False positives on multiparametric (mp)-MRI result in a large number of unnecessary biopsies in men with clinically insignificant diseases. This study investigates whether quantitative diffusion MRI can improve differentiation between false positives, true positives and normal tis-sue. Twenty-three patients underwent mp-MRI and Vascular, Extracellular and Restricted Diffu-sion for Cytometry in Tumours (VERDICT)-MRI, followed by transperineal biopsy. The patients were categorised into two groups following biopsy: (1) significant cancer - true positive (2) atro-phy/inflammation/high-grade prostatic intraepithelial neoplasia (PIN) - false positive. The clinical apparent diffusion coefficient (ADC) values of the lesions were obtained, and the intravoxel inco-herent motion (IVIM), diffusion kurtosis imaging (DKI) and VERDICT models were fitted using a deep learning approach. Significant differences (p < 0.05) between true positive and false positive lesions were found in ADC, IVIM perfusion fraction (f) and diffusivity (D), DKI diffusivity (DK) and kurtosis (K) and VERDICT intracellular volume fraction (fIC), extracellular-extravascular vol-ume fraction (fEES) and diffusivity (dEES) values. Significant differences between false positives and normal tissue were only found for the VERDICT fIC. These results demonstrate that model-based diffusion MRI could reduce the number of unnecessary biopsies due to false positive prostate lesions and shows promising sensitivity to benign diseases that mimic cancer.

The relevance of bacteria to subjective experiences or qualia is under-appreciated. Here, I make four proposals. Firstly, living systems traverse sequences of active states that determine their behaviour; these states result from competitive coherence, which depends on a connectivity-based competition between a Next process and a Now process whereby elements in the active state at time n+1 are chosen between the elements in the active state at time n and those elements in the developing n+1 state. Secondly, bacteria should help us link the mental to the physical world given that bacteria were here first, are highly complex, influence animal behaviour and dominate the Earth. Thirdly, the operation of competitive coherence to generate active states in bacteria, brains and other living systems is inseparable from qualia. Fourthly, these qualia become particularly important to the generation of active states in the highest levels of living systems, namely, the ecosystem and planetary levels.

The study of dog point following has been increasingly popular, at least partially due to the initial claims that dogs outperform apes and the suggestion that our domestication process caused dogs to have a biological capacity to communicate with humans. We take the view that dog pointing is more complicated than was initially reported, and in this study, we explore several potential variables that may make a difference. Our variables include point type (ipsilateral (same-side) vs contralateral (cross-body) points), position (standing vs seated), and distance (proximal vs distal). We find that most dogs follow ipsilateral points while less than half of the dogs in our sample follow contralateral points, and that position and distance also affect dogs’ success. We suggest that dogs acquire ipsilateral points via associative mechanisms, but that contralateral points require the dogs to understand the humans’ communicative intent.

Agriculture is the primary source of economic growth in many countries in West Africa. It provides food and livelihoods for the population. The purpose of this study is to review the digital agriculture status in five countries, namely Benin, Burkina Faso, Coˆte d’Ivoire, Ghana, and Nigeria. The study consisted of a bibliometric analysis using a database exported from the web of science through a well-defined search string. Additionally, the cases of digital technology deployment in the countries were assessed through a systematic review approach comparing the technologies used in the target countries. Representative articles from the bibliometric review published in the last five years were selected for the comparative analysis. The bibliometric analysis based on 3,249 publications revealed that the research interests have significantly increased since 2014. The top two countries in terms of authors’ nationality were Nigeria and Ghana, respectively. Climate change, Machine Learning (ML) and adoption were the hot topics of discussion. The digital agriculture survey showed that publications in Nigeria were focused on Internet of Things (IoT), Wireless Sensors Networks, blockchain, and Artificial Intelligence (IA) technologies. Ghana also has a strong interest in blockchain, AI, and big data, while Burkina Faso focused on IoT and AI. Cote d’Ivoire and Benin focused only on AI.

The aim of this work is to explain the behaviour of the multiresistance percentage of Pseudomona aeruginosa in some countries of Europe through a multivariate statistical analysis and machine learning validation, using data from the European Antimicrobial Resistance Surveillance System, the World Health Organization and the World Bank. First, we will use a descriptive analysis and a principal components analysis. Then, we use a k-means clustering to determine the countries and regions that are most affected by the antibiotic resistance. Second, we expand the database by adding some socioeconomic, governance and antibiotic-consumption variables. We then run a data panel regression analysis to determine some functions that relates the multiresistance percentage with those new variables. Finally, we use machine learning techniques to validate a pooling panel data case, using XGBoost and random forest algorithms. The results of the data panel analysis indicate that the most important variables for the multiresistance percentage are corruption control and the rule of law. Similar results are found with the machine learning validation analysis, where the human development index is an additional important variable for the multiresistance percentage.

Introduction: Dental students’ use of online material to supplement learning has been studied, but educator awareness and reaction to the findings of this research is unknown. This small local study aimed to investigate dental students’ use of online content as a learning tool from an educator’s perspective.Methods: Educators at an Irish dental school completed a survey based on dental students’ use of online learning. Quantitative descriptive analyses were carried out as appropriate on the data collected, and a subsequent focus group was held to gain deeper insight into survey results. Data were analysed for themes by deductive and inductive coding methods.Results: This study found a sample of educators were aware of some student behaviours around online videos. Most educators correctly thought that students are likely to refer to online videos to prepare for dental procedures. Several educators believed that teachers should incorporate videos into their learning, but do not themselves upload or recommend online videos. Most recalled discussing accuracy and/or relevancy of online content with their students. Fewer thought that students would discuss contradictory videos with them. Focus group participants expressed concern over the accuracy of online content. This along with a lack of time were some reasons deterring them from referring students to online videos. Conclusions: An opportunity exists for dental educators and their students to have local dialogue around (1) student use, critical appraisal, and sharing of dental procedural video material; and (2) perceived benefits and challenges of incorporating both school-produced and online videos into teaching and learning. Although arguably non-generalizable beyond this context, this study may inform future research and serve to spark conversations within schools regarding video use for teaching clinical dental procedures.

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from 8 volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides the accuracy performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. Our results indicate that the proposed method will provide the medical doctors and trainers a promising way to precisely track and understand a patient’s physical activities for better treatment.

COVID-19 has a severe risk of spreading rapidly, the quick identification of which is essential. In this regard, chest radiology images have proven to be a practical screening approach for COVID-19 affected patients. This study proposes a deep learning-based approach using Densenet-121 to detect COVID-19 patients effectively. We have trained and tested our model on the COVIDx dataset and performed both 2-class and 3-class classification, achieving 96.49% and 93.71% accuracy, respectively. By successfully utilizing transfer learning, we achieve comparable performance to the state-of-the-art method while using 15x fewer model parameters. Moreover, we performed an interpretability analysis using Grad-CAM to highlight the most significant image regions at test time. Finally, we developed a website that takes chest radiology images as input and detects the presence of COVID-19 or pneumonia and a heatmap highlighting the infected regions. Source code for reproducing results and model weights are available.

Electromyographic (EMG) signals provide information about a person's muscle activity. For hand movements, in particular, the execution of each gesture involves the activation of different combinations of the forearm muscles, which generate distinct electrical patterns. Conversely, the analysis of these muscle activation patterns, represented by EMG signals, allows recognizing which gesture is being performed. In this study, we aimed to implement an automatic identification system of hand or wrist gestures based on supervised Machine Learning (ML) techniques. We trained different computational models and determined which of these showed the best capacity to identify six hand or wrist gestures and generalize between different subjects. We used an open access database containing recordings of EMG signals from 36 subjects. Among the results obtained, we highlight the performance of the Random Forest model, with an accuracy of 95.39%, and the performance of a convolutional neural network with an accuracy of 94.77%.

Segmentation of Magnetic Resonance Images (MRI) of abdominal organs is useful for analysis prior to surgical procedures and for further processing. Deep Learning (DL) has become the standard, researchers have proposed improvements that include multiple views, ensembles and voting. Loss function alternatives, while being crucial to guide automated learning, have not been compared in detail. In this work we analyze limitations of popular metrics and their use as loss, study alternative loss variations based on those and other modifications and search for the best approach. An experimental setup was necessary to assess the alternatives. Results for the top scoring network and top scoring loss show improvements between 2 and 11 percentage points (pp) in Jaccard Index (JI), depending on organ and patient (sequence), for a total of 22 pp over 4 organs, all this being obtained just by choosing the best performing loss function instead of cross-entropy or dice. Our results apply directly to MRI of abdominal organs, with important practical implications for other architectures, as they can be applied easily to any of them. They also show the worth of variants of loss function and loss tuning, with future work needed to generalize and test in other contexts.

Spinocerebellar ataxia type 2 (SCA2) is caused by polyglutamine expansion in Ataxin-2 (ATXN2). This factor binds RNA/proteins to modify metabolism after stress, and to control calcium (Ca2+) homeostasis after stimuli, thus exerting crucial neuroprotection for cerebellar ataxias and corticospinal motor neuron degeneration. Our Atxn2-CAG100-Knock-In mouse faithfully models features observed in patients at pre-onset, early and terminal stages. Here, its cerebellar global RNA profiling revealed downregulation of signaling cascades to precede motor deficits. Validation work at mRNA/protein level defined alterations that were independent of constant physiological ATXN2 functions, but specific for RNA/aggregation toxicity, and progressive across the short lifespan. Earliest changes were detected at 3 months among Ca2+ channels/transporters (Itpr1, Ryr3, Atp2a2, Atp2a3, Trpc3), IP3 metabolism (Plcg1, Inpp5a, Itpka), and Ca2+-Calmodulin dependent kinases (Camk2a, Camk4). CaMKIV–Sam68 control over alternative splicing of Nrxn1, an adhesion component of glutamatergic synapses between granule and Purkinje neurons, was found affected. Systematic screening of pre/post-synapse components, with dendrite morphology assessment, suggested early impairment of CamKIIα abundance together with weakening of parallel fiber connectivity. These data reveal molecular changes due to ATXN2 pathology, impacting communication and excitability of cerebellar neurons. Discovery of such risk versus progression markers improves the assessment of pre-symptomatic treatments in SCA2 and related disorders.

In this paper, we have investigated the impact of an early learning assessment on students' motivation for improving their performance throughout the semester. An observation analysis was conducted on an entry level mechanical engineering course in which students are enrolled in during their first semester of engineering work. This study analyzes the effect that a first exam, with an average below a passing grade, has on student's outcome in the course. It was hypothesized that students were motivated to achieve their desired grade outcomes following inadequate performance on the first exam. This was investigated by diving into the results of the course and referencing initial performance to the remaining exam and assessment outcomes. Students were placed into grade bands ranging from 0 to 100 in 20% increments. Their results were tracked and it was shown that for the second mechanics exam, averages jumped 43.333%, 35.35%, and 30.055% for grade bands of 0 to 20, 20 to 40, and 40 to 60 respectively. Assessment grades increased as well with the remaining assessments being averaged to a score of 91.095%. Variables contributing to student performance came from both with-in and outside the classroom. Learning communities, material differentiation, and student and professor adaptation all contributed to the rise in performance. It was concluded that the internal and external variables acted in combination with one another to increase student dedication to achieve success.

Identifying dust aerosols from passive satellite images is of great interest for many applications. In this study, we developed 5 different machine-learning (ML) and deep-learning (DL) based algorithms, including Logistic Regression, K Nearest Neighbor, Random Forest (RF), Feed Forward Neural Network (FFNN), and Convolutional Neural Network (CNN), to identify dust aerosols in the daytime satellite images from the Visible Infrared Imaging Radiometer Suite (VIIRS) under cloud-free conditions on a global scale. In order to train the ML and DL algorithms, we collocated the state-of-the-art dust detection product from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) with the VIIRS observations along the CALIOP track. The 16 VIIRS M-band observations with the center wavelength ranging from deep blue to thermal infrared, together with solar-viewing geometries and pixel time and locations, are used as the predictor variables. Four different sets of training input data are constructed based on different combinations of VIIRS pixel and predictor variables. The validation and comparison results based on the collocated CALIOP data indicates that the FFNN method based on all available predictor variables is the best performing one among all methods. It has an averaged dust detection accuracy of about 81 %, 89 % and 85 % over land, ocean and whole globe, respectively, compared with collocated CALIOP. When applied to off-track VIIRS pixels, the FFNN method retrieves geographical distributions of dust that are in good agreement with on-track results as well as CALIOP statistics. For further evaluation, we compared our results based on the ML and DL algorithms to NOAA’s Aerosol Detection Product (ADP) , which is a product that classifies dust, smoke and ash using physical-based methods. The comparison reveals both similarity and differences. Overall, this study demonstrates the great potential of ML and DL methods for dust detection and proves that these methods can be trained on the CALIOP track and then applied to the whole granule of VIIRS granule.

Recent advancements in artificial intelligence (AI) and deep learning have revolutionized the field of protein engineering, particularly in the area of de novo protein design. This review article explores the impact of AI-driven approaches on protein design, with a specific focus on the role of structure prediction neural networks, such as AlphaFold and RoseTTAFold. The article discusses the paradigm shift brought about by these networks, which have enabled the design of proteins with unique structures and functions that are not found in nature. The review covers various aspects of AI-driven protein design, including the use of protein language models to harness evolutionary information, the development of de novo protein design workflows utilizing deep learning, and the application of generative models like RFdiffusion and RoseTTAFold All-Atom. The article also highlights the successes and applications of AI-driven protein design across diverse domains, such as enzyme engineering, antibody design, and vaccine development. Additionally, the review identifies current challenges and future directions in the field, emphasizing the need to address limitations in modeling conformational dynamics and designing proteins for in vivo functionality. The article concludes by underscoring the potential of AI-driven protein design to transform various aspects of science and technology, while also acknowledging the importance of interdisciplinary collaboration and the development of robust pipelines for the validation and optimization of designed proteins. Overall, this comprehensive review serves as a valuable resource for researchers and practitioners interested in understanding the current state and future prospects of AI-driven protein design.

In recent years, there has been a growing interest in the prediction of facial age due to its diverse applications in fields such as security, entertainment, and healthcare. The current scourge of underaged voting in Nigeria is a problem and this research delves into the realm of facial age prediction by employing four well-known convolutional neural network (CNN) architectures, namely VGG16, ResNet50, Mobile Net, and VGG19 to predict chronological ages from facial pictures of person. The objective is to achieve precise age estimation from facial images, utilizing two datasets: UTKFace and CASIA African Facial Datasets. The results of this investigation are noteworthy. Specifically, the VGG16 model which demonstrated remarkable performance, yielding a Mean Absolute Error (MAE) of 1.76 when applied to the UTK-Face dataset. Additionally, when utilizing Mobile-Net, an unprecedented MAE of 1.10 was achieved for the Casia Africa Face Dataset. Notably, this marks the first instance of employing the dataset for facial age detection with CNNs, and this approach outperformed previous works, yielding the lowest MAE among all the studies reviewed.

As a combination of both concepts of innovation and environmental development, green innovation is of great significance to the sustainable development of the country and industry. Previous literatures have found the separate roles of green entrepreneurial orientation and inter-organizational learning in understanding green innovation issues. However, few studies have done a comprehensive analysis of integrating three streams of research: green entrepreneurial orientation, green innovation and supply chain learning capability. Based on the resource-based view and dynamic capability theory, we examine the direct of green entrepreneurial orientation on green innovation as well as indirect effect through the mediation of supply chain learning capability. Meanwhile, an empirical data set of 228 manufacturing companies in China (Shaanxi, Guangdong, Hebei, Jiangsu, and Shandong) was used to test our hypotheses. Findings from our empirical study suggest that supply chain learning capability partially mediates the positive relationships between green entrepreneurial orientation and its two consequences—green incremental innovation and green radical innovation. In addition, this research implies that when enterprise has a strong green entrepreneurial orientation, the enterprise should make an effort to enhance the level of supply chain learning capability so as to fully develop their green innovation.

The concept of ‘big data’ has been widely discussed, and its value has been illuminated throughout a variety of domains. To quickly mine potential values and alleviate the ever-increasing volume of information, machine learning is playing an increasingly important role and faces more challenges than ever. Because few studies exist regarding how to modify machine learning techniques to accommodate big data environments, we provide a comprehensive overview of the history of the evolution of big data, the foundations of machine learning, and the bottlenecks and trends of machine learning in the big data era. More specifically, based on learning principals, we discuss regularization to enhance generalization. The challenges of quality in big data are reduced to the curse of dimensionality, class imbalances, concept drift and label noise, and the underlying reasons and mainstream methodologies to address these challenges are introduced. Learning model development has been driven by domain specifics, dataset complexities, and the presence or absence of human involvement. In this paper, we propose a robust learning paradigm by aggregating the aforementioned factors. Over the next few decades, we believe that these perspectives will lead to novel ideas and encourage more studies aimed at incorporating knowledge and establishing data-driven learning systems that involve both data quality considerations and human interactions.

Unmanned Aerial Vehicles (UAV) are increasingly being used in a variety of domains and precision agriculture is no exception. Precision agriculture is the future of agriculture and will play a key role in long-term sustainability of agricultural practices. This paper presents a survey of how image data collected using UAVs has been used in conjunction with ma-chine learning techniques to support precision agriculture. Numerous agricultural applications including classification of crop types and trees, crops detection, weed detection, cropland cover, and segmentation of farming fields are discussed. A variety of supervised, semi-supervised and unsupervised machine learning techniques for image-based preci-sion agriculture are compared. The survey showed that for traditional machine learning approaches, Random Forests performed better than Support Vector Machines (SVM) and K-Nearest Neighbor Algorithm (KNN) for crop/weed classification. And, while Convolutional Neural Networks (CNN) have been used extensively, the U-Net-based models out-performed conventional CNN models for classification and segmentation tasks. Among the Single Stage Detectors (SSD), YOLO series performed relatively well. Two-Stage Detectors like R-CNN, FPN, and Mask R-CNN generally tended to outperform SSDs. Vision Trans-formers (ViT) showed promising results amongst transformer-based models which did not generally perform better than CNNs. Finally, Generative Adversarial Networks (GANs) have been used to address the problem of smaller datasets and unbalanced data

Data mining techniques have garnered significant attention within the realm of education. However, the procurement of ample student data poses a formidable challenge. In response to this challenge, we present a student dataset characterized by its size and distinctive attributes. This dataset encompasses various task-related topics interconnected through a learning pathway, thereby enabling researchers to delve into the data from novel perspectives. Moreover, it encompasses extensive longitudinal student behavioral data, a rarity that adds substantial value. Spanning the years from 2010 to 2021, our dataset comprises a cohort of 7,933 students, 64,344 test scores, and 183,390 behavior records, solidifying its status as a valuable resource for educational research. In our experiments, we achieved successful predictions of students' test outcomes based on behavioral learning data. The strengths of our dataset render it apt for analyzing the nexus between student conduct and academic performance, crafting personalized learning recommendations, and pursuing various other research pursuits.

A topic of growing interest in urban remote sensing is the automated extraction of geometrical building information for 3D city modeling. Roof geometry information is useful for applications such as urban planning, solar potential estimation and telecommunication installation planning, and wind flow simulations for pollutant diffusion analysis. Recent research has proven that the advance in remote sensing technologies and deep learning methods offer the prospects of deriving the roof structure information accurately and efficiently. In this study, we propose a Vectorized Roof Extractor- method based on Fully Convolutional Networks (FCNs) and advanced polygonization method to extract roof structure from aerial imagery and a normalized Digital Surface Models (nDSM) in a regularized vector format. The roof structure consists of building outlines, external edges of the building roof, inner rooflines, internal intersections of the main roof planes. The methodology is comprised of segmentation, vectorization and post-processing for outer rooflines, external edges of the building roof, and inner rooflines, and internal intersections of the main roof planes. For the comparison, we adapt the Frame field Learning (FFL) method originally designed to extract building polygons [1]. Our experiments are conducted on a custom data set derived for the city of Enschede, The Netherlands, using aerial imagery, nDSM and manually digitized training polygons. The results show that the proposed Vectorized Roof Extractor outperformed adapted FFL on PoLiS distance with values of 3.5 m and 1.2 m for outlines and inner rooflines, respectively. Furthermore, the model surpassed the adapted FFL on PoLiS-thresholded F-score for outlines and inner rooflines, with 0.31 and 0.57, respectively. The Vectorized Roof Extractor produced adequate visual results, with straighter walls and fewer missed inner roofline detections. It can predict buildings with common walls thanks to skeleton graph computation. To summarize, the proposed method is suitable for urban applications and has the potential to be improved further.

In areas where conventional fundus cameras are logistically unaffordable, the smartphone-based approach is considered as a promising future of glaucoma screening due to their affordability and ease-of-use. Optic disc localization is a critical stage during glaucoma screenings. For fundus images captured with standard fundus cameras, the majority of the models available out there can locate the optic disc with satisfactory performance. However, for images that are captured with smartphone-based fundus cameras, the inherent noise and lower quality of the fundus image makes it difficult for models to detect the optic disc region. In this study, we have proposed to utilize YOLOv8n for optic disc localization due to the model’s cutting-edge performance in diverse tasks and its lightweight nature. We have used a public dataset which has 2000 low quality fundus images that are captured using a smartphone-based fundoscopy device. From these, 60% of the data was used for fine-tuning the model, and 25% for testing. By using a confidence of 50% set as threshold, the model was able to detect the optic disc successfully on over 97% of test images with intersection over union of above 0.85. These results highlight the potential of the lightweight YOLOv8n model for deployment on resource-constrained environments, offering a promising performance on accurately localizing the OD and enhancing the feasibility of affordable glaucoma screening on smartphones.

Non-neural Machine Learning (ML) and Deep Learning (DL) are used to predict system failures in industrial maintenance. However, only a few studies have assessed the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three data sets of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously and (3) a nitrogen generator working continuously. A binary classification task assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM and Transformers) are compared using multivariate time series. The dimension of the prediction windows plays a crucial role and the results highlight the effectiveness of DL approaches in classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches in classifying similar and repetitive patterns preceding a failure.

Protein molecules show varying degrees of flexibility throughout their three-dimensional structures. This flexibility is associated with the fluctuation of the torsion angle in proteins. The protein backbone can be defined mainly by two torsion angles, phi (φ) and psi (ψ). The fluctuation of torsion angles is derived from different NMR models’ variations in backbone torsion angles. The angle fluctuations in the cartesian coordinate space are used to characterize the protein’s structural flexibility. Fluctuation of torsion angle is useful in predicting protein function and structure when the torsion angles are used as restraints. This study aims to develop a machine learning method to predict torsion angle fluctuations directly from protein sequences. It explores various useful features such as disorder probability, position-specific scoring matrix profiles, secondary structure probabilities, monograms, bigram, position-specific estimated energy, half-sphere exposures, etc. Likewise, it explores well-known machine learning methods and proposes an optimized Light Gradient Boosting Machine Regressor (LightGBM) method, named TAFPred, to predict torsion angle fluctuations with the selected features. The proposed method achieves ten-fold cross-validated correlation coefficients of 0.746 and 0.737 and mean absolute errors of 0.114 and 0.123 for the angle fluctuation of φ and ψ, respectively, and attains an improvement of 10.08% in MAE, 24.83% in PCC in the phi angle, and 9.93% in MAE, 22.37% in PCC in psi angle compared to the state-of-the-art method proposed by Zhang et al.

Financial markets require a great deal of decision making from the investors and market makers. One metric that can help ease the process of decision making is investment risk which can be measured in two parts; systematic risk and idiosyncratic risk. Clear understanding of the volatilities in each risk component can be a powerful signal in recognizing the right assets to maximize the investment returns. In this paper, we focus on the idiosyncratic volatility values and pre-calculate the idiosyncratic volatility values for 31,198 members of NYSE, Amex and Nasdaq markets for the trades occurring between January 1963 and December 2019. Utilizing a subset of dataset, limited to Nasdaq100 index, we consider the application of machine learning techniques in predicting the idiosyncratic volatility values using the raw trade data to explore a data extension option for the future market trade records that have not yet occurred. We offer a deep learning based regression model and compare it with traditional tree-based methods on a small subset of our per-calculated idiosyncratic volatility dataset. Our analytical results show that the performance of the deep learning techniques is much more robust in comparison to that of the traditional tree-based baselines.

Estimating precipitation is of critical importance to climate systems and decision-making processes. This paper presents Espresso, a deep learning model designed for estimating precipitation from satellite observations on a global scale. Conventional methods, like ground-based radars, are limited in terms of spatial coverage. Satellite observations, on the other hand, allow global coverage. Combined with deep learning methods these observations offer the opportunity to address the challenge of estimating precicpation on a global scale. This research paper presents the development of a deep learning model using geostationary satellite data as input and generating instantaneous rainfall rates, calibrated using data from the Global Precipitation Measurement Core Observatory (GPMCO). The performance impact of various input data configurations on Espresso was investigated. These configurations include a sequence of four images from geostationary satellites and the optimal selection of channels. Additional descriptive features were explored to enhance the model’s robustness for global aplications. When evaluated against the GPMCO test set, Espresso demonstrated highly accurate precipitation estimation, especially within equatorial regions. A comparison against six other operational products using multiple metrics indicated its competitive performance. The model’s superior storm localization and intensity estimation were further confirmed through visual comparisons in case studies. Espresso has been incorporated as an operational product at Météo-France, delivering high-quality, real-time global precipitation estimates every 30 minutes.

CT scans are currently the most common imaging modality used for suspected stroke patients due to their short acquisition time and wide availability. However, MRI offers superior tissue contrast and image quality. In this study, eight deep learning models are developed, trained, and tested using a dataset of 181 CT/MR pairs from stroke patients. The resultant synthetic MRIs generated by these models are compared through a variety of qualitative and quantitative methods. The synthetic MRIs generated by a 3D UNet model consistently demonstrated superior performance across all methods of evaluation. Overall, the generation of synthetic MRIs from CT scans using the methods described in this paper produces realistic MRIs that can guide the registration of CT scans to MRI atlases. The synthetic MRIs enable the segmentation of white matter, gray matter, and cerebrospinal fluid using algorithms designed for MRIs, exhibiting a high degree of similarity to true MRIs.

With the popularity of solar energy in the electricity market, demand arises for data such as precise locations of solar panels for efficient energy planning, management, and distribution. However, this data is not easily accessible and in some cases, information such as precise locations does not exist. Furthermore, existing data sets for training semantic segmentation models of PV installations are limited, and their annotation is time-consuming and labor-intensive. Therefore, for additional remote sensing (RS) data creation, the pix2pix generative adversarial network (GAN) is utilized, enriching the original resampled training data of varying GSDs without compromising its integrity. Experiments done with the DeepLabV3 model, ResNet-50 backbone, and pix2pix GAN architecture were conducted to find the optimal configuration for an accurate RS imagery segmentation model. The result is a fine-tuned solar panel semantic segmentation model, trained using transfer learning and utilizing an optimal amount – 60% of generated RS imagery for additional training data, increasing model accuracy. The findings demonstrate the benefits of using GAN-generated images as additional training data, increasing the size of small data sets, and improving the capabilities of the segmentation model for solar panel detection in RS images.

In the realm of autonomous vehicle environment perception, the primary objective of point cloud target detection is to swiftly and accurately identify three-dimensional objects from point cloud data. To meet this requirement, the prevalent network architecture employed in the industry is the voxel-based PointPillars model. Nonetheless, this model faces challenges in maintaining detection accuracy when objects are obscured or diminutive in size. In response to this issue, we introduce AGPNet, a novel model that seamlessly integrates four key modules: Data Augmentation, Dynamic Graph CNN, Pillar Feature Net, and Detection Head (SSD). The Data Augmentation module enhances the adaptability of point cloud data to complex and ever-changing real-world environments. The Dynamic Graph CNN module endows the network structure with geometric features, which encapsulate not only the point itself but also its adjacent points. The Pillar Feature Net module translates three-dimensional point cloud data into pseudo-image data through the utilization of voxels. Subsequently, the Detection Head (SSD) module leverages this pseudo-image data to conduct target detection of three-dimensional objects. Our experiments, conducted on the KITTI dataset, demonstrate that our proposed method boosts object detection accuracy by 6-7 percentage points compared to the PointPillars model, while maintaining similar detection times.

The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumor from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature of DL models poses challenges in understanding their decision-making processes, particularly crucial in medical contexts where interpretability is essential. This paper explores the intersection of medical image analysis and DL interpretability, aiming to elucidate the decision-making rationale of DL models in brain tumor classification. Leveraging state-of-the-art DL frameworks with transfer learning, we conduct a comprehensive evaluation encompassing both classification accuracy and interpretability. Using state-of-the-art DL frameworks with transfer learning, we conduct a thorough evaluation covering both classification accuracy and interpretability. We employ adaptive path-based techniques to understand the underlying decision-making mechanisms of these models. Grad-CAM and Grad-CAM++ highlight critical image regions where the tumors are located.

The proliferation of deep learning in natural language processing (NLP) has led to the development and release of innovative technologies capable of understanding and generating human language with remarkable proficiency. Atinuke, a Transformer-based neural network, optimises performance across various language tasks by utilising a unique configuration. The architecture interweaves layers for processing sequential data with attention mechanisms to draw meaningful affinities between inputs and outputs. Due to the configuration of its topology and hyperparameter tuning, it can emulate human-like language by extracting features and learning complex mappings. Atinuke is modular, extensible, and integrates seamlessly with existing machine learning pipelines. Advanced matrix operations like softmax, embeddings, and multi-head attention enable nuanced handling of textual, acoustic, and visual signals. By unifying modern deep learning techniques with software design principles and mathematical theory, the system achieves state-of-the-art results on natural language tasks whilst remaining interpretable and robust.

Abstract：The brain often switches freely between focused attention and divergent thinking, and the default mode network (DMN) is activated during brain rest. The discovery, function and characteristics of default mode network all indicate that learning does not stop when the brain "rests". Mental disease can lead to dysfunctional default mode networks, which affects learning adversely. Therefore, default mode network plays an important role in learning. Neural activities such as β-wave rhythm regulation, "subconscious" divergence mode initiation, hippocampal function and neural replay occur during default mode, which also explain that "rest" promotes learning. This paper reveals the role and neural mechanism of default mode network in learning from the neural level, discusses the essential role default mode network plays in learning, and default mode network enables rest to promote learning.

Early detection of stress can prevent us from suffering from a long-term illness such as depression and anxiety. This article presents a scoping review of stress detection based on electrodermal activity (EDA) and machine learning (ML). From an initial set of 395 articles searched in six scientific databases, 58 were finally selected according to various criteria established. The scoping review has made it possible to analyse all the steps to which the EDA signals are subjected: acquisition, preprocessing, processing and feature extraction. Finally, all the ML techniques applied to the features of this signal have been studied for stress detection. It has been found that support vector machines and artificial neural networks stand out within the supervised learning methods given their high performance values. On the contrary, it has been evidenced that unsupervised learning is not very common in the detection of stress through EDA. This scoping review concludes that the use of EDA for the detection of arousal variation (and stress detection) is widely spread, with very good results in its prediction with the ML methods found during this review.

This study aims to assess the feasibility of delineating and identifying mineral ores from hyperspectral images of tin-tungsten mine excavation faces using machine-learning classification. We compiled a set of hand samples of minerals of interest from a tin-tungsten mine and analyzed two types of hyperspectral images: 1) images acquired with a laboratory set-up under close-to-optimal conditions; and 2) scan of a simulated mine face using a field set-up, under conditions closer to those in the gallery. We have analyzed the following minerals: cassiterite (tin ore), wolframite (tungsten ore), chalcopyrite, malachite, muscovite, and quartz. Classification (Linear Discriminant Analysis, Singular Vector Machines and Random Forest) of laboratory spectra had a very high overall accuracy rate (98%), slightly lower if the 450 – 950 nm and 950 – 1780 nm ranges are considered independently, and much lower (74.5%) for simulated conventional RGB imagery. Classification accuracy for the simulation was lower than in the laboratory but still high (85%), likely a consequence of the lower spatial resolution. All three classification methods performed similarly in this case, with Random Forest producing results of slightly higher accuracy. The user’s accuracy for wolframite was 85%, but cassiterite was often confused with wolframite (user’s accuracy: 70%). A lumped ore category achieved 94.9% user’s accuracy. Our study confirms the suitability of hyperspectral imaging to record the spatial distribution of ore mineralization in progressing tungsten-tin mine faces.

Due to the large interest and need, there has been much recent work in epileptic seizure detection using machine learning models. Using un-intrusive measurements of brain activity such as electroencephalograms (EEG) has allowed for large datasets to be constructed and used for computational intelligence to identify seizure events within EEG data. In this paper, we use a publicly avaibale EEG dataset to develop a lightweight Machine learning supervised model (simple Decision Tree) to classify seizure events from brain waves. The performance of this developed model was compared with a complex ML model (Support Vector Machine). The cross-validated Decision Tree model performed better for seizure event classification with an overall accuracy of 91.17%. This lightweight model will allow for developing mobile applications and user comfort

Shallow landslides pose serious threats to human existence and economic development, especially in the Himalayan areas. Landslide susceptibility mapping (LSM) is a proven way for minimizing the hazard and risk of landslides. Modeling as an essential step, various algorithms have been applied to LSM. In this study, information value (IV) and logistic regression (LR) were selected as representatives of the conventional algorithms, categorical boosting (CatBoost) and conventional neural networks (CNN) as the advanced algorithms, for LSM in Yadong county, and their performance was compared. To begin with, 496 historical landslide events were compiled into a landslide inventory map, followed by a list of 11 conditioning factors, forming a data set. Secondly, the data set was randomly divided into two parts, 80% of which was used for modeling and 20% for validation. Finally, the area under the curve (AUC) and statistical metrics were applied to validate and compare the performance of the models. The results showed that the CNN model performed the best (AUC 0.974 and accuracy=93.3%), while the LR model performed the worst (AUC 0.974 and accuracy=93.3%) and CatBoost model performed better (AUC 0.974 and accuracy=93.3%). Besides, the LSM constructed by the CNN model did a more reasonable prediction of the distribution of susceptible areas. As for feature selection, did a more detailed analysis of conditioning factors but the results were uncertain. The result analyzed by GI may be more reliable but fluctuates with the amount of data. The conclusion reveals that the accuracy of LSM can be further improved with the advancement of algorithms, by determining more representative features, which serve as a more effective guide for land use planning in the study area or other highlands where landslides are frequent.

Accurate weight measurement is pivotal for monitoring the growth and well-being of cattle. However, the conventional weighing process, which involves physically placing cattle on scales, is labor-intensive and distressing for the animals. Hence, the development of automated cattle weight prediction techniques assumes critical significance. This study proposes a weight prediction approach for Korean cattle using 3D segmentation-based feature extraction and regression machine learning techniques from incomplete 3D shapes acquired from real farm environments. In the initial phase, we generated mesh data of 3D Korean cattle shapes using a multiple-camera system. Subsequently, deep learning-based 3D segmentation with the PointNet network model was employed to segment two dominant parts of the cattle. From these segmented parts, three crucial dimensions of Korean cattle were extracted. Finally, we implemented five regression machine learning models (CatBoost regression, LightGBM, Polynomial regression, Random Forest regression, and XGBoost regression) for weight prediction. To validate our approach, we captured 270 Korean cattle in various poses, totaling 1190 poses of 270 cattle. The best result was achieved with mean absolute error (MAE) of 25.2 kg and mean absolute percent error (MAPE) of 5.81% using the random forest regression model.

This paper describes an image processing method that makes use of image parts instead of neural parts. Neural networks excel at image or pattern recognition and they do this by constructing complex networks of weighted values that can cover the complexity of the pattern data. These features however are integrated holistically into the network, which means that they can be difficult to use in an individual sense. A different method might scan individual images and use a more local method to try to recognise the features in it. This paper suggests such a method, where a trick during the scan process can not only recognise separate image parts, as features, but it can also produce an overlap between the parts. It is therefore able to produce image parts with real meaning and also place them into a positional context. Tests show that it can be quite accurate, on some handwritten digit datasets, but not as accurate as a neural network, for example. The fact that it offers an explainable interface could make it interesting however. It also fits well with an earlier cognitive model, and an ensemble-hierarchy structure in particular.

In this paper, we introduce an innovative approach to distinguish Gliosarcoma (GSM) from Glioblastoma (GBM). Our method combines causal fuzzy logic rules with the Big Bird architecture, a Transformer-based Deep Learning algorithm. Unlike prior research, which often relied on statistical models to reduce dataset dimensions before causal analysis, our approach harnesses the complete dataset in tandem with our causal fuzzy Big Bird architecture. Additionally, we benchmark our results not only against previous Gliosarcoma/Glioblastoma studies but also against GPT-2 for a comprehensive evaluation.

Communication is indispensable for today's lifestyle, and thanks to technology, millions of people can communicate as quickly as possible. The effect of this breakthrough has transformed organizations to the degree that they generate billions of emails daily to facilitate their operations. There is implicit information behind this vast corpus of human-generated content that can be mined and used for their benefit. This paper tries to address the opportunity that email logs can bring to organizations and propose an approach to discover process models by combining supervised text classification and process mining. This framework consists of two main steps, text classification, and process mining. First, Emails will be classified with supervised machine learning, and to mine, the processes fuzzy Miner is used. To further investigate the application of this framework, we also applied this framework over a real-life dataset from a case study organization.

Physicians often label anatomical structure sets in Digital Imaging and Communications in Medicine (DICOM) images with nonstandard names. As these names vary widely, the standardization of the nonstandard names in the Organs at Risk (OARs), Planning Target Volumes (PTVs), and 'Other' organs inside the area of interest is a vital problem. Prior works considered traditional machine learning approaches on structure sets with moderate success. This paper presents integrated deep learning methods applied to structure sets by integrating the multimodal data compiled from the radiotherapy centers administered by the US Veterans Health Administration (VHA) and the Department of Radiation Oncology at Virginia Commonwealth University (VCU). The de-identified radiation oncology data collected from VHA and VCU radiotherapy centers have 16,290 prostate structures. Our method integrates the heterogeneous (textual and imaging) multimodal data with Convolutional Neural Network (CNN)-based deep learning approaches like CNN, Visual Geometry Group (VGG) network, and Residual Network (ResNet). Our model presents improved results in prostate (RT) structure name standardization. Evaluation of our methods with macro-averaged F1 Score shows that our deep learning model with single-modal textual data usually performs better than the previous studies. We also experimented with various combinations of multimodal data (masked images, masked dose) besides textual data. The models perform well on the textual data alone, while the addition of imaging data shows that deep neural networks can achieve improved performance using information present in the other modalities. Additionally, using masked images and masked doses along with text leads to an overall performance improvement with the various CNN-based architectures than using all the modalities together. Undersampling the majority class leads to further performance enhancement. The VGG network on the masked image-dose data combined with CNNs on the text data performs the best and establishes the state-of-the-art in this domain.

Alzheimer’s disease has become a major concern in the healthcare domain as it is growing rapidly. Many researches have been conducted to detect it from MRI images through various deep-learning approaches. However, the problem of the availability of medical data and the privacy of the patients still exists. To mitigate this issue in Alzheimer’s disease detection, we have implemented the federated approach which is found to be more efficient, robust, and consistent compared to the conventional approach. For this, we needed deep excavation on various orientations of MRI images and transfer learning architectures. Then, we utilized the publicly available two datasets (OASIS, and ADNI), and designed various cases to evaluate the performance of the federated approach. In almost all of them, the federated approach achieved better accuracy and sensitivity. In distinguishing between two classes equally, the capability of the models was better in the found model when trained with federated approach compared to the conventional approach. In this approach. MobileNet, which is a low-cost transfer learning architecture, achieved the highest 95.24%, 81.94%, and 83.97% accuracy in OASIS, ADNI, and merged (ADNI+OASIS) test set, which was way higher than the achieved performance in Conventional approach. Moreover, in this approach, only the weights of the model were shared which keeps the original MRI images in their respective hospital or institutions, mitigating the privacy concern in the healthcare domain.

The digital world has a wealth of data, such as Internet of Things (IoT) data, business data, health data, mobile data, urban data, security data, and many more, in the current age of the Fourth Industrial Revolution (Industry 4.0 or 4IR). Extracting knowledge or useful insights from these data can be used for smart decision-making in various applications domains. In the area of data science, advanced analytics methods including machine learning modeling can provide actionable insights or deeper knowledge about data, which makes the computing process automatic and smart. In this paper, we present a comprehensive view on "Data Science'' including various types of advanced analytics methods that can be applied to enhance the intelligence and capabilities of an application through smart decision-making in different scenarios. We also discuss and summarize ten potential real-world application domains including business, healthcare, cybersecurity, urban and rural data science, and so on by taking into account data-driven smart computing and decision making. Based on this, we finally highlight the challenges and potential research directions within the scope of our study. Overall, this paper aims to serve as a reference point on data science and advanced analytics to the researchers and decision-makers as well as application developers, particularly from the data-driven solution point of view for real-world problems.

The Medi-test system we developed was motivated by the large number of resources available for the medical domain, as well as the number of tests needed in this field (during and after the medical school) for evaluation, promotion, certification, etc. Generating questions to support learning and user interactivity has been an interesting and dynamic topic in NLP since the availability of e-book curricula and e-learning platforms. Current e-learning platforms offer increased support for student evaluation, with an emphasis in exploiting automation in both test generation and evaluation. In this context, our system is able to evaluate a student’s academic performance for the medical domain. Using as input medical reference texts and supported by a specially designed medical ontology, Medi-test generates different types of questionnaires for Romanian language. The evaluation includes 4 types of questions (multiple-choice, fill in the blanks, true/false and match), can have customizable length and difficulty and can be automatically graded. A recent extension of our system also allows for the generation of tests which include images. We evaluated our system with a local testing team, but also with a set of medicine students, and user satisfaction questionnaires showed that the system can be used to enhance learning.

It is difficult to obtain necessary information accurately from Social Networking Service (SNS) while raising children, and it is thought that there is a certain demand for the development of a system that presents appropriate information to users according to the child's developmental stage. There are still few examples of research on knowledge extraction that focuses on childcare. This research aims to develop a system that extracts and presents useful knowledge for people who are actually raising children, using texts about childcare posted on Twitter. In many systems numbers in text data are just strings like words and are normalized to zero or simply ignored. In this paper, we created a set of tweet texts and a set of profiles created according to the developmental stages of infants from "0-year-old child" to "6-year-old child". For each set, we used ML algorithms such as NB (Naive Bayes), LR (Logistic Regression), ANN (Approximate Nearest Neighbor algorithms search), XGboost, RF (random forest), decision trees, and SVM (Support Vector Machine) to compare with BERT, a neural language model, to construct a classification model that predicts numbers from "0" to "6" from sentences. The accuracy rate predicted by the BERT (Bidirectional Encoder Representations from Transformers) classifier was slightly higher than that of the NB, LR, ANN, XGboost, RF, decision trees, and SVM classifiers, indicating that the BERT classification method was better.

It is difficult to obtain necessary information accurately from Social Networking Service (SNS) while raising children, and it is thought that there is a certain demand for the development of a system that presents appropriate information to users according to the child's developmental stage. There are still few examples of research on knowledge extraction that focuses on childcare. This research aims to develop a system that extracts and presents useful knowledge for people who are actually raising children, using texts about childcare posted on Twitter. In many systems numbers in text data are just strings like words and are normalized to zero or simply ignored. In this paper, we created a set of tweet texts and a set of profiles created according to the developmental stages of infants from "0-year-old child" to "6-year-old child". For each set, we used Support Vector Machine (SVM), and Bidirectional Encoder Representations from Transformers (BERT), a neural language model, to construct a classification model that predicts numbers from "0" to "6" from sentences. The accuracy rate predicted by the BERT classifier was slightly higher than that of the SVM classifier, indicating that the BERT classification method was better.

Machine learning has seen enormous growth in the last decade, with healthcare being a prime application for advanced diagnostics and improved patient care. The application of machine learning for healthcare is particularly pertinent in Africa, where many countries are resource-scarce. However, it is unclear how much research on this topic is arising from African institutes themselves, which is a crucial aspect for applications of machine learning to unique contexts and challenges on the continent. Here, we conduct a bibliometric study of African contributions to research publications related to machine learning for healthcare, as indexed in Scopus, between 1993 and 2022. We identified 3,772 research outputs, with most of these published since 2020. North African countries currently lead the way with 64.5% of publications for the reported period, yet Sub-Saharan Africa is rapidly increasing its output. We found that international support in the form of funding and collaborations is correlated with research output generally for the continent, with local support garnering less attention. Understanding African research contributions to machine learning for healthcare is a crucial first step in surveying the broader academic landscape, forming stronger research communities, and providing advanced and contextually aware biomedical access to Africa.

Scoring targets in shooting sports is a crucial and time-consuming task that relies on manually counting bullet holes. This paper introduced an automatic score detection model using object detection techniques. The performance of seven models belonging to two different architectural setups was compared. Models like YOLOv8n, YOLOv8s, YOLOv8m, RetinaNet-50, and RetinaNet-101 are single-shot detectors, while Faster RCNN-50 and Faster RCNN-101 belong to the two-shot detectors category. The dataset was manually captured from the shooting range and expanded by generating more versatile data using Python code. Before the dataset was trained to develop models, it was resized (640x640) and augmented using Roboflow API. The trained models were then assessed on the test dataset, and their performance was compared using matrices like mAP50, mAP50-90, precision, and recall. The results showed that YOLOv8 models can detect multiple objects with good confidence scores. Among all, YOLOv8m performed the best with the highest mAP50 value of 96.7%, followed by the performance of YOLOv8s with the mAP50 value of 96.5%. It is suggested that if the system is to be implemented in a real-time environment, YOLOv8s is a better choice since it took significantly less inference time (2.3ms) than YOLOv8m (5.7ms) and yet generated the competitive mAP50.

This paper investigates the adaptability of four state-of-the-art Artificial Intelligence (AI) models to the Australian mammographic context through transfer learning, explores the impact of image enhancement on model performance and analyses the relationship between AI outputs and histopathological features for clinical relevance and accuracy assessment. A total of 1712 screening mammograms (n=856 cancer cases and n=856 matched normal cases) were used in this study. The 856 cases with cancer lesions were annotated by two expert radiologists and the level of concordance between their annotations was used to establish image subsets. The area under the receiver operating characteristic curve (AUC) was used to evaluate the performance of Globally aware Multiple Instance Classifier (GMIC), Global-Local Activation Maps (GLAM), I&amp;H and End2End AI models, both in the pre-trained and transfer learning modes, with and without applying the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm. The four AI models with and without transfer learning in the high-concordance subset outperformed those in the entire dataset. Applying the CLAHE algorithm to mammograms improved the performance of the AI models. In the high-concordance subset with transfer learning and CLAHE algorithm applied, the AUC of the GMIC model was highest (0.912), followed by GLAM model (0.909), I&amp;H (0.893) and End2End (0.875). There were significant differences (P&lt;0.05) in the performances of the four AI models between high-concordance subset and entire dataset. The AI models demonstrated significant differences in malignancy probability concerning different tumour size categories in mammograms. The performance of AI models was affected by several factors such as concordance classification, image enhancement and transfer learning. Mammograms with strong concordance of radiologists’ annotations, applying image enhancement and transfer learning could enhance the accuracy of AI models.

The increasing use of Convolutional Neural Networks (CNN) has brought about a significant transformation in numerous fields, such as image categorization and identification. In the development of a CNN model for classifying images of sericea lespedeza (SL; Lespedeza cuneata) from weed images, four architectures were explored: CNN-Model Variant 1, CNN-Model Variant 2, VGG16, and ResNet50. The CNN-Model Variant 1 demonstrated 100 % validation accuracy, while Variant 2 achieved 90.78% validation accuracy. Pre-trained models, like VGG16 and ResNet50, were also analyzed. In contrast, ResNet50's steady learning pattern indicated potential for better generalization. A detailed evaluation of these models revealed that Variant 1 achieved a perfect score in precision, recall, and F1-score, indicating superior optimization and feature utilization. Variant 2 presented a balanced performance, with metrics between 86% and 93%. The VGG16 mirrored the behavior of Variant 2, both maintaining around 90% accuracy, but ResNet50's results revealed a conservative approach for class 0 predictions. Overall, Variant 1 stood out in performance, while both Variant 2 and VGG16 showed balanced results. The reliability of CNN model Variant 1 is highlighted by the significant accuracy percentages, which demonstrate its potential for practical implementation in agriculture. Smartphone application for the identification of SL in a field-based trial has shown promising results with an accuracy of 98%-99%. Using a CNN model with batch normalization has the potential to play a crucial role in redefining and optimizing the management of undesirable vegetation in the future.

Machine Learning techniques can be used to identify whether deficits in cognitive functions contribute to antisocial and aggressive behavior. This paper initially presents the results of tests conducted on delinquent and non-delinquent youths to assess their cognitive functions. The dataset extracted from these assessments, consisting of 37 predictor variables and one target. was used to train three algorithms that aim to predict whether the data corresponds to that of a young offender or a non-offending youth. Prior to this, statistical tests were conducted on the data to identify characteristics that exhibited significant differences in order to select the most relevant features and optimize the prediction results. Additionally, other feature selection methods, such as Boruta, RFE, and Filter, were applied, and their effects on the accuracy of each of the three machine learning models used (SVM, RF, and KNN) were compared. 80% of the data were utilized for training, while the remaining 20% were used for validation. The best result was achieved by the K-NN model trained with 19 features selected by the Boruta method, followed by the SVM model trained with 24 features selected by the filter method.

Machine learning models facilitate the search for non-linear relationships when modeling hydrological processes, but they are equally effective for automation at the data preparation stage. The tasks whose automation was analyzed consisted in estimating changes in the roughness of a mountain streambed and the extent of floods from images. The Segment Anything Model (SAM) developed this year by Meta was used for this purpose. Images from many years from the Wielka Puszcza mountain stream located in the Polish Carpathians were used as the only input data. The model was not additionally trained for the described tasks. The model can be run in several modes, but the two most appropriate were used in this study. The first one is available in the form of a web application, while the second one is available in the form of a Jupyter notebook run in the Google Colab environment. Both methods do not require specialized knowledge and can be used by virtually any hydrologist. In the roughness estimation task, the average Intersection over Union (IoU) ranges from 0.55 for grass to 0.82 for shrubs/trees. Ultimately, it was possible to estimate the roughness coefficient of the mountain streambed between 0.027 and 0.059 based solely on image data. In the task of estimation of the flood extent, when selecting appropriate images, one can expect IoU at the level of at least 0.94, which seems to be an excellent result considering that SAM is a general-purpose segmentation model. It can therefore be concluded that SAM model can be a useful tool for a hydrologist.

The prevalence of chronic diseases is dramatically increasing demand for emergency healthcare. Existing systems rely on patients self-identifying symptoms, causing dangerous delays. This study develops an AI and IoT-powered “digital twin” solution to enable continuous real-time monitoring and timely prediction of diverse medical emergencies. A digital twin is a virtual representation of an individual, modeled using multidimensional physiological data from wearable sensors. Machine learning techniques analyze patterns in this data to identify anomalies and predict emergencies like heart attacks or falls. A key contribution is an optimized ensemble algorithm combining gradient boosted trees, neural networks, and other techniques to accurately detect emergency events. Evaluation on a dataset of 9158 samples shows the digital twin identifies key emergencies with over 90% recall, enabling prevention and rapid response. It allows risk stratification and personalized interventions based on early warnings, circumventing over 2 million avoidable emergency room visits annually. This study demonstrates the feasibility of an integrated, predictive, patient-centric emergency response system enabled by digital twin technology.

3D reconstruction from a single 2D input is a classic problem in the field of computer vision. With the advancements in deep learning, the performance of 3D reconstruction has also significantly improved. The reconstruction task is more difficult for objects with no textures or complex deformations. This paper serves as a review of recent literature on 3D reconstruction from a single view, with a focus on deep learning methods from 2018 to 2021. Due to lack of standard datasets or 3D shape representation methods, it is hard make direct comparisons between all reviewed methods. However, this paper reviews different approaches for reconstructing 3d shape as depth maps, surface normals, point clouds and meshes; along with various loss functions and evaluation metrics used to train and evaluate these methods.

Stress has been identified as one of the major causes of automobile crashes which then lead to high rates of fatalities and injuries each year. Stress can be measured via physiological measurements and in this study the focus will be based on the features that can be extracted by common wearable devices. Hence the study will be mainly focusing on the heart rate variability (HRV). This study is aimed to develop a good predictive model that can accurately classify stress levels from ECG-derived HRV features, obtained from automobile drivers, testing different machine learning methodologies such as K-Nearest Neighbor (KNN), Support Vector Machines (SVM), Multilayer Perceptron (MLP), Random Forest (RF) and Gradient Boosting (GB). Moreover, the models obtained with highest predictive power will be used as reference for the development of a machine learning model that would be used to classify stress from HRV features derived from HRV measurements obtained from wearable devices. We demonstrate that MLP was the ideal stress classifier by achieving a Recall of 80%. The proposed method can be also used on all applications in which is important to monitor the stress level e. g. in physical rehabilitation, anxiety relief or mental wellbeing.

The application of Explainable AI (XAI) to improve understanding of complex non-linear SST teleconnections and gain predictive skills is at the frontier of climate research. In this study, we attempt to refine the applications of XAI advancements to ENSO prediction by including SSTA in the western North Pacific (WNP) as a precursor. Our analyses indicate that the baseline accuracy increases from the 60% threshold previously reported for ENSO to &gt;85% for moderate warm, cold, and neutral ENSO states one year in advance when WNP SSTA is included. Precision increases to over 90% for higher magnitude El Niños and La Niñas. Experiments conducted at 4-year lead times yield a strong WNP SSTA signal. A moderate SSTA signal is observed at 3-year lead time with no predictability; however, predictability spikes to over 80% when stratospheric zonal winds are included with WNP SSTA. While additional scientific work is required to make robust connections between XAI and dynamical processes, our results demonstrate a potential to improve long term predictability of ENSO through the ability of XAI in capturing SST patterns evolving at extended spatial and temporal scales.

Background This paper draws learnings and successes based on field implementation experience spanning four years (2016–2019) of implementing CLTS by Prince of Peace Orphans and Widows Vision, a community-based organization located in Kaberamaido district in eastern Uganda. Methods The study aimed to document, disseminate and inform from an evidence-based point of view how adaptation and collaborative engagements triggers learning from mistakes to inform iterative changes from improvements and success.This is a descriptive paper that used project documents review based on field implementation experience. Existing project reports were synthesised, collated and curated for evidence. Data were drawn from project reports and records to inform narratives in writing. Implementation of the project was executed in homogenous rural communities occupied by people of the same dialect, cultural and social settings. Results We note that success in CLTS implementation can hardly be achieved by merely following prescriptions in handbooks and guidelines but rather by devising innovative community engagement and other participatory and community-driven techniques that foster adaptive management, promote ownership, and buy-in.Having learned from our failures, we used data to inform decisions and transformatively deviated from traditional CLTS implementation and introduced high impact and innovative approaches such as the use of CLTS helpdesks and Situation room, the Pamoja approach, learning labs and iterative feedback loops, innovatively tackling slippage and carefully introducing the follow-up mandona approach. These enhanced experiential learning and ultimately resulted in sustained sanitation behaviour. Conclusions The CLTS approach as outlined in the handbook needs to be flexibly adapted to address contextual needs. Reflective and learning sessions reinforced with routine feedback loops from implementers and beneficiaries yields tremendous results, propagates experiential learning, and ultimately results in a transformative deviation from undesirable to desired sanitation behaviours. These innovative approaches once carefully blended have proved to be sustainable, are adaptable and can work in an even larger scale and in a variety of contexts.

Shipbreaking research has not been in the forefront until the last decade in which environmental and occupational hazards have been highlighted while economic sustainability and contextual conditions were not equally considered. The adoption of a triple bottom line approach across core business issues (environmental impacts, workplace safety ) as well as peripheral stakeholders expectation (environmental sustainability focus) has been retarded due to the less attention on the latter. Based on the findings of the 128 review papers, the study suggests that organizational learning and economic sustainability needs to prioritize through the formation of strange alliance among the stakeholders. The study argues that the dialogue and discussion on the peripheral stakeholders (NGOs, yard managers, national and international policy organizations) would lead to a more sustainable shipbreaking industry in the south Asian regions.

We describe a novel system for online prediction of lead seizures from long-term intracranial electroencephalogram (iEEG) recordings for canines with naturally occurring epilepsy. This study adopts new specification of lead seizures, reflecting strong clustering of seizures in observed data. This clustering results in fewer lead seizures (~7 lead seizures per dog), and hence new challenges for online seizure prediction, that are addressed in the proposed system. In particular, machine learning part of the system is implemented using the Group Learning method suitable for modeling sparse and noisy seizure data. In addition, several modifications for the proposed system are introduced to cope with non-stationarity of noisy iEEG signal. They include: (1) periodic re-training of SVM classifier using most recent training data; (2) removing samples with noisy labels from training data; (3) introducing new adaptive post-processing technique for combining many predictions made for 20-second windows into a single prediction for 4 hr segment. Application of the proposed system requires only 2 lead seizures for training the initial model, and results in high prediction performance for all four dogs (with mean 0.84 sensitivity, 0.27 time-in-warning, and 0.78 false-positive rate per day). Proposed system achieves accurate prediction of lead seizures during long-term test periods, 3–16 lead seizures during 169–364 days test period, whereas earlier studies did not differentiate between lead vs. non-lead seizures and used much shorter test periods (~few days long).

High-power laser facilities necessitate predicting incremental damage to final optics to identify evolving damage trends. In this study, we propose a surface damage detection method utilizing image segmentation employing ResNet-18, and a damage area estimation network employing U-Net++. Paired sets of online and offline images of optics obtained from a large laser facility is used to train the network. The trends of varying damage could be identified by incorporating additional experimental parameters. A key advantage of the proposed method is that the network can be trained end-to-end on small samples, eliminating the need for manual labeling or feature extraction. The software developed based on these models can facilitate the daily inspection and maintenance of optics in large laser facilities.

A common spinal condition, spondylolisthesis is the presence of a relative back or forth displacement between the upper and lower vertebra due to one vertebra being oriented away from the smooth curvature of a normal spine. Aging-related illnesses such as degenerative spondylolisthesis are especially burdensome on social welfare and health-care systems in an aging society, especially radiologists and clinical physicians. Therefore, we proposed a computer aided diagnosis algorithm, named LumbarNet, for vertebral slippage detection on clinical X-ray images. Collaborating with i) a P-grade, ii) a piecewise slope detection scheme, and iii) a dynamic shift detection routine, LumbarNet was thus specialized for analyzing complex structural patterns in lumbar spine X-ray images and outcompeted other U-Net based methods. Extensive experiments on lumbar spine X-ray images in standard clinical practices showed that LumbarNet achieved a mean intersection over union value of 0.88 in vertebral region detection and an accuracy of 88.83% in vertebral slippage detection.

The collaborative economy comprises resource circulation systems where consumers can act as both obtainers and providers of products and services. Despite considerable research on collaborative economies, there is a dearth of understanding of how individuals switch from being an obtainer to a provider. We address this void by drawing on 31 in-depth semi-structured interviews with collaborative economy obtainers. The findings suggest that personal values, learning experience, social benefits, mutuality, and peer influence drive obtainers to become providers. In contrast, distrusting strangers, a sense of intimacy, a lack of resources to share, and a lack of skills inhibit the switchover process. Our findings contextualize the drivers and inhibitors idiosyncratically to convert obtainers into providers, offer important implications for managers, contribute to the collaborative economy and sharing economy literature, and suggest compelling avenues for future 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.

We confirm that energy dissipation weighting provides the most accurate approach to determining the effective hydraulic conductivity (Keff) of a binary K grid. A deep learning algorithm (UNET) can infer Keff with extremely high accuracy (R2 > 0.99). The UNET architecture could be trained to infer the energy dissipation weighting pattern from an image of the K distribution with high fidelity, although it was less accurate for cases with highly localized structures that controlled flow. Furthermore, the UNET architecture learned to infer the energy dissipation weighting even if it was not trained on this information directly. However, the weights were represented within the UNET in a way that was not immediately interpretable by a human user. This reiterates the idea that even if ML/DL algorithms are trained to make some hydrologic predictions accurately, they must be designed and trained to provide each user-required output if their results are to be used to improve our understanding of hydrologic systems most effectively.

In this paper we derive a unified perspective for Optimal Transport (OT) theory and Mean Field Control (MFC) theory to analyse the learning process for Neural Networks algorithms in a high-dimensional framework. We consider Mean Field Neural Networks in the context of MFC theory, specifically the mean field formulation of OT theory that allows the development of highly efficient algorithms while providing a powerful tool in the context of explainable Artificial Intelligence.

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%.

Software defect prediction models enable test managers to predict defect-prone modules and assist with delivering quality products. A test manager would be willing to identify the attributes that can influence defect prediction and should be able to trust the model outcomes. The objective of this research is to create software defect prediction models with a focus on interpretability. Additionally, it aims to investigate the impact of size, complexity, and other source code metrics on the prediction of software defects. This research will also assess the reliability of cross-project defect prediction. Well-known machine learning techniques such as support vector machines, k-nearest neighbors, random forest classifiers, and artificial neural networks were applied to publicly available PROMISE datasets. The interpretability of this approach has been demonstrated by SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME) techniques. The developed interpretable software defect prediction models showed reliability on independent and cross-project data. Finally, the results demonstrate that static code metrics can contribute to the defect prediction models, and the inclusion of explainability assists in establishing trust in the developed models.

A morphological feature estimation method is presented, that can be used to monitor fish from low contrast underwater images and videos. The fish orientation is classified in order to apply a shape alignment technique that is based on the Ensemble of Regression Trees machine learning method. Shape alignment allows the estimation of fish dimensions (length, height, mass) and the location of fish body parts of particular interest such as the eyes and gills. The developed system can be exploited both for fish monitoring in open sea as well as aquacultures where non-invasive, low cost morphological feature extraction is essential. Fish health can be assessed from malformations in body shape, the color of the eyes or the gills as well as the fish behavior. The proposed method can estimate the position of 18 landmarks with an accuracy of about 95% from low resolution and low contrast underwater images where the fish can be hardly distinguished from its background. Hardware acceleration can be applied at various stages of the proposed method for real time video processing. As a case study, the developed system has been trained and tested with several Mediterranean fish species in the category of seabream or similar: diplodous sargus annularis (white seabream), diplodus annularis seabream (spawn), oblada melanura (saddled seabream), pagrus pagrus (common seabream), etc. A large dataset with low resolution underwater videos and images has been created in the context of this work.

Combustion power plants emit carbon dioxide (CO₂), a major contributor to climate change. Direct emissions measurement is cost-prohibitive globally, while reporting varies in detail, recency, and granularity. To fill this gap and greatly increase the number of power plants worldwide with independent emissions monitoring, we developed and applied machine learning (ML) models using power plant plumes as proxy signals to estimate electric power generation and CO₂ emissions using Landsat 8, Sentinel-2, and PlanetScope imagery. Our ML models estimated power plant activity on each image snapshot, and then an aggregation model predicted plant utilization over a 30-day period. Lastly, emissions factors specific to region, fuel, and plant technology were used to convert estimated electricity generation to CO₂ emissions. Models were trained with reported hourly generation data in the US, Europe, and Australia and were validated with additional generation and emissions data from the US, Europe, Australia, Türkiye, and India. All results with sufficiently large sample sizes indicate that our models outperformed baseline approaches. In conducting external validation to compare modeled versus reported annual generation and emissions in the countries where available, we calculated the root mean square error overall for modeled countries with validation data as respectively 1.75 TWh (236 plants across 17 countries over 4 years) and 2.04 Mt CO₂ (207 plants across 17 countries over 4 years). Ultimately, we applied our ML method to plants that comprise 32% of global power plant CO₂ emissions averaged over 2015-2022. This dataset is the most comprehensive independent and free-of-cost global power plant point-source emissions monitoring system currently known to the authors and is publicly available at climatetrace.org to support global emissions reduction.

Hypertension stands as the foremost modifiable risk factor for cardiovascular disorders in South Asia. This research demonstrates the superiority of statistical models over traditional approaches in identifying clinical risks related to hypertension. Leveraging individual-level data from the Bangladesh Demographic and Health Survey (2017-18), a unified dataset was created. Adhering to JNC7 and ACC/AHA guidelines for hypertension classification, two prominent regression models were employed to estimate the prevalence of undiagnosed hypertension. A substantial 16% of hypertension cases in Bangladesh remain undetected. The study identifies undiagnosed hypertension as a heightened risk, particularly among the youth and residents of Sylhet and Rangpur divisions. Statistical models exhibit efficacy in discerning undiagnosed hypertension and associated factors in South Asia. Subsequent investigations should incorporate biological markers to enhance statistical models and ascertain their practicality.

In a computing context, cybersecurity is undergoing massive shifts in technology and its operations in recent days, and data science is driving the change. Extracting security incident patterns or insights from cybersecurity data and building corresponding data-driven model, is the key to make a security system automated and intelligent. To understand and analyze the actual phenomena with data, various scientific methods, machine learning techniques, processes, and systems are used, which is commonly known as data science. In this paper, we focus and briefly discuss cybersecurity data science, where the data is being gathered from relevant cybersecurity sources, and the analytics complement the latest data-driven patterns for providing more effective security solutions. The concept of cybersecurity data science allows making the computing process more actionable and intelligent as compared to traditional ones in the domain of cybersecurity. We then discuss and summarize a number of associated research issues and future directions. Furthermore, we provide a machine learning-based multi-layered framework for the purpose of cybersecurity modeling. Overall, our goal is not only to discuss cybersecurity data science and relevant methods but also to focus the applicability towards data-driven intelligent decision making for protecting the systems from cyber-attacks.

There is a significant risk of injury in sports and intense competition due to the demanding physical and psychological requirements. Hamstring strain injuries (HSI) are the most prevalent type of injury among professional soccer players and are the leading cause of missed days in the sport. These injuries stem from a combination of factors, making it challenging to pinpoint the most crucial risk factors and their interactions, let alone find effective prevention strategies. Recently, there has been a growing recognition of the potential of tools provided by artificial intelligence (AI). However, current studies primarily concentrate on enhancing the performance of complex machine learning models, often overlooking their explanatory capabilities. Consequently, medical teams encounter difficulty interpreting these models and are hesitant to trust them fully. In light of this, there is an increasing need for advanced injury detection and prediction models that can aid doctors in diagnosing or detecting injuries earlier and with greater accuracy. Accordingly, this study aims to identify biomarkers of muscle injuries in professional soccer players through a biomechanical analysis, employing several ML algorithms, such as Decision tree (DT) methods, Discriminant methods, Logistic regression, Naive Bayes, Support vector machine (SVM), K-nearest neighbor (KNN), Ensemble methods, Boosted and bagged trees, Artificial Neural Networks (ANN), and XGBoost. In particular, XGBoost was also used to obtain the most important features. The findings highlight that the variables that most effectively differentiate the groups and could serve as reliable predictors for injury prevention are the maximum muscle strength of the hamstrings and the stiffness of the same muscle. With regards to the 35 techniques employed, a precision of up to 78% was achieved with XGBoost, indicating that by considering scientific evidence, suggestions based on various data sources, and expert opinions, it is possible to attain good precision, thus enhancing the reliability of the results for doctors and trainers. Furthermore, the obtained results strongly align with the existing literature, although further specific studies about this sport are necessary to draw a definitive conclusion.

Every month teachers face the dilemma of what exercises should their students practice, and what their consequences are on long-term learning. Since teachers prefer to pose their own exercises, this generates a large number of questions, each one attempted by a small number of students. Thus, we couldn’t use models based on big data such as deep learning. Instead, we developed a simple to understand state-space model that predicts end-of-year national test scores. We used 2,386 online fourth-grade mathematic questions designed by teachers and each attempted by some of the 500 students in 24 low socioeconomic schools. We found that the state-space model predictions improved month-by-month and that in most months it outperformed linear regression models. Moreover, the state-space estimator provides for each month a direct mechanism to simulate different practice strategies and compute their impact on the end-of-year standardized national test. We built iso-impact curves based on two critical variables: the number of questions solved correctly in the first attempt and the total number of exercises attempted. This allows the teacher to visualize the trade-off between asking students to do exercises more carefully or doing more exercises. To the best of our knowledge, this model is the first of its kind in education. It is a novel tool that supports teachers drive whole classes to achieve long-term learning targets.

Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operation, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying breast cancer from unregistered multi-view mammograms. This motivates us to leverage the architecture of Vision Transformers to capture long-range relationships of multiple mammograms from the same patient. For this purpose, we employ local Transformer blocks to separately learn patch relationships within a specific view (CC/MLO) of one side (right/left) of mammogram. The outputs from different views and sides are concatenated and fed into global Transformer blocks, to jointly learn patch relationships between two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of CC and MLO view mammograms, which include 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our two-view Transformer-based model achieves lesion classification accuracy of 77.0% and area under ROC curve (AUC = 0.814), outperforming state-of-the-art multi-view CNNs by 3.1% and 3%, respectively. Meanwhile, the new two-view model improves mammographic case classification accuracies of two single-view models by 7.4% (CC) and 4.5% (MLO), respectively. The promising results unveil the great potential of using Transformers to develop high-performing computer-aided diagnosis (CADx) schemes of mammography.

Near-surface humidity (Qa) is a key parameter that modulates oceanic evaporation and influences the global water cycle. Remote sensing observations act as feasible sources for long-term and large-scale Qa monitoring. However, existing satellite Qa retrieval models are subject to apparent uncertainties due to model errors and insufficient training data. Based on in situ observations collected over the China Seas over the last two decades, a deep learning approach named Ensemble Mean of Target deep neural networks (EMTnet) was proposed to improve the satellite Qa retrieval over the China Seas for the first time. The EMTnet model outperforms five representative existing models by nearly eliminating the mean bias and significantly reducing the root-mean-square error in satellite Qa retrieval. According to its target deep neural networks selection process, the EMTnet model can obtain more objective learning results when the observational data are divergent. The EMTnet model was subsequently applied to produce a 30-year monthly gridded Qa data over the China Seas. It indicates that the climbing rate of Qa over the China Seas under the background of global warming are probably underestimated by current products.

Extensive, but remote oil and gas fields of the United States, Canada, and Russia require the construction and operation of extremely long pipelines. Global warming and local heating effects lead to rising soil temperatures and thus a reduction in the sub-grade capacity of the soils; this causes changes in the spatial positions and forms of the pipelines, consequently increasing the number of accidents. Oil operators are compelled to monitor the soil temperature along the routes of the remoted pipelines in order to be able to perform remedial measures in time. They are therefore seeking methods for the analysis of volumetric diagnostic information. To forecast soil temperatures at the different depths we propose compiling a multidimensional dataset, defining descriptive statistics; selecting uncorrelated time series; generating synthetic features; robust scaling temperature series, tuning the additive regression model to forecast soil temperatures.

This paper presents a novel approach for indoor acoustic source localization using microphone arrays and based on a Convolutional Neural Network (CNN). The proposed solution is, to the best of our knowledge, the first published work in which the CNN is designed to directly estimate the three dimensional position of an acoustic source, using the raw audio signal as the input information avoiding the use of hand crafted audio features. Given the limited amount of available localization data, we propose in this paper a training strategy based on two steps. We first train our network using semi-synthetic data, generated from close talk speech recordings, and where we simulate the time delays and distortion suffered in the signal that propagates from the source to the array of microphones. We then fine tune this network using a small amount of real data. Our experimental results show that this strategy is able to produce networks that significantly improve existing localization methods based on SRP-PHAT strategies. In addition, our experiments show that our CNN method exhibits better resistance against varying gender of the speaker and different window sizes compared with the other methods.

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.

This study evaluates whether a combination of photodiode sensor measurements, taken during laser powder bed fusion (L-PBF) builds, can be used to predict the resulting build quality via a purely data-based approach. We analyse the relationship between build density and features that are extracted from sensor data collected from three different photodiodes. The study uses a Singular Value Decomposition to extract lower-dimensional features from photodiode measurements, which are then fed into machine learning algorithms. Several unsupervised learning methods are then employed to classify low density (< 99% part density) and high density (≥ 99% part density) specimens. Subsequently, a supervised learning method (Gaussian Process regression) is used to directly predict build density. Using the unsupervised clustering approaches, applied to features extracted from both photodiode sensor data as well as observations relating to the energy transferred to the material, build density was predicted with up to 93.54% accuracy. With regard to the supervised regression approach, a Gaussian Process algorithm was capable of predicting the build density with a RMS error of 3.65%. The study shows, therefore, that there is potential for machine learning algorithms to predict indicators of L-PBF build quality from photodiode build-measurements. Moreover, the work herein describes approaches that are predominantly probabilistic, thus facilitating uncertainty quantification in machine-learnt predictions of L-PBF build quality.

The COVID-19 is a highly contagious viral infection which played havoc on everyone's life in many different ways. According to the world health organization and scientists, more testing potentially helps governments and disease control organizations in containing the spread of the virus. The use of chest radiographs is one of the early screening tests to determine the onset of disease, as the infection affects the lungs severely. This study will investigate and automate the process of testing by using state-of-the-art CNN classifiers to detect the COVID19 infection. However, the viral could of many different types; therefore, we only regard for COVID19 while the other viral infection types are treated as non-COVID19 in the radiographs of various viral infections. The classification task is challenging due to the limited number of scans available for COVID19 and the minute variations in the viral infections. We aim to employ current state-of-the-art CNN architectures, compare their results, and determine whether deep learning algorithms can handle the crisis appropriately. All trained models are available at https://github.com/saeed-anwar/COVID19-Baselines

Downward short-wave (SW) solar radiation is the only essential energy source powering the atmospheric dynamics, ocean dynamics, biochemical processes, etc. on our planet. Clouds are the main factor limiting the SW flux over the land and the Ocean. For the accurate meteorological measurements of the SW flux one needs expensive equipment - pyranometers. For some cases where one does not need golden-standard quality of measurements, we propose estimating incoming SW radiation flux using all-sky optical RGB imagery which is assumed to incapsulate the whole information about the SW flux. We used DASIO all-sky imagery dataset with corresponding SW downward radiation flux measurements registered by an accurate pyranometer. The dataset has been collected in various regions of the World Ocean during several marine campaigns from 2014 to 2022, and it will be updated. We demonstrate the capabilities of several machine learning models in this problem, which are multilinear regression, Random Forests, Gradient Boosting and convolutional neural networks (CNN). We also applied the inverse target frequency (ITF) re-weighting of the training subset and the approach of pre-classification in order to raise the SW flux approximation quality. We found that the CNN is capable of approximating downward SW solar radiation with higher accuracy compared to existing empiric parameterizations. We also found that the ITF reweighting of the training subset increases the approximation quality substantially. The estimates of the SW radiation flux using all-sky imagery may be of particular use in case of the need for the fast radiative budgets assessment of a site.

“You should know the words by the company they keep!” has been one of the most famous slogans attributed to John Rubert Firth, 1957. This has ignited a whole school in linguistic research known as the British empiricist contextualism. Sixty years later, many un- or semi-supervised machine learning algorithms have been successfully designed and implemented aiming at extracting word meaning from within the context of a text corpus. These algorithms treat words, more or less, as vectors of real numbers representing frequencies of word occurrences within context and word meaning as positions of words in a high-dimensional vector space model. Word associations, in turn, are treated as calculated distances among them. With the rise of Deep Learning (DL) and other artificial neural networks based architectures, learning the positioning of words and extracting word associations as measured by their distances has further improved. In this paper, however, we revisited the main stream of algorithmic approaches and set the stage for a partly cross-disciplinary evaluation framework to judge about the nature of the extracted word associations by state-of-the-art machine learning algorithms. Our preliminary results are based on word associations extracted from the application of DL framework on a Google News text corpus, as well as on comparisons with human created word association lists such as word collocation dictionaries and psycholinguistic experiments. The results and conclusions provide some insights into the inherited limitations in interpreting the type of word associations and underpinning relations between words with inevitable consequences in other areas, such as extraction of knowledge graphs or image understanding.

Deep learning is emerging in many industrial sectors in hand with big data analytics to streamline production. In the biomanufacturing sector, big data infrastructure is lagging comparatively to other industries. A promising approach is to combine Deep Neural Networks (DNN) with prior knowledge in Hybrid Neural Network (HNN) workflows that are less dependent on the quality and quantity of data. This paper reviews published articles over the past 30 years on the topic of HNN applications to bioprocesses. It revealed that HNNs were applied to various bioprocesses, including microbial cultures, animal cells cultures, mixed microbial cultures, and enzyme biocatalysis. HNNs were mainly applied for process analysis, process monitoring, development of software sensors, open- and closed-loop control, batch-to-batch control, model predictive control, intensified design of experiments, quality-by-design, and recently for the development of digital twins. Most previous HNN studies combined shallow Feedforward Neural Networks (FFNNs) with physical laws, such as macroscopic material balance equations, following the semiparametric design principle. Only recently, deep HNNs based on deep FFNNs, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM) networks and Physics Informed Neural Networks (PINNs) have been reported. The biopharma sector is currently a major driver but applications to biologics quality attributes, new modalities, and downstream processing are significant research gaps.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

Deep learning has shown remarkable results in every field, especially in the biomedical field, due to its ability to exploit large-scale datasets. A convolutional neural network (CNN) is a widely used deep learning approach to solve medical imaging problems. Over the past few years, many studies have focused on CNN-based techniques for brain tumor diagnosis. There are, however, still some critical challenges that CNNs face towards clinic application. This study presents a comprehensive review of current literature that involves CNN architectures for brain tumor classification. We compare the key achievements in the performance evaluation metrics of the applied classification algorithms. In addition, this review assesses the clinical effectiveness of the included studies to elaborate on the limitations and directions of this area for future work. No review focusing on the clinical effectiveness of previous works in this field has been published. We believe that this study has the potential to elevate the application of CNN-based deep learning methods in clinical practice and also can be a quick reference for biomedical researchers who are interested in this field.

The Ames/quantitative structure-activity relationship (QSAR) International Challenge Projects held during 2014–2017 and 2020–2022, evaluated the performance of various predictive models. Despite the significant insights gained, the rules allowing participants to select prediction targets introduced ambiguity in model performance evaluation. This reanalysis identified the highest-performing prediction model, assuming a 100% coverage rate (COV) for all prediction target compounds and an estimated performance variation due to changes in COV. All models from both projects were evaluated using balance accuracy (BA), Matthews correlation coefficient (MCC), F1 Score (F1), and the first principal component (PC1). After normalizing the COV, a correlation analysis with these indicators was conducted, and the evaluation index for all prediction models in terms of the COV was estimated. In total, 109 models, the highest estimated BA (76.9) at 100% COV was MMI-VOTE1, reported by Meiji Pharmaceutical University (MPU). The best models for MCC, F1, and PC1 were all MMI-STK1, also reported by MPU. All models reported by MPU ranked in the top four. MMI-STK1 was estimated to have F1 scores of 59.2, 61.5, and 63.1 at COV levels of 90%, 60%, and 30%, respectively. These findings highlight the current state and potential of the Ames prediction technology.

The COVID-19 pandemic has wreaked havoc on the whole world, taking over half a million lives and capsizing the world economy in unprecedented magnitudes. With the world scampering for a vaccine, early detection and containment is the only redress. Existing diagnostic technologies with high accuracy like RT-PCRs are expensive and sophisticated, requiring skilled individuals for specimen collection and screening, resulting in lower outreach. So, methods excluding direct human intervention are much sought after, and artificial intelligence-driven automated diagnosis, especially with radiography images, captured the researchers' interest. This survey marks a detailed inspection of the deep-learning-based automated detection of COVID-19 works done to date, a comparison of the available datasets, methodical challenges like imbalanced datasets, and others, along with probable solutions with different pre-processing methods, and scopes of future exploration in this arena. We also benchmarked the performance of 315 deep models in diagnosing COVID-19, Normal, and Pneumonia from x-ray images of a custom dataset created from four others. The dataset is publicly available at https://github.com/rgbnihal2/COVID-19-X-ray-Dataset. Our results show that DenseNet201 model with Quadratic SVM classifier performs the best (accuracy: 98.16%, sensitivity: 98.93%, specificity: 98.77%) and maintains high accuracies in other similar architectures as well. This proves that even though radiography images might not be conclusive for radiologists, but it is so for deep learning algorithms for detecting COVID-19. We hope this extensive review will provide a comprehensive guideline for researchers in this field.

Detection of the region of interest (ROI) is a critical step in laryngeal image analysis for the delineation of glottis contour. The process can improve both computational efficiency and accuracy of the image segmentation task, which will facilitate subsequent analysis and characterization of the vocal fold vibration as it correlates with voice quality and pathology. This study aims to develop machine learning based approaches for automatic detection of ROI for glottis image sequences captured by high-speed video-endoscopy (HSV), a clinical laryngeal imaging modality. In particular, we first applied the supporting vector machine (SVM) method using histogram of oriented gradients (HOG) feature descriptor, and second, trained a convolutional neural network (CNN) model for this task. Comparisons are made for both approaches in terms of accuracy of recognition and computation time.

Measuring and predicting Carbon Emission (CE) is important to enabling the main culprit of various urgent environmental issues including global warming. However, prior studies did not fully incorporate the impact of micro-level urban streetscapes, which might lead to biased prediction of urban CE. To fill the gap, we developed an effective framework to predict residential CE in urban areas from widely existing and publicly available street-view images (SVI) using machine learning. First, we used a semantic segmentation algorithm to classify more than 30 streetscape elements from SVI images to describe the built environment whose features might affect residential and transportation CE. Second, based on the streetscapes quantified, we trained a 10-fold cross-validation method with various machine learning models to predict the CE at the 1KM grid level using CE data from the PlanetData. We found first, built environment features such as sidewalks, roads, fences, buildings, and walls are significantly correlated with the residential CE. Second, the presence of buildings and subtle streetscape features (e.g., walls, fences) indicates higher-density residential areas which are related to more residential CE. Third, vegetation (e.g., trees and grass) are reversely related to residential CE. Our findings shed light on the feasibility of using a single and open data source (i.e., the SVI) to effectively model neighborhood-level CE for regions across diverse urban forms. Our framework is useful for urban planners to inform new town development and urban regeneration towards the low CE goals.

AI applications are transforming the technology and digital sector, seamlessly integrating into the daily interactions of individuals with the digital world. Key entry points to the internet, such as search engines, are now complemented by recommendation systems that curate content on social networks, streaming platforms, and online marketplaces. Additionally, virtual assistants have become ubiquitous across various platforms. While these groundbreaking changes are gradually extending to several industries, there remains significant untapped potential for the application of artificial intelligence in diverse domains. The renewable energy sector, in particular, continually reinvents itself through research and innovation to meet the escalating demand. Positioned at the forefront of technological evolution, this industry is well-placed to effectively adopt and tailor the innovations of artificial intelligence to its specific needs. Presently, both emerging and established tools leverage elements of AI to enhance processes and introduce functionalities that were previously unattainable. If the current trajectory persists, AI-enhanced tools have the potential to assume a role as crucial to the future of engineering as computer-aided design (CAD) software is in contemporary times.

Predicting trip purpose from comprehensive and continuous smart card data is beneficial for transport and city planners in investigating travel behaviours and urban mobility. Here we propose a framework, ActivityNET, using machine learning (ML) algorithms to predict passengers’ trip purpose from smart card data and Points-of-Interest (POIs) data. The feasibility of the framework is demonstrated in two phases. Phase I focuses on extracting activities from individuals’ daily travel patterns from smart card data and combining them with POIs using the proposed ‘activity-POIs consolidation algorithm’. Phase II feeds the extracted features into an artificial neural network (ANN) with multiple scenarios and predicts trip purpose under primary activities (home and work) and secondary activities (entertainment, eating, shopping, child drop-offs/pick-ups and part-time work) with high accuracy. As a case study, the proposed ActivityNET framework is applied in Greater London and illustrates a robust competence to predict trip purpose. The promising outcomes demonstrate that the cost-effective framework offers high predictive accuracy and valuable insights into transport planning.

More and more people quantify their sleep using wearables and are getting obsessed in their pursuit of optimal sleep (“orthosomnia”). However, it is criticized that many of these wearables are giving inaccurate feedback and even can lead to negative daytime consequences. Acknowledging these facts, we here aim to extend previous findings [] in a new sample of 136 self-reported poor sleepers by implementing optimization procedures to minimize erroneous classification when ambulatory sensing sleep. Firstly, here, we introduce an advanced interbeat-interval (IBI) quality control using a random forest method to account for wearable recordings in naturalistic and more noisy settings. We further aim to improve sleep classification by opting for a loss function model instead of overall epoch-by-epoch accuracy to avoid model biases towards the majority class (i.e., “light sleep”). Using these implementations, we compare the classification performance between the optimized (loss function model) and the accuracy model. We use signals derived from PSG, one-channel ECG, and two consumer wearables: the ECG breast belt Polar® H10 (H10) and the Polar® Verity Sense (VS), an optical Photoplethysmography (PPG) heart-rate sensor. Results reveal high overall accuracy for the new model for ECG (86.3 %, κ=.79), H10 (84.4%, κ=.76), and VS (84.2%, κ=.75) with intended improvements in deep sleep and wake. In addition, the new optimized model displays moderate to high correlations and agreement with PSG on primary sleep parameters, while measures of reliability, expressed in intra-class correlations, suggest excellent reliability for most sleep parameters. Finally, it is demonstrated that the new model is still classifying sleep accurately in 4-classes in users taking heart-affecting and/or psychoactive medication which can be considered a prerequisite for use also in high age groups and/or with common disorders. Further improving and validating sleep stage classification algorithms with affordable wearables may resolve existing scepticism and open the door for such approaches in clinical practice.

Deep learning (DL), which is originated from an artificial neural network (ANN), is one of the major technologies of today's smart cybersecurity systems or policies to function in an intelligent manner. Popular deep learning techniques, such as Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN or ConvNet), Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM), Self-organizing Map (SOM), Auto-Encoder (AE), Restricted Boltzmann Machine (RBM), Deep Belief Networks (DBN), Generative Adversarial Network (GAN), Deep Transfer Learning (DTL or Deep TL), Deep Reinforcement Learning (DRL or Deep RL), or their ensembles and hybrid approaches can be used to intelligently tackle the diverse cybersecurity issues. In this paper, we aim to present a comprehensive overview from the perspective of these neural networks and deep learning techniques according to today's diverse needs. We also discuss the applicability of these techniques in various cybersecurity tasks such as intrusion detection, identification of malware or botnets, phishing, predicting cyber-attacks, e.g. denial of service (DoS), fraud detection or cyber-anomalies, etc. Finally, we highlight several research issues and future directions within the scope of our study in the field. Overall, the ultimate goal of this paper is to serve as a reference point and guidelines for the academia and professionals in the cyber industries, especially from the deep learning point of view.

Introduction. Until now, the impact of learning variables on consumers' choices concerning Chinese product brands in the international online shopping framework remains unknown. Accordingly, this study aims to examine the effect of those learning variables on global consumers' choices of Chinese product brands. Method. A total of 44,704 transactions related to the buying process have been collected from a programming language and the Octopus Software within a Chinese International Online Shopping platform. Analysis. The 44,704 transactions have been analyzed through a Decision Tree. Results. The study points out that the number of e-retailers' subscribers reinforces the international consumers' trust online. At the same time, the pricing levels and quantity of product availability are used by global online consumers to assess the originality of Chinese product brands. Conclusions. First, this study extends the existing literature on consumer learning by going beyond the learning variables considered. Second, the study boosts consumer learning literature by elucidating the most significant learning variables guiding international online consumers' choices and purchases. The application of the results will enable brands and e-retailers to understand (1) the stages of the international online consumers' choice; (2) the buying strategies of global consumers.

Structure–function relationships in proteins have been one of the crucial scientific topics. Heme proteins have diverse and pivotal biological functions. Therefore, clarifying their structure–function correlation is significant to understand their functional mechanism and is informative for various fields of science. In this study, we constructed convolutional neural network models for predicting protein functions from the tertiary structures of heme-binding sites (active sites) of heme proteins to examine the structure–function correlation. As a result, we succeeded in the classification of oxygen-binding protein (OB), oxidoreductase (OR), proteins with both functions (OB–OR), and electron transport protein (ET) with high accuracy. Although the misclassification rate for OR and ET was high, the rates between OB and ET and between OB and OR were almost zero, indicating that the prediction model works well between protein groups with very different functions. However, predicting the function of proteins modified with amino acid mutation(s) remains a challenge. Our findings indicate a structure–function correlation in the active site of heme proteins. This study is expected to be applied to the prediction of more detailed protein functions such as catalytic reactions.

Accurately quantifying the above-ground volume (AGV) and thus above-ground biomass (AGB) of forest stands is an important aspect in the conservation of mangrove ecosystem owing to their ecological and economic benefits. However, the number of studies focusing on quantifying mangrove forests’ biomass has been relatively low due to their marshy terrain, making exploratory studies challenging. In recent times, the use of LiDAR technologies in forest inventory studies has become increasingly popular, due to the reliability of LiDAR as a highly accurate means of 3D spatial data acquisition. In this study, we propose an end-to-end methodology for estimating AGV of mangrove forest stands from terrestrial LiDAR data. Many of the recent studies on this topic effectively employ machine learning algorithms such as multi layer perceptron, random forests, etc. for filtering foliage in the point cloud data of single trees. This study further extends that approach by incorporating the impact of class imbalance of forest point cloud data in a weighted random forest classifier. For the task of segmentation of wood/foliage points in a single tree point cloud, this approach yielded an average increase of 2.737% in the balanced accuracy score, 0.007 in the Cohen’s kappa score, 2.745% in the ROC AUC score and 0.857% in the F1 score. For the task of AGV estimation of a single tree, this approach resulted in an average coefficient of determination of 0.93 with respect to the ground truth volumes. For the task of counting pneumatophores in a plot-level point cloud, the proposed breadth-first searching method yielded an average coefficient of determination of 0.9391. Also, the machine learning classifier and geometric features used in this study were invariant to tree species and hence could be generalised for the classification of point clouds of other tree species as well. Finally, a breadth-first graph-search segmentation based approach is also proposed as part of this pipeline to estimate the contribution of pneumatophores to the AGB of mangrove forest stands. Since pneumatophores are a special adaptation of mangrove forests for gaseous exchange in marshy environments, this study aims to incorporate the detection and AGB estimation of pneumatophores in the inventory of mangrove forest stands. Studying the contribution of pneumatophores to the AGB of mangrove forest plots could also aid future mangrove forest inventory studies in modeling the underlying root network and estimating the below-ground biomass of mangrove trees.

Development of supervised AI algorithms requires a large amount of labeled images. Image labelling is both time-consuming and expensive. Therefore, we explored the value of e-learning derived annotations for AI algorithm development in medical imaging. Methods We have developed an e-learning platform that involves image-based single click labelling as part of the educational learning process. Ten radiology residents, as part of their residency training, trained the recognition of pneumothorax on 1161 chest X-rays in posterior-anterior projection. Using this data, multiple AI algorithms for detecting pneumothorax were developed. Classification and localization performance of the models was tested on an independent internal testing dataset and on the public NIH ChestX-ray14 dataset. Results The AI models F1 scores on the internal and the NIH dataset were 0.87 and 0.44, respectively. Sensitivity was 0.85 and 0.80 for classification and specificity 0.96 and 0.48 for classification. F1 scores were 0.72 and 0.66, sensitivity 0.72 and 0.72. False positive rate was 0.36 and 0.32 for localisation. Conclusion Our results demonstrated that e-learning derived annotations are a valuable data source for algorithm development. Further work is needed to include additional parameters such as user performance, consensus of diagnosis, and quality control in the development pipeline.

The ‘inverse problem’ of mass spectrometric molecular identification (‘given a mass spectrum, calculate/predict the 2D structure of the molecule whence it came’) is largely unsolved, and is especially acute in metabolomics where many small molecules remain unidentified. This is largely because the number of experimentally available electrospray mass spectra of small molecules is quite limited. However, the forward problem (‘calculate a small molecule’s likely fragmentation and hence at least some of its mass spectrum from its structure alone’) is much more tractable, because the strengths of different chemical bonds are roughly known. This kind of molecular identification problem may be cast as a language translation problem in which the source language is a list of high-resolution mass spectral peaks and the ‘translation’ a representation (for instance in SMILES) of the molecule. It is thus suitable for attack using the deep neural networks known as transformers. We here present MassGenie, a method that uses a transformer-based deep neural network, trained on ~6 million chemical structures with augmented SMILES encoding and their paired molecular fragments as generated in silico, explicitly including the protonated molecular ion. This architecture (containing some 400 million elements) is used to predict the structure of a molecule from the various fragments that may be expected to be observed when some of its bonds are broken. Despite being given essentially no detailed nor explicit rules about molecular fragmentation methods, isotope patterns, rearrangements, neutral losses, and the like, MassGenie learns the effective properties of the mass spectral fragment and valency space, and can generate candidate molecular structures that are very close or identical to those of the ‘true’ molecules. We also use VAE-Sim, a previously published variational autoencoder, to generate candidate molecules that are ‘similar’ to the top hit. In addition to using the ‘top hits’ directly, we can produce a rank order of these by ‘round-tripping’ candidate molecules and comparing them with the true molecules, where known. As a proof of principle, we confine ourselves to positive electrospray mass spectra from molecules with a molecular mass of 500Da or lower, including those in the last CASMI challenge (for which the results are known), getting 49/93 (53%) precisely correct. The transformer method, applied here for the first time to mass spectral interpretation, works extremely effectively both for mass spectra generated in silico and on experimentally obtained mass spectra from pure compounds. It seems to act as a Las Vegas algorithm, in that it either gives the correct answer or simply states that it cannot find one. The ability to create and to ‘learn’ millions of fragmentation patterns in silico, and therefrom generate candidate structures (that do not have to be in existing libraries) directly, thus opens up entirely the field of de novo small molecule structure prediction from experimental mass spectra.

In this paper, we present the design of a wearable photoplethysmography (PPG) system, R-band for acquiring the PPG signals. PPG signals are influenced by the respiration or breathing process and hence can be used for estimation of respiration rate. R-Band detects the PPG signal that is routed to a Bluetooth low energy device such as a nearbyplaced smartphone via microprocessor. Further, we developed an algorithm based on Extreme Learning Machine (ELM) regression for the estimation of respiration rate. We proposed spectral kurtosis features that are fused with the state-ofthe-art respiratory-induced amplitude, intensity and frequency variations-based features for the estimation of respiration rate (in units of breaths per minute). In contrast to the neural network (NN), ELM does not require tuning of hidden layer parameter and thus drastically reduces the computational cost as compared to NN trained by the standard backpropagation algorithm. We evaluated the proposed algorithm on Capnobase data available in the public domain.

While thunderstorms can pose severe risks to property and life, forecasting remains challenging, even at short lead times, as these often arise in meta-stable atmospheric conditions. In this paper, we examine the question of how well we could perform short-term (up to 180min) forecasts using exclusively multi-spectral satellite images and past lighting events as data. We employ representation learning based on deep convolutional neural networks in an “end-to-end” fashion. Here, a crucial problem is handling the imbalance of the positive and negative classes appropriately in order to be able to obtain predictive results (which is not addressed by many previous machine-learning-based approaches). The resulting network outperforms previous methods based on physically-based features and optical flow methods (similar to operational prediction models) and generalizes across different years. A closer examination of the classifier performance over time and under masking of input data indicates that the learned model actually draws most information from structures in the visible spectrum, with infrared imaging sustaining some classification performance during the night.

Early detection of cancer increases the probability of recovery. This paper presents an intelligent decision support system (IDSS) for the early diagnosis of cancer based on gene expression profiles collected using DNA microarrays. Such datasets pose a challenge because of the small number of samples (no more than a few hundred) relative to the large number of genes (on the order of thousands). Therefore, a method of reducing the number of features (genes) that are not relevant to the disease of interest is necessary to avoid overfitting. The proposed methodology uses the information gain (IG) to select the most important features from the input patterns. Then, the selected features (genes) are reduced by applying the grey wolf optimization (GWO) algorithm. Finally, the methodology employs a support vector machine (SVM) classifier for cancer type classification. The proposed methodology was applied to two datasets (Breast and Colon) and was evaluated based on its classification accuracy, which is the most important performance measure in disease diagnosis. The experimental results indicate that the proposed methodology is able to enhance the stability of the classification accuracy as well as the feature selection