Several elements in IIHS bumper FE model have been assigned to be references, in order to collect training data which, allow the machine learning model to study the method of predicting loading types of each finite element. 2-D and 3-D implementations were provided by machine learning models, which determined stacking sequences of each finite element in PIC bumper beam. It was found that the PIC bumper beam, which was designed by machine learning model has direct impact on reducing the possibility of failure as well as increasing bending strength effectively than conventional composite bumper beam. Moreover, 3-D implementation produced better results compared with 2-D implementation since it was preferable to choose loading type information which was achieved from surroundings when the target elements were located either at corner or junction of planes instead of using information came from the same plane of target.

Nowadays, the Internet of Things (IoT) devices and applications have rapidly expanded worldwide due to their benefits in improving the business environment, industrial environment, and people's daily lives. However, the IoT devices are not immune to malicious network traffic, which causes potential negative consequences and sabotages IoT operating devices. Therefore, developing a method for screening network traffic is necessary to detect and classify malicious activity to mitigate its negative impacts. Therefore, this research proposes a predictive machine learning model to detect and classify network activity in an IoT system. Specifically, our model distinguishes between normal and anomaly network activity. Furthermore, it classifies network traffic into five categories, normal, Mirai attack, denial of service (DoS) attack, Scan attack, and man-in-the-middle (MITM) attack. Five supervised learning models were implemented to characterize their performance in detecting and classifying network activities for IoT systems. This includes models shallow neural networks (SNN), decision trees (DT), bagging trees (BT), support vector machine (SVM), and k-nearest neighbor (kNN). The learning models were evaluated on a new and broad dataset for IoT attacks, the IoTID20 dataset. Besides, a deep feature engineering process was applied to the dataset to improve the accuracy of the learning models. Our experimental evaluation exhibited an accuracy of 100% recorded for the detection using all implemented models and an accuracy of 99.4%-99.9% recorded for the classification process.

Corona Virus Infectious Disease (COVID-19) is newly emerging infectious disease. This disease is known to the globe in early 2019. Poor status of mental health is often caused by unemployment, ongoing socio-economic condition. Poor mental health may even accelerate the process of panic attack. It has been happening rapidly during COVID-19. It has a great effect on human health. This paper utilizes multiple related factors those have impact on causing panic attack. Recurrent Neural Network (RNN) based framework is utilized in this paper that assembles multiple RNN layers along with other parameters into a single platform. This method is implemented by capturing interfering factors and predicts panic attack tendency of people during COVID-19. Early prediction of panic attacks may assist in saving life from unwanted circumstances.

Due to the complex underground environment, pumping machines are prone to produce numerous failures. The indicator diagrams of faults are similar in a certain degree, which produces indistinguishable samples. As the samples increases, manual diagnosis becomes difficult, which decreases the accuracy of fault diagnosis. For accurately and quickly judging the fault type, we propose an improved adaptive activation function and apply it to five types of neural networks. The adaptive activation function improves the negative semi-axis slope of the ReLU activation function by combining the gated channel conversion unit to improve the performance of the deep learning model. The proposed adaptive activation function is compared with the traditional activation function through the fault diagnosis data set and the public data set. The results show that the activation function has better nonlinearity, can improve the generalization performance of deep learning model, the accuracy of fault diagnosis. In addition, the proposed adaptive activation function can also be well embedded in other neural networks.

Federated learning trains a neural network model using the client's data to maintain the benefits of centralized model training, while maintaining the privacy. However, if the client data are not independently and identically distributed (non-IID) because of different environments, the accuracy of the model may suffer from client drift during training owing to discrepancies in each client's data. This study proposes a personalized federated learning algorithm based on the concept of multitask learning to divide each client model into two layers: a feature extraction layer and a category prediction layer. The feature extraction layer maps the input data to a low-dimensional feature vector space. Furthermore, the parameters of the neural network are aggregated with those of other clients using an adaptive method. The category prediction layer maps low-dimensional feature vectors to the label sample space, with its parameters remaining unaffected by other clients to maintain client uniqueness. The proposed personalized federated learning method produces faster learning model convergence rates and higher accuracy rates for the non-IID datasets in our experiments.

The body of scientific literature continues to grow annually. Over 1.5 million abstracts of biomedical publications were added to the PubMed database in 2021. Therefore, developing cognitive systems that provide a specialized search for information in scientific publications based on subject area ontology and modern artificial intelligence methods is urgently needed. We previously developed a web-based information retrieval system, ANDDigest, designed to search and analyze information in the PubMed database using a customized domain ontology. This paper presents an improved ANDDigest version that uses fine-tuned PubMedBERT classifiers to enhance the quality of short name recognition for molecular-genetics entities in PubMed abstracts on eight biological object types: cell components, diseases, side effects, genes, proteins, pathways, drugs, and metabolites. This approach increased average short name recognition accuracy by 13%. The new ANDDigest version (01.2022) has a web interface and is freely available to users at https://anddigest.sysbio.ru/.

The spread of the Coronavirus pandemic has been accompanied by an infodemic. The false information that is embedded in the infodemic affects people’s ability to have access to safety information and follow proper procedures to mitigate the risks. This research aims to target the falsehood part of the infodemic, which prominently proliferates in news articles and false medical publications. Here, we present NeoNet, a novel supervised machine learning text mining algorithm that analyzes the content of a document (news article, a medical publication) and assigns a label to it. The algorithm is trained by TFIDF bigram features which contribute a network training model. The algorithm is tested on two different real-world datasets from the CBC news network and Covid-19 publications. In five different fold comparisons, the algorithm predicted a label of an article with a precision of 97-99 %. When compared with prominent algorithms such as Neural Networks, SVM, and Random Forests NeoNet surpassed them. The analysis highlighted the promise of NeoNet in detecting disputed online contents which may contribute negatively to the COVID-19 pandemic.

Indoor scene recognition has great significance for intelligent applications such as mobile robots, location-based services (LBS) and so on. Wherever we are or whatever we do, we are under a specific scene. The human brain can easily discern a scene with a quick glance. However, for a machine to achieve this purpose, on one hand, it often requires plenty of well-annotated data which is time-consuming and labor-intensive. On the other hand, it is hard to learn effective visual representations due to large intra-category variation and inter-categories similarity of indoor scenes. To solve these problems, in this paper, we adopted an unsupervised visual representation learning method which can learn from unlabeled data with a Siamese Convolutional Neural Network (Siamese ConvNet) and graph-based constraints. Specifically, we first mined relationships between unlabeled samples with a graph structure. And then, these relationships can be used as supervision for representation learning with a Siamese network. In this method, firstly, a k-NN graph would be constructed by taking each image as a node in the graph and its k nearest neighbors are linked to form the edges. Then, with this graph, cycle consistency and geodesic distance would be considered as criteria for positive and negative pairs mining respectively. In other words, by detecting cycles in the graph, images with large differences but in the same cycle can be considered as same category (positive pairs). By computing geodesic distance instead of Euclidean distance from one node to another, two nodes with large geodesic distance can be regarded as in different categories (negative pairs). After that, visual representations of indoor scenes can be learned by a Siamese network in an unsupervised manner with the mined pairs as inputs. In order to evaluate the proposed method, we tested it on two scene-centric datasets, MIT67 and Places365. Experiments with different number of categories have been conducted to excavate the potential of proposed method. The results demonstrated that semantic visual representations for indoor scenes can be learned in this unsupervised manner. In addition, with the learned visual representations, indoor scene recognition models trained with the learned representations and a few of labeled samples can achieve competitive performance compared to the state-of-the-art approaches.

Efficient textual data distributions (TDD) alignment and generation are open research problems in textual analytics and NLP. It is presently difficult to parsimoniously and methodologically confirm that two or more natural language datasets belong to similar distributions, and to identify the extent to which textual data possess alignment. This study focuses on addressing a segment of the broader problem described above by applying multiple supervised and unsupervised machine learning (ML) methods to explore the behavior of TDD by (i) topical alignment, and (ii) by sentiment alignment. Furthermore we use multiple text generation methods including fine-tuned GPT-2, to generate text by topic and by sentiment. Finally we develop a unique process driven variation of Kullback-Leibler divergence (KLD) application to TDD, named KL Textual Distributions Contrasts (KL-TDC) to identify the alignment of machine generated textual corpora with naturally occurring textual corpora. This study thus identifies a unique approach for generating and validating TDD by topic and sentiment, which can be used to help address sparse data problems and other research, practice and classroom situations in need of artificially generated topic or sentiment aligned textual data.

Building energy consumption plays an essential role in urban sustainability. The prediction of the energy demand is also of particular importance for developing smart cities and urban planning. Machine learning has recently contributed to the advancement of methods and technologies to predict demand and consumption for building energy systems. This paper presents a state of the art of machine learning models and evaluates the performance of these models. Through a systematic review and a comprehensive taxonomy, the advances of machine learning are carefully investigated and promising models are introduced.

Myofascial Pain Syndrome (MPS) is a prevalent chronic pain disorder characterized by myofascial trigger points (MTrPs). Current diagnosis relies on manual detection of MTrPs, which has low inter-rater reliability. This study aims to enhance diagnosis through machine learning (ML) and a combination of texture-features extracted from B-mode ultrasound (B-mode-US) images. Four texture-features were investigated: statistical-features, and their combination with Gabor, local binary (LBP), and SEGL, LBP + gray-level-co-occurrence-matrices + Edge for the classification of MTrPs on the B-mode-US images. B-mode-US images of trapezius muscles (n=90) were examined for MTrPs and healthy muscle. Three methods of LBP, SEGL, and Gabor were separately calculated for each B-mode-US image. Then, the statistical-features (e.g., entropy) were calculated over the B-mode-US images and those three methods. Seven Machine learning (ML) classifiers (e.g., neural network) with the calculated statistical-features were applied to discriminate MTrPs from healthy muscle. Additionally, traditional statistical analysis (i.e., ANOVA) was calculated between statistical-features within each method. The results indicated that the combination of statistical-features effectively discriminated between MTrPs and healthy muscles, based on traditional statistical analysis. However, ML classifiers struggled due to high variation and similar mean values among them. This discrepancy between them prompts further exploration of US texture-based automated ML for MTrPs diagnosis.

This paper focuses on the new users cold-start issue in the context of recommender systems. New users who do not receive pertinent recommendations may abandon the system. In order to cope with this issue, we use active learning techniques. These methods engage the new users to interact with the system by presenting them with a questionnaire that aim to understand their preferences to the related items. Example of questions may include "do you like this book?" and the users answer,"yes", "no", "I have not read it (unknown)", will reflect the degree of interest for the item by the users. As a consequence, the system can learn the users' preferences from these answers. The goal of active learning is to correctly choose the questions (items) for users. Thus it is necessary to personalize the questionnaires to retrieve the maximum information by avoiding "unknown" answers. In this paper, we propose an active learning technique that exploits past users' interests and past users' predictions in order to identify the best questions to ask.

ABSTRACT Background It is important to be able to predict, for each individual patient, the likelihood of later metastatic occurrence, because the prediction can guide treatment plans tailored to a specific patient to prevent metastasis and to help avoid under- or over-treatment. Deep Neural Network (DNN) learning, commonly referred to as deep learning, has become popular due to its success in image detection and prediction, but questions such as whether deep learning outperforms other machine learning methods when using non-image clinical data remain unanswered. Grid search has been introduced to deep learning hyperparameter tunning for the purpose of improving its prediction performance, but the effect of grid search on other machine learning methods are under-studied. In this research, we take the empirical approach to study the performance of deep learning and other machine learning methods when using non-image clinical data to predict the occurrence of breast cancer metastasis (BCM) 5, 10, or 15-years after the initial treatment. We developed DNN models as well as models using 9 other machine learning methods including Naive Bayes (NB), Logistic Regression (LR), Support Vector Machine (SVM), LASSO, Decision Tree (DT), k-Nearest Neighbors (KNN), Random Forrest (RF), AdaBoost (ADB), and XGBoost (XGB). We used grid search to tune hyperparameters for all methods. We then compared the deep learning models to the models trained using the 9 other machine learning methods. Results Based on the mean test AUC results, DNN ranks 6th, 4th, and 3rd when predicting 5-year, 10-year, and 15-year BCM respectively, out of 10 machine learning methods. The top performing methods in predicting 5-year BCM are XGB(1^st), RF(2^nd), and KNN(3^rd). For predicting 10-year BCM the top performers are XGB (1^st), RF(2^nd), and NB(3^rd) . Finally, for 15-year BCM the top performers are SVM (1^st), LR and LASSO (tied for 2^nd), and DNN (3^rd). The ensemble methods RF and XGB outperform other methods when data are less balanced, while SVM, LR, LASSO, and DNN outperform other methods when data are more balanced. Our statistical testing results show that at a significance level of 0.05 DNN overall performs no worse than other machine learning methods when predicting 5-year, 10-year, and 15-year BCM. Conclusions Our results show that deep learning with grid search overall performs at least as well as other machine learning methods when using non-image clinical data. It is interesting to note that some of the other machine learning methods such as XGB, RF, and SVM are very strong competitors of DNN when incorporating grid search. It is also worth noting that the computation time required to do grid search with DNN is way more than that required to do grid search with the other 9 machine learning methods.

In the field of maneuvering target tracking, the combined observations of azimuth and Doppler may cause weak observation or non-observation in the application of traditional target tracking algorithms. Additionally, traditional target-tracking algorithms require pre-defined multiple mathematical models to accurately capture the complex motion states of targets, while model mismatch and unavoidable measurement noise lead to significant errors in target state prediction. To address those above challenges, in recent years, the target-tracking algorithms based on neural networks, such as recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and Transformer architectures, have been widely used for their unique advantages to achieve accurate predictions. To better model the nonlinear relationship between the observation time series and the target state time series, as well as the contextual relationship among time series points, we present a deep learning algorithm called recursive downsample-convolve-interact neural network (RDCINN) based on convolutional neural network (CNN) that downsamples time series into sub-sequences and extracts multi-resolution features to enable the modeling of complex relationships between time series, which overcomes the shortcomings of traditional target-tracking algorithms in using observation information inefficiently due to weak observation or non-observation. The experimental results show that our algorithm outperforms other existing algorithms in the scenario of strong maneuvering target tracking with the combined observations of azimuth and Doppler.

Most natural language processing (NLP) tasks operate an input sentence as a sequence with token-level embeddings and features, despite its clausal structures. Taking Abstract Meaning Representation (AMR) parsing as an example, recent parsers are empowered by Transformers and pre-trained language models, but long-distance dependencies (LDDs) introduced by long sequences are still open problems. We argue that LDDs are not superficially blamed on the sequence length but are essentially related to the internal clause hierarchy. Typically, non-verb words in a clause cannot depend on words outside, and verbs from different but related clauses have much longer dependencies than those in the same clause. With this intuition, we introduce a type of clausal feature, hierarchical clause annotation (HCA), into AMR parsing and propose two HCA-based approaches, HCA-based self-attention (HCA-SA) and HCA-based curriculum learning (HCA-CL), to integrate HCA trees of complex sentences for addressing LDDs. We conduct extensive experiments on two in-distribution (ID) AMR datasets (AMR 2.0 and AMR 3.0) and three out-of-distribution (OOD) ones (TLP, New3, and Bio). Experimental results show that our HCA-based approaches achieve significant and explainable improvements against the baseline model and outperform the state-of-the-art (SOTA) model when encountering sentences with complex clausal structures that introduce most LDD cases.

In the achievement of the Sustainable Development Goals (SDGs), education plays a fundamental role. However, traditional methodologies do not favor the enrichment and personal development essential to promote global awareness. The use of active methodologies based on experiences improve the quality of learning. This work describes the design, implementation, and evaluation of the acquired knowledge of a didactic proposal for non-formal education as a support for regulated education based on botany content. Firstly, a workshop was held, where young people participated directly in developing field work with a real scientific methodology. Subsequently, a group of students was chosen to be interviewed to obtain a global vision of the learning they obtained. The motivation of the students was quite positive, which allowed us to obtain voluntary participation in the field work and gave the students a participative attitude throughout the development of the workshops. Four months later, this positive attitude remained during their direct involvement in various activities, and the students still remembered the fundamental content discussed. Relating the didactic proposal to its immediate environment was shown to increase interest in learning and value in its own context. The results of this educational experience have been very positive, as knowledge was acquired, and interest in the preservation of the environment and the profession of a researcher was promoted.

Water plays a vital role in the healthy growth of pears. Early detection of water stress can play a significant role in the timely management of water deficiency for pear yield. Most current methods are labour-intensive, time-consuming, only provide point measurements, and could be destructive. In this research, a real-time non-destructive method using a push-broom hyperspectral system (400-1000nm) was used to collect hyperspectral image data and detect the water stress of the pear seedling leaves. To build a reliable prediction model, machine learning techniques were used. The Successive Projections Algorithm (SPA) was applied for optimal wavelength selection. In particular, CNN was applied to obtain the features of key wavelengths. Both the CNN features and key wavelengths were put into RR-MLR, BLR and ENN for analysis. The training accuracy of the three modellings all reach the accuracy above 70% after about 100 epochs, while combination of CNN features outperformed the mere main spectra analysis. This research demonstrated that hyperspectral imaging coupled with machine learning techniques could be applied to predict the water content of pear leaves predict non-destructively.

Oral Squamous Cell Carcinoma is one among the most common cancer and early detection is the main key to avoid deaths. Automated diagnostic tools that process the histopathological images of a patient to detect abnormal oral lesions will be very much useful for the clinicians. A deep learning framework have been designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed Swarm Intelligence technique called Modified Gorilla Troops Optimizer. Various optimization algorithms are implemented in literature for optimal parameter identification, weights updating and feature selection in deep learning models, but this work focuses on usage of optimization algorithm as intermediate layer that transforms the extracted features into the features that are more suitable for classification. Three datasets totally comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures namely InceptionV2, MobileNetV3, and EfficientNetB3 are investigated as feature extraction layers. Two fully connected Neural Network layers along with batch normalization and dropout are used as classification layers. Among the investigated feature extraction models, MobileNetV3 performs well in all the three datasets with the highest accuracy of 0.89. Usage of the proposed Modified Gorilla Troops Optimizer as an intermediate layer boosts this accuracy to 0.95.

Background: Silent MRA has shown promising results in evaluating the stents used for intracranial aneurysm treatment. A deep learning-based algorithm was recently introduced by GE. The purpose of this study was to compare the performance of several MRA techniques in lumen visibility in silicone models with flow diverter stents. Methods: Two Surpass Evolve stents of different sizes were implanted in two silicone tubes. The tubes were placed in separate boxes in straight position and in two different curve configurations and connected to a pulsatile pump to construct a flow loop. Using a GE 3.0T scanner, TOF and silent MRA images were acquired, and deep learning reconstruction was applied to the silent MRA dataset. Intra-luminal signal intensity in the stent (SIin-stent), in the tube outside the stent (SIvessel) and of the background (SIbg) were measured for each scan. Results: The SIin-stent/SIbg and SIin-stent/SIv ratio were higher on silent scans and DL-based reconstructions than on TOF images. The stent tips created severe artefacts on TOF images, which could not be observed on silent scans. Conclusions: Our study demonstrated that the DL algorithm improved the quality of the silent technique in evaluating the flow diverter stent patency.

Aerosol Optical Thickness (AOT) is one of the critical factors for global atmospheric conditions, climate change, and air pollution. AOT has been exposed as a major component of air pollution in Bangladesh. This paper aims to map the seasonal distribution of AOT from 2002-2022 and to explore the internal relationship between AOT and ten air pollutants using remote sensing and machine learning tools. These ten air pollutants are Particulate matter (PM2.5), Methane (CH4), Carbon monoxide (CO), Nitrogen dioxide (NO2), Formaldehyde (HCHO), Ozone (O3), Sulfur dioxide (SO2), Aerosol Particulate Radius (APR), Nitrogen oxide (NOx) and Black carbon (BC). The results show that the concentrations of AOT were higher in December-January-February (mean value 0.50) and March-April-May (mean value 0.50) seasons, mostly in the central, western, and southern parts of Dhaka, Narayanganj, and Munshiganj districts. AOT was a bit less in June-July-August (mean value 0.33) and September-October-November (mean value 0.37). This paper also revealed that the AOT was correlated positively with PM2.5 (0.60), CH4 (0.80), NO (0.76), and BC (0.83) while correlated negatively with CO (-0.66), HCHO (-0.16), SO2 (-0.41), APR (-0.48), and NOx (-0.20). From the machine learning, the Rational quadratic GPR (RME-0.0024, MAE-0.0015, R2-0.96), Matern 5/2 GPR (RMSE-0.0023, MAE-0.0015, R2-0.96), and Squared Exponential GPR (RMSE-0.0015, MAE-0.0015, R2-0.96) were found good classifiers to predict AOT. UN agencies, government line departments, and local and regional development councils for air pollution mitigation and long-term protective measures may use the paper's key results.

With the escalation of size and complexity of modern Denial of Service attacks, there is a need for research in the context of Machine Learning (ML) used in attack execution and defense against such attacks. This paper investigates the potential use of ML in generating behavioral telemetry data using Long-Short Term Memory network and spoofing requests for the analyzed traffic to look legitimate. For this research, a custom testing environment was built, that listens for mouse and keyboard events and analyzes them accordingly. While the economic feasibility of this attack currently limits its immediate threat, advancements in technology could make it more cost-effective for attackers in the future. Therefore, proactive development of countermeasures remains essential to mitigate potential risks and stay ahead of evolving attack methods.

Due to the significant price difference, expensive oils like olive oil are often blended with cheaper edible oils. This practice of adulteration in edible oils, aimed at increasing profits for producers, poses a major concern for consumers. Furthermore, adulteration in edible oils can lead to various health issues impacting consumer well-being. In order to meet the requirements of fast, non-destructive, universal, accurate and reliable quality testing for edible oil, the oblique-incidence reflectivity difference (OIRD) method combined with machine learning algorithms was introduced to detect a variety of edible oils. The prediction accuracy of Gradient Boosting, K-Nearest Neighbor, and Random Forest models exceeded 95%. Experimental results indicate that the OIRD method can serve as a powerful tool for detecting edible oils.

With the recent advances in Machine Learning (ML), several models have been successfully applied to financial and accounting data to predict the likelihood of companies’ bankruptcy. However, time series have received little attention in literature with a lack of studies on the application of Deep Learning sequence models as Recurrent Neural Networks (RNN) and the recent Attention-based models in general. In this research work, we investigated the application of Long Short Term Memory (LSTM) networks to exploit time series of accounting data for bankruptcy prediction. The main contributions of our work are the following: a) we have proposed a Multi-head LSTM that models each financial variable in a time window independently and compared it with a single-input LSTM and other traditional ML models. The Multi-head LSTM outperforms all the other models; b) We identify the optimal time series length for bankruptcy prediction to be equal to 4 years of accounting data; c) We made public the dataset we used for the experiments that include data from 8262 different public companies in the American stock market generated in the period between 1999-2018. Furthermore, we prove the efficacy of the Multi-head LSTM models in terms of lower false positives and better division of the two classes.

Early detection of wildfires has been limited using the sun-synchronous orbit satellites due to their low temporal resolution and wildfires’ fast spread in the early stage. NOAA’s geostationary weather satellites GOES-R can acquire images every 15 minutes at 2km spatial resolution, and have been used for early fire detection. However, advanced processing algorithms are needed to provide timely and reliable detection of wildfires. In this research, a deep learning framework, based on Gated Recurrent Units (GRU), is proposed to detect wildfires at early stage using GOES-R dense time series data. GRU model maintains good performance on temporal modelling while keep a simple architecture, makes it suitable to efficiently process time-series data. 36 different wildfires in North and South America under the coverage of GOES-R satellites are selected to assess the effectiveness of the GRU method. The detection times based on GOES-R are compared with VIIRS active fire products at 375m resolution in NASA’s Fire Information for Resource Management System (FIRMS). The results show that GRU-based GOES-R detections of the wildfires are earlier than that of the VIIRS active fire products in most of the study areas. Also, results from proposed method offer more precise location on the active fire at early stage than GOES-R Active Fire Product in mid-latitude and low-latitude regions.

There are understandable signs that the COVID-19 pandemic has had a straining impact on the higher education sector in South Africa and the far reaches of the world. However, the necessary preparation and skills of lecturers and students are considered a major problem when integrating online education into teaching. The aim of the paper is to examine (Science, Technology, Engineering, Mathematics) STEM lecturers' experiences with digital assessments and perspectives on the continuity of digital transformation in the higher education sector in the post-COVID-19 era at one of South Africa’s rural universities. In 2022, a survey of ten (10) lecturers was conducted and the reports were also consulted by four (4) e-learning practitioners to obtain their views on the use of online learning and contact courses in the post-pandemic period. A qualitative research approach was used to understand the puzzling issues faced by STEM lecturers at a previously disadvantaged institution in Limpopo Province. The results of this study show that there is a puzzling conundrum that hinders the integration of effective online learning. Furthermore, online education as the new normal in the post-COVID-19 era seems unattainable due to extremely complex and difficult-to-understand mathematical symbols. Software and tools proved to be limitations in terms of establishing an interactive learning environment for students and lecturers on online learning platforms. Lecturers’ use of learning and teaching platforms deteriorated due to numerous unknown challenges, but also the tightening of COVID-19 restrictions. Furthermore, the results showed that science and mathematics lecturers believe that contact learning remains irreplaceable across generations and eras as some are not technology enthusiasts. This paper recommends that the lack of technological systems as well as technological resistance and reluctance to adopt transformative pedagogy and innovative practices should not be viewed as a thorny issue to end the dominance of online education in STEM courses.

Modern power system integrates more and more new energy and use a large number of power electronic equipment. This makes it face more challenges in online optimization and real-time control. Deep reinforcement learning(DRL) has the ability of processing big data and high-dimensional features, as well as the ability of independently learning and optimizing decision-making in complex environments. In this paper, we explore DRL based online combination optimization method of grid section for large complex power system. In our method, to improve the convergence speed of the model, we propose to discretize the output action of the unit and simplify the action space. We also design a reinforcement learning loss function with strong constraints to further improve the convergence speed of the model and facilitate the algorithm to obtain the stable solution. Moreover, to avoid the local optimal solution problem caused by the discretization of the output action, we propose to use the annealing optimization algorithm to make the granularity of the unit output finer. We verify our method on IEEE 118-bus system. The experimental results show that our model has fast convergence speed and better performance, and can obtain stable solutions.

Augmented reality (AR) offers an accessible, inexpensive, and rich user experience that has the potential to engage end-users in an immersive environment. Along with vivid visualizations coupled with virtual agents, this technology further develops learning interest in end-users, guides them in various tasks, and boosts motivation and productivity. In this study, we leverage the deep penetration of mobile phones in daily lives and their advanced features to design, develop and demonstrate an AR application (CirculAR) that offers unique user-environment interaction in a gamified way. CirculAR combines learning with enjoyment to help end-users understand fundamental sustainability and circular economy principles. The application has been showcased in a controlled environment to heterogenous audiences and has been shown to improve end-user engagement and motivation. First, participants older than 18 were recruited to showcase the technology acceptance and engagement towards circular economy principles through AR. Then, students aged 5 to 15 years old, along with their parents and educators, were invited to a treasure hunt game where our virtual agent ARis guided them through a map full of virtual experiences. Assessment and evaluation were performed through a survey and a questionnaire. The outcome of their analysis showcased an increase in the dedication and enjoyment of the performed activities, engagement and learning attributes given the AR virtual agent supporting functionalities. Observations during showcasing reported a need for more commitment from the younger audience compared to the older one. This application contributes to the discourse on mobile AR as a tool for the education of novel concepts with a high impact on our daily lives and decisions and aims to shed light on the design principles of educative tools.

(1) Background: Although diagnostic criteria for massive hemorrhage with organ dysfunction such as disseminated intravascular coagulation associated with delivery have been empirically established based on clinical findings, strict logic has yet to be used to establish numerical criteria. (2) Methods: A dataset of 107 deliveries with ≥2,000 g of blood loss, among 13,368 deliveries from nine national perinatal centers in Japan between 2020 and 2023 was obtained. Twenty-three patients had fibrinogen levels <170 mg/dl, which is the initiation of coagulation system failure per our previous reports. Three of these patients had hematuria. We used six machine learning methods to identify the borderline criteria dividing the fibrinogen/fibrin/fibrinogen degradation product (FDP) planes, using 15 coagulation fibrinolytic factors. (3) Results: The boundaries of hematuria development on a two-dimensional plane of fibrinogen and FDP were obtained. If the FDP–fibrinogen/3–60 (mg/dl) value is positive, this indicates hematuria; otherwise, the case is non-hematuria, as demonstrated by the support vector machine method that seemed the most appropriate. (4) Conclusions: The borderline criterion dividing the fibrinogen/FDP plane for patients with hematuria that could be considered organ dysfunction in massive hemorrhage during delivery was obtained using artificial intelligence, and this method seemed to be useful.

Visualising textual content could be helpful to professionals as well as amateurs across several fields. However, training a text-to-image generator in the mainstream domain requires large amounts of paired text-image and data, which is too expensive to collect since labeling millions of images and videos can be tiresome. GANs like StackGAN and StyleGAN can be considered as solutions to generate images from text. But the images generated may be of low accuracy and resolution, and the entire processing can be highly time-consuming. Moreover, image generation is a notion that is still being researched. Hence, the process of developing a Video Generation model necessitates substantial research. Despite the need for such a model, modern technology has lagged behind the solutions to this problem. This proposal suggests combining two methods, Text modification for Action Definition (TexAD) and SeQuential Image Generation for Video Synthesis (SQIGen). The proposed solution synthesises a sequence of images from textual information feeds and combines these images to create a video. TexAD uses Natural Language Processing and Deep Learning techniques to process, classify and modify text data. SQIGen is an extension of the VQGAN+CLIP neural network architecture that generates a sequence of images from the modified text data

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it becomes crucial to identify ion-binding sites. Accurate identification of protein-ion binding sites helps us to understand proteins’ biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32−, SO42−, PO43−, NO2−). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46% respectively in F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools producing prediction results for a hundred sequences for a specific ion in under ten minutes.

NMR spectral datasets, especially in systems with limited samples, can be difficult to interpret if they contain multiple chemical components (phases, polymorphs, molecules, crystals, glasses, etc…) and the possibility of overlapping resonances. In this paper, we benchmark several blind source separation techniques for analysis of NMR spectral datasets containing negative intensity. For benchmarking purposes, we generated a large synthetic datasbase of quadrupolar solid-state NMR-like spectra that model spin-lattice T1 relaxation or nutation tip/flip angle experiments. Our benchmarking approach focused exclusively on the ability of blind source separation techniques to reproduce the spectra of the underlying pure components. In general, we find that FastICA (Fast Independent Component Analysis), SIMPLISMA (SIMPLe-to-use-Interactive Self-modeling Mixture Analysis), and NNMF (Non-Negative Matrix Factorization) are top-performing techniques. We demonstrate that dataset normalization approaches prior to blind source separation do not considerably improve outcomes. Within the range of noise levels studied, we did not find drastic changes to the ranking of techniques. The accuracy of FastICA and SIMPLISMA degrades quickly if excess (unreal) pure components are predicted. Our results indicate poor performance of SVD (Singular Value Decomposition) methods, and we propose alternative techniques for matrix initialization. The benchmarked techniques are also applied to real solid state NMR datasets. In general, the recommendations from the synthetic datasets agree with the recommendations and results from the real data analysis. The discussion provides some additional recommendations for spectroscopists applying blind source separation to NMR datasets, and for future benchmark studies. Applications of blind source separation to NMR datasets containing negative intensity may be especially useful for understanding complex and disordered systems with limited samples and mixtures of chemical components.

To support pathologists in breast tumor diagnosis, deep learning plays a crucial role in the development of histological whole slide image (WSI) classification methods. However, automatic classification is challenging due to the high-resolution data and the scarcity of representative training data. To tackle these limitations, we propose a deep learning-based breast tumor gigapixel histological image multi-classifier integrated with a high-resolution data augmentation model to process the entire slide by exploring its local and global information and generating its different synthetic versions. The key idea is to perform classification and augmentation in feature latent space, reducing the computational cost while preserving the class label of the input. We adopt a deep learning-based multi-classification method and evaluate the contribution given by a Conditional Generative Adversarial Network-based data augmentation model on the classifier’s performance for three tumor classes in the BRIGHT Challenge dataset. The proposed method has allowed us to achieve an average F1 equal to 69.5, considering only the WSI dataset of the Challenge. The results are comparable to those obtained by the Challenge winning method (71.6), also trained on the annotated tumor region dataset of the Challenge.

The modern supply chain (SC) is growing in terms of data, devices, users, and stakeholders, which introduced new security challenges and threats, especially with the reliance on centralized servers or cloud platforms. In addition, increased trust among system participants exposes the SC to a higher risk of vulnerabilities which require strong security measures. This article proposes a hybrid security framework for SC systems, BC-DRLzSC, that integrates Blockchain (BC) and Deep Reinforcement Learning (DRL) designed to operate in a zero trust (ZT) environment. In particular, we propose a decentralized BC-based approach integrated with smart contracts to manage system participant registration and authentication and to control access to system resources. BC-DRLzSC adopts a ZT architecture to reinforce SC security, which can be achieved with an advocate to verify each entity’s trustworthiness before granting or retaining access to system resources. Incorporating the ZT architecture, with BC and DRL, can potentially and significantly bolster SC system security. DRL is employed to develop a proactive attack detection model that continuously monitors the incoming traffic from authenticated nodes within the network and predicts any malicious actions. Finally, we evaluate the performance of our proposed DRL solution using the NSL-KDD dataset.

Social media platforms are increasingly enabling the propagation of content from groups related to drug use, thus posing risks for the wider population and, in particular, individuals who are amenable to drug use and drug addiction. The detection of drug use content on social media platforms is a priority for governments, technology companies, and drug law enforcement organizations. To counter this issue, various techniques have been developed to identify and promptly remove drug use content, while also blocking its creators from network access. In this paper, we introduce a manually annotated Twitter dataset, comprising 156,521 tweets published between 2008 and 2022, specifically compiled for the purpose of drug use detection. The dataset underwent annotation by several group of expert annotators who classified the tweets as either drug use or non-drug use. Exploratory data analysis was conducted to comprehend the dataset's characteristics. Various classification algorithms, including SVM, XGBoost, RF, NB, LSTM, and BERT were employed using the dataset. Among the traditional machine learning models, SVM utilizing term frequency-inverse document frequency features achieved the highest F1-Score (0.9017). However, BERT with textual features concatenated with numerical and categorical features in ensemble method surpassed the performance of traditional models, attaining F1-Score of 0.9112. To facilitate future research and enhance English online drug use classification accuracy, the dataset will be made publicly available.

The continuous and precise mapping of glacier calving fronts is essential for monitoring and understanding rapid glacier changes in Antarctica and Greenland, which have the potential for significant sea level rise within the current century. This effort has been mostly restricted to the slow and painstaking manual digitalization of the calving front positions in thousands of satellite imagery products. Here, we have developed a machine learning toolkit to robustly and automatically detect glacier calving front margins in satellite imagery. The toolkit is based on semantic image segmentation using Convolutional Neural Networks (CNN) with a modified U-Net architecture to isolate the calving fronts from satellite images after having been trained with a dataset of images and their corresponding manually-determined calving fronts. As a case study we train our neural network on a varied set Landsat images with lowered resolutions from Jakobshavn, Sverdrup, and Kangerlussuaq glaciers, Greenland and test the results on novel images from Helheim glacier, Greenland to evaluate the performance of the approach. The neural network is able to identify the calving front in new images with a mean deviation of 96.3 m from the true fronts, equivalent to 1.97 pixels on average, while the corresponding error for manually-determined fronts on the same resolution images is 92.5 m. We find that the trained neural network significantly outperforms common edge detection techniques, and can be used to continuously map out calving-ice fronts with a variety of data products.

Deep learning is an emerging area of machine learning (ML) research. It comprises multiple hidden layers of artificial neural networks. The deep learn- ing methodology applies nonlinear transformations and model abstractions of high level in large databases. The recent advancements in deep learning architec- tures within numerous fields have already provided significant contributions in artificial intelligence. This article presents a state of the art survey on the contri- butions and the novel applications of deep learning. The following review chron- ologically presents how and in what major applications deep learning algorithms have been utilized. Furthermore, the superior and beneficial of the deep learning methodology and its hierarchy in layers and nonlinear operations are presented and compared with the more conventional algorithms in the common applica- tions. The state of the art survey further provides a general overview on the novel concept and the ever-increasing advantages and popularity of deep learning.

The ridge line of the western Pacific subtropical high (WPSHRL) plays an important role in determining the shift of the summer rain belt in eastern China. In this study, we developed a forecast system for the June WPSHRL index based on the latest autumn and winter sea surface temperature (SST). Considering the adverse condition of the small observed sample size, a very simple neural network (NN) model was selected to extract the non-linear relationship between input predictors (SST) and target predictands (WPSHRL) in the forecast system. In addition, some techniques are used to deal with the adverse condition, enhance the stabilization of forecast skills, and analyze the interpretability of the forecast system. The forecast experiments show that the linear correlation coefficient between the predictions from the forecast system and their corresponding observations is around 0.6, and about three-fifths of the observed abnormal years (the years with an obviously high or low WPSHRL index) are successfully predicted. Furthermore, sensitivity experiments show that the forecast system is relatively stable in terms of forecast skill. The above evaluations suggest that the forecast system is valuable in a real application sense.

Estimating evapotranspiration at field scale is a major component of sustainable water management. Due to the difficulty to assess some major unknowns of the water cycle at that scale, including irrigation amounts, evapotranspiration is often computed as the residual of the instantaneous surface energy budget. One of the Surface Energy Bal-ance components with the largest uncertainties in their quantification over bare soils and sparse vegetation areas is the ground heat flux (G). Over the last decades, the es-timation of G with RS data has been mainly achieved with empirical equations, on the basis of the G and net radiation (Rn) ratio, G/Rn. G/Rn empirical equations generally require vegetation data (Type I empirical equations), in combination with surface tem-perature (Ts) and albedo (Type II empirical equations). In this article we aim to evalu-ate the estimation of G with RS. For the first time, we compare eight G/Rn empirical equations against two types of machine learning (ML) methods: an ensemble ML type, the Random Forest (RF), and the Neural Networks (NN). The comparison of each method is evaluated over dense dataset, including a wide range of climate and land covers, with data of Eddy-Covariance towers extended along the mid-latitude area that encompass the European and African continent. Our results have shown evidence that the driver of G in bare soils and sparse vegetation areas (Fraction of Vegetation, Fv <= 0.25) is Ts, instead of vegetation greenness indexes. On the other hand, the estimation of G with Rn, Ts or Fv decreases at dense vegetation areas (Fv >= 0.50). There are not significant differences between the most accurate type I and II empirical equations. For bare soils and sparse vegetation areas the empirical equation that better estimates G is E8, which combines the Leaf Area Index (LAI) and Ts. In dense vegetation areas (Fv >= 0.25), an exponential empirical equation based on Fv (E4), shows the best performance. However, ML better estimates G than the empirical equations, independently of the Fv ranges. A RF model with Rn, LAI and Ts as predictor variables shows the best accuracy and performance metrics, outperforming the NN model.

The implementation of neural networks (NN) on edge devices enables local processing of wireless data but faces challenges such as high computational complexity and memory requirements when deep neural networks (DNN) are used. Shallow neural networks customized for specific problems are more efficient, requiring fewer resources, and resulting in a lower latency solution. An additional benefit of the smaller network size is that it is suitable for real-time processing on edge devices. The main concern with shallow neural networks is their accuracy performance compared to DNNs. In this paper, we demonstrate that a customized adaptive activation function (AAF) can meet the accuracy of a DNN. We designed an efficient FPGA implementation for a customized segmented spline curve neural network (SSCNN) structure to replace the traditional fixed activation function with an AAF. We compared our SSCNN with different neural network structures such as real-valued time delay neural network (RVTDNN), augmented real-valued time delay neural network (ARVTDNN), and deep neural networks with different parameters. Our proposed SSCNN implementation uses 40% fewer hardware resources and no Block RAMS compared to the DNN with similar accuracy. We experimentally validate this computationally efficient and memory-saving FPGA implementation of SSCNN for digital predistortion of RF power amplifiers using the AMD/Xilinx RFSoC ZCU111. The implemented solution uses less than 3% of the available resources. The solution also enables an increase of the clock frequency to 221.12 MHz, allowing the transmission of wide bandwidth signals.

Tight gas, a category of Deep Green Energy Resources, rely on advanced intelligent monitoring methods for their extraction. Conventional logging for reservoir evaluation relies on logging data and the manual setting of evaluation criteria to classify reservoirs. However, the complexity and heterogeneity of tight reservoirs pose challenges in accurately identifying target layers by using traditional well-logging techniques. Machine learning may hold the key to solving this problem, as it enables computers to learn without being explicitly programmed and manually added rules. Therefore, it is possible to make reservoir evaluation via using machine learning methods. In this paper, the reservoir quality index (RQI) and porous geometric parameters obtained from the optimized inversion of the spherical-tubular model are adopted to evaluate the reservoir. Then, three different machine learning approaches, the random forest (RF) algorithm, support vector machine (SVM) algorithm, and extreme gradient boosting (XGB) algorithm, are utilized for reservoir classification. The selected dataset covers more than 7,000 samples from five wells. The data from four wells are arranged as the training dataset, and the data of the remaining one well is designed as the testing dataset to calculate the prediction accuracies of different machine learning algorithms. Among them, accuracies of RF, SVM, and XGB are all higher than 90%, and XGB owns the highest result by reaching 97%. Machine learning based approaches can greatly assist reservoir prediction by implementing the well-logging data. The research highlights the application of reservoir classification with a higher prediction accuracy by combining machine learning algorithms with NMR logging based pore structure characterization, which can provide a guideline for sweet spot identification within the tight formation. This not only optimizes resource extraction but also aligns with the global shift towards clean and renewable energy sources, promoting sustainability and reducing the carbon footprint associated with conventional energy production. In summary, the fusion of machine learning and NMR logging based reservoir evaluation plays a crucial role in advancing both energy efficiency and the transition to cleaner energy sources.

Cancer metastasis accounts for approximately 90% of cancer deaths, and elucidating markers in metastasis is the first step in its prevention. To characterize metastasis marker genes of breast cancer (MGs), XGBoost models that classify metastasis status were trained with gene expression profiles from TCGA. Then, a metastasis score (MS) was assigned to each gene by calculating the inner product between the feature importance and AUC performance of the models. As a result, the 54, 202, and 357 genes with the highest MS were characterized as MGs by empirical P-value cutoffs of 0.001, 0.005, and 0.01, respectively. The three sets of MGs were compared with those from existing metastasis marker databases, which provided significant results in most comparisons. We noticed that the set of MGs with the median EP cutoff showed better performance than the other two sets, suggesting the importance of the cutoff used in determining MGs. They were also significantly enriched in biological processes associated to breast cancer metastasis. The MGs that could not be identified by statistical analysis (e.g., GOLM1, ELAVL1, UBP1, and AZGP1) as well as the MGs with the highest MS (e.g., ZNF676, FAM163B, LDOC2, IRF1, and STK40) were verified via the literature. Additionally, we checked how close the MGs are located to each other in the protein–protein interaction networks. We expect that the characterized markers will help understand and prevent breast cancer metastasis.

Deep learning is improving by leaps and bounds in remote sensing images (RSIs) analysis, pre-trained convolutional neural networks (CNNs) have shown remarkable performance in remote sensing image scene classification (RSISC). Nonetheless, pre-trained CNNs require massive annotated data as samples for data training. When labeled samples are not sufficient, the most common solution is to the pre-trained CNNs using a great deal of natural image dataset (e.g. ImageNet). However, these pre-trained CNNs require a large quantity of labelled data for training, which is often not feasible in RSISC, especially when the target RSIs have different imaging mechanisms from RGB natural images. In this paper, we proposed an improved hybrid classical-quantum transfer learning CNNs composed of classical and quantum elements to classify open-source RSI dataset. The classical part of the model is made up of a ResNet network which extracts useful features from RSI datasets. To further refine the network performance, a tensor quantum circuit is subsequently employed by tuning parameters on near-term quantum processors. We tested our models on open-source RSI dataset. In our comparative study, we have concluded that the hybrid classical-quantum transferring CNN has achieved better performance than other pre-trained CNNs based RSISC methods with small training samples. Moreover, it has been proved that the proposed algorithm improves the classification accuracy while greatly decreasing sum of model parameters and sum of training data.

Wearable sensors have the potential to enable comprehensive patient characterization and optimized clinical intervention. Critical to realizing this vision is accurate estimation of biomechanical time-series in daily-life, including joint, segment, and muscle kinetics and kinematics, from wearable sensor data. The use of physical models for estimation of these quantities often requires many wearable devices making practical implementation more difficult. However, regression techniques may provide a viable alternative by allowing the use of a reduced number of sensors for estimating biomechanical time-series. Herein, we review 46 articles that used regression algorithms to estimate joint, segment, and muscle kinematics and kinetics. We present a high-level comparison of the many different techniques identified and discuss the implications of our findings concerning practical implementation and further improving estimation accuracy. In particular, we found that several studies report the incorporation of domain knowledge often yielded superior performance. Further, most models were trained on small datasets in which case nonparametric regression often performed best. No models were open-sourced, and most were subject-specific and not validated on impaired populations. Future research should focus on developing open-source algorithms using complementary physics-based and machine learning techniques that are validated in clinically impaired populations. This approach may further improve estimation performance and reduce barriers to clinical adoption.

An active power dispatch method for a microgrid (MG) with multi-type loads, renewable energy sources (RESs) and distributed energy storage devices (DESDs) is the focus of this paper. The MG operates in a grid-connected model, and distributed power sources contribute to the service for load demands. The outputs of multiple DESDs are controlled to optimize the active power dispatch. Our goal with optimization is to reduce the economic cost under time-of-use (TOU) price, and to adjust the excessively high or low load rate of distributed transformers (DTs) caused by the peak-valley demand and load uncertainties. To simulate a practical environment, the stochastic characteristics of multi-type loads are formulated. The transition matrix of system state is provided. Then, a finite-horizon Markov decision process (FHMDP) model is established to describe the dispatch optimization problem. A learning-based technique is adopted to search the optimal joint control policy of multiple DESDs. Finally, simulation experiments are performed to validate the effectiveness of the proposed method, and the fuzzification analysis of the method is presented.