With the development of deep learning, several Graph Neural Networks (GNN)-based approaches have been utilized for text classification. However, GNNs encounter challenges in capturing contextual text information within a document sequence. To address this, a novel text classification model RB-GAT is proposed by combining RoBERTa-BiGRU embedding and a multi-head Graph ATtention Network (GAT). First, the pre-trained RoBERTa model is exploited to learn word and text embeddings in different contexts. Second, the Bidirectional Gated Recurrent Unit (BiGRU) is employed to capture long-term dependencies and bidirectional sentence information from the text context. Next, the multi-head graph attention network is applied to analyze this information, which serves as a node feature for the document. Finally, the classification results are generated through a Softmax layer. Experimental results on three benchmark datasets demonstrate that our method can achieve an accuracy of 71.48%, 98.45%, and 80.32% on Ohsumed, R8, and MR, which is superior to the existing nine text classification approaches.

Fraudulent transactions pose a significant threat to financial institutions and e-commerce platforms.Machine learning models, trained on historical labeled data (fraudulent vs. legitimate transactions), are often employed to identify and prevent fraud. However, real-world datasets frequently exhibit class imbalance, where fraudulent transactions (minority class) are significantly outnumbered by legitimate transactions (majority class). Machine learning models may perform poorly as a result of this imbalance, underestimating fraud and favouring the majority class. This paper proposes a novel approach to address class imbalance and improve fraud detection accuracy. We explore the implementation of FROST (Feature space RObust Synthetic saTuration) oversampling, a technique specifically designed to generate synthetic samples for the minority class. The FROST function leverages the k-nearest neighbors (KNN) algorithm and a user-defined amplification factor (m) to create synthetic data points that closely resemble existing minority class instances. We integrate the FROST-enhanced oversampling technique into the machine learning pipeline for fraud detection. The paper evaluates the effectiveness of this approach compared to traditional oversampling methods and analyzes its impact on classification accuracy metrics.

Background: Fine-needle aspiration cytology (FNAC) is widely used to diagnose and monitor thyroid nodules. The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) is the standard for interpreting FNAC specimens. The risk of malignancy in Bethesda III nodules also known as Atypia of Undetermined Significance (AUS) varies significantly throughout several studies published worldwide. This retrospective study examines the risk of cancer in thyroid FNAC categorized as Bethesda III, as identified in the final histopathology of thyroidectomy specimens at a single endocrine surgery center. Methods: This retrospective cohort analysis included 1038 consecutive patients who underwent elective thyroid surgery with complete follow up data between January 2020 and March 2024. Preoperative data on clinical and pathological characteristics have been collected. The final histopathology report from the thyroidectomy specimen was compared to the results of the preoperative FNAC on nodules that were judged to be Bethesda category III. Statistical methods were performed using SPSS version 29. Results: A total of 670 ultrasound-guided FNACs (64.5%) performed during the study period were included in the final analysis. The study population was predominantly female, represented by 79.6% of patients with a mean age of 42.5 (SD 12.1), while 20.4% were male and significantly older with mean age 45.13 years (p = 0.02). The FNAC inadequacy rate was 5.1%, which was associated with a high risk of malignancy (6 out of 34, 17.6%). Out of the total sample size of 170 patients classified as group III, 57 were found to have malignancies in final surgical histopathology, representing 33.5% of the cases within this category. The secondary gender-related outcome analysis showed that female patients classified under the Bethesda II category had a significantly higher risk of malignancy, with a rate of 21.2%, compared to males who had a malignancy rate of 3.4% in the same Bethesda category (p = 0.001, chi square test). However, female had more better prognostic non-invasive tumors than male (p = 0.02, chi square test). Conclusion: The study's results indicate that Bethesda categories II and III are associated with a higher risk of malignancy in comparison to the reports of the first and third editions of the TBSRTC, particularly for female patients classified under category II.

In the extensive monitoring of maritime traffic, maritime management frequently encounters incomplete automatic identification system (AIS) data, particularly in critical static fields like vessel types. This shortfall presents substantial challenges in safety management, necessitating robust methods for data completion. Distinct from road traffic, where road width imposes constraints, maritime vessels of identical classifications often choose significantly divergent routes, deviating by several nautical miles. Sole dependence on trajectory clustering is insufficient. Addressing this issue, we segments the maritime area into spatiotemporal grids, transforming vessel paths into sequences of grid encodings. Utilizing natural language processing techniques, we integrate the Word2vec word embedding approach with our novel biLSTM self-attention chunk-max pooling net (biSAMNet) model, enhancing the classification of vessel trajectories. This method is crucial for determining static details like vessel types. Employing the Taiwan Strait as a case study and benchmarking against CNN, RNN, and methods based on the attention mechanism, our findings underscore our model’s superiority. The biSAMNet achieves an impressive vessel classification F1 score of 0.94, using only 5-dimensional word embeddings, highlighting the effectiveness of Word2vec pre-trained embedding layers. This research introduces a novel paradigm for processing vessel trajectory data, greatly enhancing the accuracy of filling in incomplete vessel type details.

In Indonesia, types of meat are still identified manually due to increasing prices for beef and buf-falo ahead of Idul Fitri. Traders mix beef with pork to thwart the beef scam. Haar wavelet and GLCM, GLCM with angles of 0°, 45°, 90°, and 135°, as well as matrices using contrast, correlation, energy, homogeneity, and entropy, are used in feature extraction. The following are the results of meat image classification testing using k-NN, Haar wavelet, and GLCM: The k-NN algorithm shows superiority in identifying fresh (99%), frozen (99%), and rotten (96%) meat texture images with the most fantastic accuracy results in every situation. Meanwhile, GLCM routinely provides good results, especially regarding the texture image of fresh meat (183.21) and rotten meat (115.79). However, despite delivering less throughput than k-NN and GLCM, Haar wavelets are still helpful, especially when dealing with fresh meat texture images (89,96).

Accurate diagnosis for the 400 million people with rare diseases is critical for healthcare decisions, prognosis, understanding disease mechanisms, and identification of treatments. Despite advances in genome sequencing, barriers such as high interpretation costs, diagnostic expertise, throughput associated delays, and uncertain variant classifications persist, with demand exceeding capacity. Many variant classification methods focus narrowly on specific consequences, leading to the use of complex integrative pipelines that often overlook transcript variability and lack prediction transparency. To overcome these limitations, we introduce DITTO. This transparent, transcript-aware machine-learning method demonstrates superior overall performance in accuracy, recall, and precision when compared to existing tools. DITTO is publicly available at https://github.com/uab-cgds-worthey/DITTO

Landslides, resulting from disturbances in slope equilibrium, pose a significant threat to landscapes, infrastructure, and human life. Triggered by factors such as intense precipitation, seismic activities, or volcanic eruptions, these events can cause extensive damage and endanger nearby communities. A comprehensive understanding of landslide characteristics, including spatio-temporal patterns, dimensions, and morphology, is vital for effective landslide-disaster management. Existing Remote Sensing approaches mostly use either optical or Synthetic Aperture Radar (SAR) sensors. Integrating information from both these types of sensors promises greater accuracy for identifying and locating landslides. This study proposes a novel approach, the ML-LaDeCORsat (Machine Learning-based coseismic Landslide Detection using Combined Optical and Radar Satellite Imagery), that integrates freely available Sentinel-1, Palsar-2, and Sentinel-2 imagery data, along with relevant spectral indices and suitable bands using machine-learning-based classification for coseismic landslide detection implemented in Google Earth Engine (GEE). The approach includes a robust and reproducible training and validation strategy. Using landslides from four different earthquake case studies, we demonstrate the superiority of our approach over existing solutions in coseismic landslide iden-tification and localization, providing a detection accuracy of 87-92%. ML-LaDeCORsat can be adapted to other landslide events (GEE script is provided). Transfer learning experiments proofed that our model can be applied to other coseismic landslide events without the need for additional training data. Our novel approach therefore facilitates quick and reliable identification of co-seismic landslides, highlighting its potential to contribute towards more effective disaster management.

Aggressive mature T-cell lymphoma (TCL) is a disease that carries a poor prognosis. The mechanism, at the functional protein level, of the resistance to therapy of TCL has not yet been well clarified. To comprehensively clarify the mechanism, we first reviewed the literature, as mentioned in the Introduction section, on 22 types of representative functional proteins reported as being potentially associated with treatment resistance, mainly in hematologic tumors. Next, we retrospectively analyzed the tumor cell expressions of these 22 functional proteins in 16 randomly selected patients with TCL who had received CHOP (cyclophosphamide, hydroxyl doxorubicin, oncovin, and prednisolone) therapy as first-line treatment. As a result, we propose a new three-group prognostic classification of TCL (the TCL Urayasu Classification) based on the mechanism of resistance to treatment of these tumors. The study subjects included 7 patients (44%) with peripheral T-cell lymphoma, not otherwise specified (PTCL-NOS), 6 patients (38%) with angioimmunoblastic T-cell lymphoma (AITL), and 3 patients (19%) with anaplastic large T-cell lymphoma (ALCL). Immunohistochemistry was performed in paraffin-embedded tumor tissue sections prepared from these patients as antigens using antibodies against the 22 previously reported treatment-resistance-related proteins to determine the tumor cell expression statuses of these proteins. Log-rank test was performed to compare the overall survival (OS) after CHOP therapy of the patients showing positive and negative immunostaining for these proteins, as well as among patients grouped based on other factors. Overall, the median OS of the TCL patients was about 33.5 months. When compared by the disease type, the prognosis was found to be worse in the order of ALCL, AITL, and PTCL. A multivariate analysis showed that expression of glucose-regulated protein 94 (GRP94), a protein that serves as a pro-survival component under endoplasmic reticulum (ER) stress in the tumor microenvironment, was significantly associated with shortened survival. No significant difference was observed for the conventional poor prognostic factors: high-risk International Prognostic Index (IPI) and high-risk Prognostic Index for peripheral T-cell lymphoma, unspecified (PTCL-U) (PIT). However, when GRP94 was combined with six other factors, listed below, as survival-shortening factors, significant differences were observed. The 6 factors were 1) programmed cell death-ligand 1 (PD-L1) and 2) programmed cell death 1 (PD-1), which are involved in immune surveillance; 3) aldo-keto reductase family 1 member C3 (AKR1C3), which is an enzyme that inactivates HO (hydroxyl doxorubicin [H] and oncovin [O]) of CHOP; 4) P53, a tumor suppressor; 5) Glucose-regulated protein 78 (GRP78), an ER stress protein; 6) thymidine phosphorylase (TP), which is an enzyme involved in thymidine catabolism. Based on the combination of GRP94 and the six other factors expressed in the tumors, we propose a new prognostic classification system for TCL (TCL Urayasu classification). Group 1 (group with a relatively good prognosis): GRP94-negative (n = 6; median OS, 88 months; p < 0.01); Group 2 (group with a poor prognosis): GRP94-positive, plus expression of 2 of the 6 aforementioned factors (n = 5; median OS, 25 months; p > 0.05); and Group 3 (group with a very poor prognosis): GRP94-positive, plus expression of at least 3 of the 6 aforementioned factors (n = 5; median OS, 10 months; p < 0.01). Thus, the TCL Urayasu prognostic classification is a simple, useful, and innovative classification that also explains the mechanism of resistance to treatment for each functional protein. Accumulation of more cases and further analyses are expected in the future to enable clinical application, such as use of a stratified treatment approach and treatment using inhibitors.

This paper explores the capability of various machine learning algorithms, including Random Forests and advanced gradient boosting techniques such as XGBoost, LightGBM, and CatBoost, to predict customer churn in the telecommunications sector. For this analysis, a dataset available to the public was employed. The performance of these algorithms was assessed using recognized metrics, including Accuracy, Precision, Recall, F1-score, and the Receiver Operating Characteristic Area Under Curve (ROC AUC). These metrics were evaluated at different phases: subsequent to data preprocessing and feature selection; following the application of SMOTE and ADASYN sampling methods; and after conducting hyperparameter tuning on the data that had been adjusted by SMOTE and ADASYN. The outcomes underscore the notable efficiency of upsampling techniques such as SMOTE and ADASYN in addressing the imbalance inherent in customer churn prediction. Notably, the application of random grid search for hyperparameter optimization did not significantly alter the results, which remained comparatively unchanged. The algorithms' performance post- ADASYN application marginally surpassed that observed after SMOTE application. Remarkably, LightGBM achieved an exceptional F1-score of 89% and an ROC AUC of 95% subsequent to the ADASYN sampling technique. This underlines the effectiveness of advanced boosting algorithms and upsampling methods like SMOTE and ADASYN in navigating the complexities of imbalanced datasets and intricate feature interdependencies.

Quaking aspen (Populus tremuloides Michx.) is an important deciduous species in western U.S. forests. Existing maps of aspen distribution are based on Landsat imagery and often miss small stands (&lt;0.09 ha or 30 m²), which rapidly regrow when managed or following disturbance. In this study, we present methods for deriving a new regional map of aspen forests using one year of Sentinel-1 (S1) and Sentinel-2 (S2) imagery in Google Earth Engine. We assessed the annual phenology of aspen in the Southern Rockies and leveraged the frequent temporal resolution of S1 and S2 to create ecologically relevant seasonal composites. Additionally, we derived spectral indices and radar textural features targeting the canopy structure, moisture, and chlorophyll content. Using spatial block cross-validation and Random Forests, we assessed the accuracy of different scenarios and selected the best performing set of features for classification. Comparisons were then made with existing landcover products across the study region. The resulting map improves on existing landcover products in both accuracy (average F1-score = 93.1%) and detection of smaller forest patches. These methods enable accurate mapping at spatial and temporal scales relevant to forest management for one of the most widely distributed tree species in North America.

Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant scattering information of objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. Although significant progress has been achieved in related research, there are still issues such as insufficient utilization of polarimetric information and features. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features inputted into the deep learning network are the power values of polarimetric channels, where these channels are treated equivalently and contain complete polarimetric information. In terms of experimental comparative study, besides polarimetric power combinations, three different data input schemes were employed as data for the input end of the convolutional neural network (CNN), taking into account existing research. The neural networks utilizes the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of different input schemes. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification.

Timely and accurate information on tree species is crucial for the sustainable management of natural resources, forest inventory, biodiversity detection, and carbon stock calculation. The advancement of remote sensing technology and artificial intelligence has facilitated the acquisition and analysis of remote sensing data, resulting in more precise and effective classification of tree species. Multimodal remote sensing data and deep learning seem to be the current tree species classification research mainstream, whether or not. The current review on the remote sensing data and deep learning tree species classification methods perspectives to analyze the unimodal and multimodal remote sensing data and classification methods in this realm is missing. To bridge the gap, we search for major trends in the remote sensing data and tree species classification methods, provide a detailed overview of classic deep learning-based methods for tree species classification, and discuss the limitations.

The profile of secondary metabolites occurring in apple cuticular layer is not only characteristic for particular apple cultivar, but also dynamically reflects various external factors in growing environment. In this study, the possibility to authenticate apple samples based on analysis of their cuticular layer extracts was investigated. Ultra-high-performance liquid chromatography coupled to high resolution tandem mass spectrometry (UHPLC-HRMS/MS) was employed for obtaining metabolomic fingerprints. In total, 274 authentic apple samples, four cultivars harvested within the seasons 2020 to 2022 in the Czech Republic and Poland were analysed. The generated complex data processed by univariate and multivariate statistical methods enabled to build classification models for discrimination of apple cultivars as well as their geographical origin. The models showed very good performance in differentiation of Czech and Polish samples for three of four cultivars: ‘Gala’, ‘Golden Delicious’ and ‘Idared’, moreover, the validity of the models was verified over harvest seasons. The diagnostic markers, besides metabolites of triterpene biosynthetic pathway, mainly represented wax esters. ‘Jonagold’, which is known to be susceptible to mutations, was the only cultivar for which the unambiguous classification of geographical origin was not possible.

Multivariate Time Series Classification (MTSC) is one of most important tasks in time series analysis, aiding in activities such as human motion recognition and medical diagnostics. Existing methods for MTSC do not explicitly model temporal differences and generalize the idea of temporal difference into a efficient temporal module. Additionally, existing methods are not yet able to capture cross-variable relationships well during network training. As a result, they are unable to achieve convincing feature representation, leading to suboptimal classification accuracy. In this paper, we propose a novel MTSC model called Temporal Difference and Cross-variate Fusion Network (TDCFN), which integrates a two-stream differential LSTM network and a cross-variate feature extraction network to enhance feature representation. TDCFN achieves superior classification accuracy by capturing dynamic temporal evolution and inter-variable relationships. The experimental results show that TDCFN can achieve competitive performance with state-of-the-art multivariate time series classification approaches.

Postpartum haemorrhage (PPH) is a significant cause of maternal morbidity and mortality worldwide, particularly in low-resource settings. This study aimed to develop a predictive model for PPH using early risk factors and rank their importance in terms of predictive ability. The dataset was obtained from an observational case-control study in Northern Rwanda. Various statistical models and machine learning techniques were evaluated, including logistic regression, logistic re-gression with elastic-net regularisation, Random Forest, Extremely Randomized Trees, and gradient boosted trees with XGBoost. Random Forest emerged as the best predictive model for PPH across three different train-test data partitions. The important predictors identified in the study were haemoglobin level during labour and maternal age. However, there were differences in PPH risk factor importance in different data partitions, highlighting the need for further investigation. These findings contribute to understanding PPH risk factors, highlight the importance of considering different data partitions and implementing cross-validation in predictive modelling, and emphasise the value of identifying the appropriate prediction model for the application. Effective PPH pre-diction models are essential for improving maternal health outcomes on a global scale. This study provides valuable insights for healthcare providers to develop predictive models for PPH to identify high-risk women and implement targeted interventions

Incorrect sitting posture, characterized by asymmetrical or uneven positioning of the body, often leads to spinal misalignment and muscle tone imbalance. Prolonged maintenance of such postures can adversely impact well-being and contribute to the development of spinal deformities and musculoskeletal disorders. In response, smart-sensing chairs equipped with cutting-edge sensor technologies have been introduced as a viable solution for real-time detection, classification, and monitoring of sitting postures, aiming to mitigate the risk of musculoskeletal disorders and promote overall health. This comprehensive literature review evaluates the current body of research on smart-sensing chairs, with a specific focus on the strategies used for posture detection and classification, as well as the effectiveness of different sensor technologies. A meticulous search across MDPI, IEEE, and Google Scholar databases yielded 34 pertinent studies that utilize non-invasive methods for posture monitoring. The analysis reveals that Force Sensing Resistors (FSR) are the predominant sensors utilized for posture detection, whereas Convolutional Neural Networks (CNN) and Artificial Neural Networks (ANN) are the leading machine learning models for posture classification. However, it was observed that CNNs and ANNs do not outperform traditional statistical models in terms of classification accuracy, due to constrained size and lack of diversity within training datasets. These datasets often fail to comprehensively represent the array of human body shapes and musculoskeletal configurations. Moreover, this review identifies a significant gap in the evaluation of user feedback mechanisms, essential for alerting users to their sitting posture and facilitating corrective adjustments.

Conclusions: Our findings suggest that the NMS-E represents a valuable preoperative diagnostic tool for endometriosis, effectively correlating with the disease's severity and surgical outcomes. Incorporating the NMS-E into clinical practice could significantly enhance the management of endometriosis by addressing current diagnostic limitations and guiding surgical planning.

Understanding clinical significance of variants of unknown significance (VUS) reported in next-generation sequencing (NGS) has become essential in cancer treatment. Our study examined six widely used in silico tools: PolyPhen-2, Align-GVGD, MutationTaster2, CADD, REVEL, and Chat-GPT. We utilized a dataset of gene variants known to potentially affect immune therapy. No single tool could comprehensively determine mutation variant pathogenicity. MutationTaster2021 showed the highest overall accuracy and MCC among the tools. Notably, REVEL and Chat-GPT exhibited 100% specificity, suggesting their proficiency in accurately identifying pathogenic variants and minimizing false positives. In contrast, CADD displayed optimal sensitivity, making it suitable for effectively ruling out benign variants.

Efficient triaging and referral assessment are critical in ensuring prompt medical intervention in the Community Health Care (CHC) system. However, the existing triaging systems in many Community Health Services are an intensive, time-consuming process and often lack accuracy, particularly for various symptoms that might represent heart failure or other health-threatening conditions. There is a noticeable limit of research papers describing AI technologies for triaging patients. This paper proposes a novel quantitative data-driven approach using machine learning (ML) modelling to improve the community clinical triaging process. Furthermore, this study aims to employ the feature selection process and machine learning power to reduce the triaging process’s waiting time and increase accuracy in clinical decision-making. The model was trained on medical records of “Heart Failure” patients’ dataset, which included demographics, past medical history, vital signs, medications, and clinical symptoms. A comparative study was conducted using the list of machine learning algorithms where XGBoost demonstrated the best performance among other ML models. The triage levels of 2,35,982 patients achieved an accuracy of 99.94%, precision of 0.9986, recall of 0.9958, and f1-score of 0.9972 within 0.059 seconds. The proposed diagnostic model can be implemented for the CHC decision system and be developed further for other medical conditions.

It is the aim of this article to introduce a concise notation that is be able to capture the most important dimensions of sexuality and thus facilitate discussions. Moreover, the major three dimensions - sex, gender, and sexual orientation - lead to a straightforward classification which motivates the quest for stringent explanatory models, some of which are also discussed.

Sentiment analysis plays a crucial role in understanding customer feedback, guiding product development, and informing business decisions. This paper introduces term sentiment entropy (TSE), a novel weighting method that leverages the distribution of sentiment labels associated with words to enhance text classification accuracy. TSE complements traditional TF-IDF techniques by capturing the nuances of sentiment variation across different contexts. Experiments across diverse public datasets demonstrate TSE's potential to improve sentiment analysis performance, especially in capturing subtle sentiment shifts and adapting to specific domains. While computational cost and label quality pose challenges, TSE offers a promising avenue for refining sentiment analysis and opening new research frontiers.

Malocclusions have a continuously increasing prevalence from a generation to another as a result of climate changes, soil, atmosphere and water pollution. All of these aspects have unfavorable consequences on the nutritional scheme. Thus, nutrition together with other etiopathogenic factors contribute to complex alterations in the somatic development of the entire organism and, implicitly, of the cephalic extremity. The study group included 4147 children from randomly selected schools from Vâlcea County, Romania. The aim of this study is to determine the prevalence of malocclusions in schoolchildren from Vâlcea County, Romania, according to the three main classes of malocclusions (according to Angle’s classification), age groups (from 6 to 10 years old and from 11 to 14 years old), gender (male and female) and place of origin (rural and urban). For Angle class I malocclusions we recorded the highest prevalence (48,78% from the total number of schoolchildren with malocclusions), followed by Angle class II malocclusions (45,85% from the total number of schoolchildren with malocclusions) and for Angle class III malocclusions we found the lowest prevalence (5,37% from the total number of schoolchildren with malocclusions).According to gender, we found the highest prevalence in female gender (29,90% from the total number of female subjects), while in male gender we recorded a prevalence of 27,70% from the total number of male subjects. Regarding the place of origin, there is a higher prevalence of malocclusions in the urban areas (29,16%). The study subgroup included 140 children randomly selected from the total number of subjects from the study group. They were included in a more advanced study. The aim is to find potential associations between the presence of malocclusions and various oral variables. Categorical variables were expressed as numerical values and percentages, and their association was evaluated with either the Chi-square test of association or homogeneity, or the Fisher Exact test. The acquired data were incorporated into a binomial logistic regression model to assess the likelihood of developing malocclusions in relation to the following variables: defective phonation, bruxism, frequency of teeth brushing, onychophagia, oral respiration, infantile deglutition, placing objects between the maxillaries, thumb sucking and salivary aspects. It is also aimed to compare the results obtained with similar ones from the specialized literature.

Herein, we examined the effects of weather parameters and individual clinicodemographic risk factors on hemorrhagic stroke (HS) incidence, severity on admission, and disability at discharge in a harsh desert climate. In a retrospective design we studied patients admitted to a stroke unit in Arab Emirates in 2016-2019. With a distributed lag nonlinear model we explored immediate and delayed effects of weather on stroke incidence. Supervised machine learning was used to build models predictive of scores in NIHSS and mRS scales. We assessed model performance by calculating ROC AUC, F1 scores, specificity, and sensitivity. HS risk increased after a significant change in any weather parameter. The risk was reduced below baseline after 1-week adjustment to environmental changes. Climate input from the previous 3 days yielded reliable classification models. Humidex was a better predictor of severity than air temperature, whereas body mass index, age, and time of day at stroke onset were the strongest clinical predictors. Weather parameters before admission were stronger predictors of disease severity than individual clinical factors. We addressed limitations of previous studies by analyzing a full set of climate parameters: ambient temperature, relative humidity, humidex, atmospheric pressure, and wind speed. Predictive models may help to optimize patient management and develop preventative strategies.

Evolution remains an incessant process in viruses, allowing them to elude host immune response and induce severe diseases, impacting the diagnostic and vaccine effectiveness. Predicting emerging viral genomes is crucial, particularly in diseases like dengue, where viruses disrupt host cells, leading to fatal outcomes. Deep learning has been applied to predict dengue fever cases; there has been relatively less emphasis on its significance in forecasting emerging Dengue Virus (DENV) serotype. While Recurrent Neural Networks (RNN) were originally designed for modeling temporal sequences, our proposed DL-DVE generative and classification model, trained on complete genome data of DENV, transcends traditional approaches by learning semantic relationships between nucleotides in a continuous vector space instead of representing contextual meaning of nucleotide characters. Leveraging 2000 publicly available DENV complete genome sequences, our Long Short-Term Memory (LSTM) based generative and Feedforward Neural Network (FNN) based classification DL-DVE model showcases proficiency in learning intricate patterns and generating sequences for emerging serotype of DENV. The generative model showed accuracy of 93% and the classification model provided insight into the specific serotype label, corroborated by BLAST search verification. Evaluation metrics such as ROC-AUC value 0.818, accuracy, precision, recall and F1 score all to be around 99.00%, demonstrated the classification model’s reliability.  Our model classified the generated sequences as DENV-4, exhibiting 65.99% similarity to DENV-4 and around 63-65% similarity with other serotypes, indicating notable distinction from other serotypes. Moreover, the intra-serotype divergence of sequences with a minimum 90% similarity underscored their uniqueness. We analyzed the conserved motifs in the genome through MEME Suite (version 5.5.5). Our research strives to contribute to the ongoing fight against the Dengue virus by offering predictive insights into its genomic evolution. Looking ahead, proactive predictive modeling before mutations occur holds potential for guiding vaccine design and diagnostic kit development.

To ensure consumers can purchase high-quality rice, accurate identification of rice varieties is particularly important. Methods: This article conducts research based on machine learning algorithms from the perspectives of image, spectrum, and spectrogram fusion. Six types of hyperspectral image data of rice were preprocessed using convolutional smoothing (SG) and multiple scatter correction (MSC). Texture information of the images was extracted using gray-level co-occurrence matrix. Spectra, texture, and spectrogram data were fused into a new matrix. Spectral, texture, and spectrogram fusion data were used as inputs for the model, and support vector machines (SVM), logistic regression (LR), and K-nearest neighbors (KNN) classification models were constructed and compared. Results: From the classification results, the spectrogram fusion classification performance was better than classification models using only spectra or texture. Conclusion: The research results showed that the accuracy of SVM and LR classification models exceeded 90%, and the LR model performed the best, effectively classifying rice varieties.

Machine safety is not only a prerequisite for successful production, but also the foundation for sustainability and growth of any manufacturing organisation. The latest approaches in this rapidly developing field are the integration of effective risk management tools and strategies into occupational health and safety (OHS) systems. In this article, using a specific example from practice, we will show how using multi-criteria decision making (AHP) support Machinery Safety Decision Making (MSDM) from the point of reducing losses. Using Classification and Regression Tree Analysis (CART), we estimated the efficiency, cost-effectiveness and thus the sustainability level of the relevant safety measures. These were proposed risk reduction measures that typically raised uncertainty among managers regarding the estimation of cost-effectiveness. The advantage of application decision trees approach is possibility to identify and establish relatively homogeneous groups of undesirable events and their impact on the organisation's objectives. A comprehensive model has been developed to support management decision making in manufacturing organizations in implementing and improving safety measures in line with manufacturing sustainability goals.

Light detection and ranging (LIDAR) sensors using a polarization-diverse receiver are able to capture polarimetric information about the target under measurement. This information can be used in a classifier to make an instantaneous assessment of the type of material present, enabling a shot-by-shot prediction of the material type and distance to the target.

In the dynamic landscape of the telecommunications industry, understanding and mitigating customer churn is paramount for maintaining competitive advantage and sustaining revenue streams. This comprehensive literature review delves into the intricacies of customer churn prediction, a crucial aspect in fortifying the bond between telecom businesses and their customers. The review methodically analyzes 11 articles published between 2000 and March 2024, spotlighting the strategic role of Customer Relationship Management and the prevalence of high churn rates that necessitate a shift from customer acquisition to retention strategies. Furthermore, the review navigates through the challenges inherent in churn prediction, including the complexities of managing large, imbalanced, and noisy datasets and the intricacies involved in model selection and optimization. Despite these challenges, the paper highlights the superior capability of machine learning techniques in handling complex datasets to provide accurate predictions, albeit acknowledging their practical complexities. The main aim of the study is to provide an overview, serving as a knowledge base for researchers interested in machine learning techniques within the realm of telecommunications.

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

Accurate classification of objects in 3D point clouds is a significant problem in several applications, such as autonomous navigation and augmented/virtual reality scenarios, which has become a research hot spot. In this paper, we presented a deep learning strategy for 3D object classification in augmented reality. The proposed approach is a combination of the GRU and LSTM. LSTM networks learn longer dependencies well, but due to the number of gates, it takes longer to train; on the other hand, GRU networks have a weaker performance than LSTM, but their training speed is much higher than GRU, which is The speed is due to its fewer gates. The proposed approach used the combination of speed and accuracy of these two networks. The proposed approach achieved an accuracy of 0.99 in the 4,499,0641 points dataset, which includes eight classes (unlabeled, man-made terrain, natural terrain, high vegetation, low vegetation, buildings, hardscape, scanning artifacts, cars). Meanwhile, the traditional machine learning approaches could achieve a maximum accuracy of 0.9489 in the best case.

it still undergoes corrosion when exposed to corrosive environments. This paper proposes an evaluation method for assessing the corrosion level of SPCC steel specimens using traditional eddy current testing (ECT), along with two different machine learning approaches. The objective is to classify the corroded state of the specimens into two states: a less corroded state (state-1) and a highly corroded state (state-2). Generative and discriminative models were implemented for classification. The generative classifier was based on the Gaussian mixture model (GMM), while the discriminative model was based on the logistic regression model. The models used features based on the absolute maximum of the perturbation magnetic field components at two different frequencies. The performance of the classifiers was evaluated using metrics such as absolute error, accuracy, precision, recall, and F1 score. The results indicate that high classification accuracy can be achieved based on both methods using traditional eddy current testing.

The Eurasian grapevine (\textit{Vitis vinifera L.}) is the most widely grown horticultural crop in the world and is important for the economy of many countries. In the wine production chain, grape varieties play an important role, as they directly influence the authenticity and classification of the product. Identifying the different grape varieties is therefore fundamental for quality control and control activities, as well as for regulating production. Currently, ampelography and molecular analysis are the main approaches to identifying grape varieties. However, both methods have limitations. Ampelography is subjective and prone to errors and is experiencing enormous difficulties as ampelographers are increasingly scarce. On the other hand, molecular analyses are very demanding in terms of cost and time. In this scenario, Deep Learning (DL) methods have emerged as a classification alternative to deal with the scarcity of ampelographers and avoid molecular analyses. In this study, the most recent and current methods for identifying grapevine varieties using DL classification-based approaches are presented through a systematic literature review. The steps of the standard DL-based classification pipeline were described for the 18 most relevant studies found in the literature, highlighting their pros and cons. Potential directions for improving this field of research were also presented.

The application of deep learning algorithms to predict the molecular profiles of various cancers from digital images of hematoxylin and eosin (H&E)-stained slides has been reported in recent years, mainly in gastric and colon cancers. In this study, we investigated the potential use of H&E-stained endometrial cancer slide images to predict the associated mismatch repair (MMR) status. H&E-stained slide images were collected from 127 cases of the primary lesion of endometrial cancer. After digitization using a Nanozoomer virtual slide scanner (Hamamatsu Photonics), we segmented the scanned images into 5,397 tiles of 512 × 512 pixels. The MMR proteins (PMS2, MSH6) were immunohistochemically stained, classified into MMR proficient/deficient, and annotated for each case and tile. We trained several neural networks, including convolutional and attention-based networks, using tiles annotated with the MMR status. Among the tested networks, ResNet50 exhibited the highest area under the receiver operating characteristic curve (AUROC) of 0.91 for predicting the MMR status. The constructed prediction algorithm may be applicable to other molecular profiles and useful for pre-screening before implementing other, more costly genetic profiling tests.

The objectives of this paper are to investigate the tradeoffs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image, modern high-resolution satellite image data sets (Maxar WorldView data) and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100-200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.

Intrahepatic cholangiocarcinoma (ICCA) is a malignant epithelial neoplasm characterized by biliary differentiation within the liver. ICCA is molecularly heterogeneous and exhibits a broad spectrum of histopathological features. It is a highly aggressive carcinoma with high mortality and poor survival rates. ICCAs are classified into two main subtypes: small duct type and large duct types. These two tumor types have different cell origins and clinicopathological features. ICCAs are characterized by numerous molecular alterations, including mutations in KRAS, TP53, IDH1/2, ARID1A, BAP1, BRAF, SAMD4, and EGFR, and FGFR2 fusion. Two main molecular subtypes–inflammation and proliferation–have been proposed. Recent advances in high-throughput assays using next-generation sequencing have improved our understanding of ICCA pathogenesis and molecular genetics. The diagnosis of ICCA poses a significant challenge for pathologists because of its varied morphologies and phenotypes. Accurate diagnosis of ICCA is essential for effective patient management and prognostic determination. This article provides an updated overview of ICCA pathology, focusing particularly on molecular features, histological subtypes, and diagnostic approaches.

In this paper we describe a method which combines sentiment analysis with machine learning techniques and/or multivariate statistical analysis. By applying this methodology it is possible to classify a collection of texts into two or more groups or clusters. On the basis of a number of previously defined clusters, the novelty of the outlined approach is the use of the sentiment analysis results as input to the machine learning model or multivariate statistical analysis. Once the classifier has been obtained, we can assign a given text into one of the pre-established clusters. The groups or clusters can represent different time periods, classes of texts transcribed from different conversations, etc. The method is illustrated through an example taken from one of the two studies in which we have applied this methodology. In one of the studies, the method was used to classify press news of a volcanic eruption, while in the other study it was used to classify the conversations recorded between a chatbot with different kinds of speakers (humans or chatbots). This last study was the seminal work in which we introduced this methodology.

This study introduces SkinLiTE, a lightweight supervised contrastive learning model, tailored to enhance the detection and typification of skin lesions in dermoscopic images. The core of SkinLiTE lies in its unique integration of supervised and contrastive learning approaches, which leverages labeled data to learn generalizable representations. This approach is particularly adept at handling the complexities and imbalances inherent in skin lesions datasets. The methodology encompasses a two-phase learning process. In the first phase, SkinLiTE utilizes an encoder network and a projection head to transform and project dermoscopic images into a feature space where contrastive loss is applied, focusing on minimizing intra-class variations while maximizing inter-class differences. The second phase freezes the encoder's weights, leveraging the learned representations for classification through a series of dense and dropout layers. The model was evaluated using three datasets from Skin Cancer ISIC 2019-2020, covering a wide range of skin conditions. SkinLiTE demonstrated superior performance across various metrics—accuracy, AUC , and F1 score—particularly when compared with traditional supervised learning models. Notably, SkinLiTE achieved an accuracy of 0.9087 using AugMix augmentation for binary classification of skin lesions. It also showed comparable results with the state-of-the-art approaches of ISIC challenge without relying on external data, underscoring its efficacy and efficiency. The results highlight the potential of SkinLiTE as a significant step forward in the field of dermatological AI, offering a robust, efficient, and accurate tool for skin lesion detection and classification. Its lightweight architecture and ability to handle imbalanced datasets make it particularly suited for integration into Internet of Medical Things environments, paving the way for enhanced remote patient monitoring and diagnostic capabilities. This research contributes to the evolving landscape of AI in healthcare, demonstrating the impact of innovative learning methodologies in medical image analysis.

Most common classifications for acetabular bone defects are based on radiographic two-dimension imaging, with low reliability and reproducibility. With the rise of modern processing techniques based on 3D modelling, methodologies for volumetric quantification of acetabular bone loss are available. Our study aims to describe a new methodology for quantitative assess-ment of acetabular defects, based on 3D modelling, focused on the surface analysis of the integrity of the main anatomical structures of the acetabulum represented by four corresponding sectors (posterior, superior, anterior, and medial). The defect entity is measured as the Area Increase Ra-tio (AIR) detected in all the sectors analyzed on three planes of view (frontal, sagittal and axial) compared to healthy hemipelvises. The analysis was performed on 3D-models from the CT-scan of six exemplary specimens with a unilateral pathological hemipelvis. AIR between the native and the pathological hemipelvis was calculated for each sector, for a total of 48 analysis (range, +0.93% - +171.35%). AIR of >50% were found in 22/48(45.8%) sectors and affected mostly the posterior, medial and superior sectors (20/22, 90.9%). Qualitative analysis showed consistency of the data with the morphological features of the defects. Further studies with larger samples are needed to validate the methodology and potentially develop a new classification scheme.

The availability of current land cover and land use (LCLU) information for monitoring the status of land resources has considerable value in ensuring sustainable land use planning. Similarly, the need to provide updated information on the extent of LCLU change in West Africa has become apparent, given the increasing demand for land resources driven by the rapid population growth in the sub-region. SERVIR West Africa, a regional consortium jointly supported by USAID and NASA to foster the use of geospatial and earth observation data and science for decision-making on critical environmental and food security challenges, in collaboration with the Food and Agriculture Organization of the United Nations (FAO), is building technical capacity in the sub-region to develop and implement harmonized regional land cover classification system for LULC change monitoring in West Africa, based on the Land Cover Meta Language (LCML-ISO 19144-2). This article focuses on the process, potential opportunities, outputs of this collaboration, exemplary use cases, and recommendations for the next steps.

Using multi-color flow cytometry analysis, we studied the immunophenotypical differences between leukemic blasts/LSCs from patients with AML/MDS and hematopoietic stem and progenitor cells (HSPCs) from patients in complete remission (CR) following their successful treatment. The panel of markers included CD34, CD38, CD45RA, CD123 as representatives for a hierarchical hematopoietic stem and progenitor cell (HSPC) classification as well as programmed death ligand 1 (PD-L1). Rather than restricting the evaluation on a 2- or 3-dimensional analysis, we applied a t-distributed stochastic neighbor embedding (t-SNE) approach to get a deeper insight and segregation between leukemic and normal HPSCs. For that purpose, we created a t-SNE map, which resulted in the visualization of 27 cell clusters based on their similarity concerning the composition and intensity of antigen expression. Two of these clusters were “leukemia-related” containing a great proportion of CD34⁺/CD38^- hematopoietic stem cells (HSCs) or CD34⁺ cells with a strong coexpression of CD45RA/CD123, respectively. CD34⁺ cells within the latter cluster were also highly positive for PD-L1 reflecting their immunosuppressive capacity. Beyond this proof of principle study, the inclusion of additional markers will be helpful to refine the differentiation between normal HSPCs and leukemic cells, particularly in the context of minimal disease detection and antigen-targeted therapeutic interventions. Furthermore, we suggest a protocol for the assignment of new cell ensembles in quantitative terms, via a numerical value, the Pearson coefficient, based on a similarity comparison of the t-SNE pattern with a reference.

Classifying network flow subsequences in an Industrial IoT gateway is an effective method for identifying Industrial IoT faults. This paper proposes a subsequence classification algorithm SSGBUL-IKNN based on unsupervised learning encoding to address the problem of low classification accuracy. Firstly, we built a network module based on unsupervised learning to encode the flow sequence of the Industrial IoT gateway. In the encoding module, a subsequence calibration algorithm controls the increasing error during the coding process. Then, the specific fault type is obtained through an improved KNN classification algorithm based on the indication distance source from the integrated coding sequences converted by multi-dimensional network flow sequences. The test result on three Industrial IoT datasets of a sewage treatment plant shows that the accuracy of SSGBUL-IKNN in this paper exceeds 92%, significantly higher than the algorithm DTW and TSF. It reaches the classification requirements of Industrial IoT fault diagnosis.

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2-2.2 ped/m2). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance.

In 2022, the new WHO Classification of Endocrine and Neuroendocrine Tumors, Fifth Edition (beta version) (WHO 5th) was published. The importance of understanding the molecular genetics of thyroid tumors as revealed by large-scale genomic analyses such as The Cancer Genome Atlas (TCGA). Consequently, the WHO 5th was fundamentally revised, resulting in a systematic classification based on tumor cell-of-origin and clinical risk. This paper outlines following critical points of the WHO 5th. 1. Genetic mutations in follicular cell-derived neoplasms (FDN) highlight the role of mutations in the MAP kinase pathway, including RET, RAS, and BRAF, as drivers of carcinogenesis. Differentiated thyroid cancers such as follicular thyroid carcinoma (FTC) and papillary thyroid carcinoma (PTC) have specific genetic alterations that correlate with morphological classifications: RAS-like tumors (RLTs) and BRAF p.V600E-like tumors (BLTs), respectively. 2. The Framework for benign lesions have revised. The WHO 5th introduces new categories such as "developmental abnormalities" and "thyroid follicular nodular disease" in benign FDN. 3. Low-Risk Tumors include NIFTP, TT-UMP, and HTT. 4. PTC histological variants are reclassified as "subtypes" in the WHO 5th. 5. The concept of high-grade carcinomas is introduced, encompassing poorly differentiated thyroid carcinoma (PDTC), differentiated high-grade thyroid carcinoma (DHGTC), and high-grade medullary thyroid carcinoma (MTC). 6. Squamous cell carcinoma is included in anaplastic thyroid carcinoma (ATC) in the WHO 5th due to shared genetic and prognostic features. 7. Hürthle cell adenoma/carcinoma is renamed oncocytic thyroid adenoma/carcinoma. 8. Other miscellaneous tumors are classified into salivary gland-type carcinomas of the thyroid, thyroid tumours of uncertain histogenesis, thymic tumours within the thyroid, and embryonal thyroid neoplasms. The WHO 5th thus emphasizes the importance of classifying tumors based on genetic abnormalities together with histomorphology, aiding in accurate pathological diagnosis and treatment selection, including molecular-targeted therapies.

Microarray gene expression analysis is a powerful technique used in cancer classification and research to identify and understand gene expression patterns that can differentiate between different cancer types, subtypes, and stages. However, microarray databases are highly redundant, inherently nonlinear, and noisy. Therefore, extracting meaningful information from such a huge database is a challenging one. The paper adopts the Fast Fourier Transform (FFT) and Mixture Model (MM) for dimensionality reduction and utilizes the Dragonfly optimization algorithm as the feature selection technique. The classifiers employed in this research are Nonlinear Regression, Naïve Bayes, Decision Tree, Random Forest and SVM (RBF). The classifiers' performances are analyzed with and without feature selection methods. Finally, Adaptive Moment Estimation (Adam) and Random Adaptive Moment Estimation (RanAdam) hyper-parameter tuning techniques are used as improvisation techniques for classifiers. The SVM (RBF) classifier with the Fast Fourier Transform Dimensionality Reduction method and Dragonfly feature selection achieved the highest accuracy of 98.343% with RanAdam hyperparameter tuning compared to other classifiers.

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

Educational institutions must identify students who are academically struggling to provide them with necessary support to improve their performance. In this context, recommendation systems powered by deep learning techniques are vital for detecting and categorizing such students. These systems help students plan their future by uncovering patterns in their historical academic data. This study introduces a new deep learning model designed to classify academically underperforming students in educational settings. The model incorporates a Gated Recurrent Neural Network (GRU) and includes specific neural network features like a dense layer, max-pooling layer, and the ADAM optimization algorithm. The model's training and evaluation were conducted using a dataset comprising 15,165 student assessment records from various academic institutions. The performance of the developed GRU model was benchmarked against other educational recommendation systems, including Recurrent Neural Network models, AdaBoost, and the Artificial Immune Recognition System v2. The proposed GRU model demonstrated remarkable accuracy, achieving an overall rate of 99.70%.

The rise in both the frequency of natural disasters and the ubiquity of artificial intelligence has led to novel applications of new technologies in improving disaster response processes, such as the labor-intensive assessment of disaster damages. Assessment of residential and commercial structure damages, a precursory step to government agencies being able to provide most of their financial assistance, has benefited from aerial and satellite imagery-based computer vision models; however, limitations of using such imagery include the ground structures being obscured by clouds or smoke, as well as the lack of resolution to distinguish individual structures from others. Using a different data source, we propose a damage severity classification model using ground-level imagery, focusing on residential structures damaged by wildfires. This classifier, a Vision Transformer (ViT) model trained on over 18,000 professionally labeled images of damaged homes from the 2020-2022 California wildfires, has achieved an accuracy score of over 95%. Further, we have open sourced the training dataset–the first of its kind and scale–as well as built a publicly available web application prototype, which we demoed to and received feedback from disaster response officials, both of which further contribute to the broader literature beyond the proposed model.

Quantum logic is a well-structured theory, which has recently received some attention because of its fundamental relation to quantum computing. However, the complex foundation of quantum logic borrowing concepts from different branches of mathematics as well as its peculiar settings have made it a non-trivial task to device suitable applications. This article aims to propose for the first time an approach to use quantum logic in image processing at hand of a process for shape classification. We show how to make use of the principal component analysis to realize quantum logical propositions. In this way we are able to assign a concrete meaning to the rather abstract quantum logical concepts, and we are able to compute a probability measure from the principal components. For shape classification we consider encrypting given point clouds of different objects by making use of specific distance histograms. This enables to initiate the principal component analysis. At hand of experiments, we explore the possibility to distinguish between different geometrical objects and discuss the results in terms of quantum logical interpretation.

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.

Urban tree classification is pivotal in urban planning and management, facilitating informed decision-making processes. In this study, we introduce a novel data presentation method termed Pseudo Tree Crown, designed to enhance the accuracy and efficiency of urban tree classification. Leveraging the latest advancements in artificial intelligence (AI), we employ a state-of-the-art classification scheme, PyTorch, to maximize the accuracy of tree classification. Our results demonstrate a robust classification accuracy of over 95% from high spatial resolution imagery from Unmanned Aerial Vehicle (UAV), underscoring our proposed approach’s effectiveness. Moreover, the adaptability of our method renders it applicable to various study areas, highlighting its versatility and potential for widespread implementation in urban planning and management initiatives.

Speech recognition, or automatic speech recognition (ASR), is a technology designed to convert spoken language into text using software. However, conventional ASR methods involve several distinct components, including language, acoustic, and pronunciation models with dictionaries. This modular approach can be time-consuming and may influence performance. In this study, we propose a method that streamlines the speech recognition process by incorporating a unified recurrent neural network (RNN) architecture. Our architecture integrates a convolutional neural network (CNN) with an RNN and employs a connectionist temporal classification (CTC) loss function. Key experiments were carried out using a dataset comprising 576,656 valid sentences, using erosion techniques. Evaluation of the model performance, measured by the word error rate (WER) metric, demonstrated remarkable results, achieving a WER of 2%. This approach has significant implications for the realm of speech recognition, as it alleviates the need for labor-intensive dictionary creation, enhancing the efficiency and accuracy of ASR systems, and making them more applicable to real-world scenarios. For future enhancements, we recommend the inclusion of dialectal and spontaneous data in the dataset to broaden the model's adaptability. Additionally, fine-tuning the model for specific tasks can optimize its performance for targeted objectives or domains, further enhancing its effectiveness in those areas.

As Artificial Intelligence (AI) technology, particularly Machine Learning algorithms, becomes increasingly ubiquitous, our abilities to understand and interpret AI and machine learning algorithms are becoming increasingly desirable. Visualization has been used as a common tool to view and understand complex machine learning processes. In this paper, we will focus on developing a general framework for the visualization of machine learning models as a scalar valued multi-dimensional function to help users understand how the models behave over different viewing spaces. We first give a formal definition of the visualization problem. Interpolation-based morphing and subspace sampling techniques are applied to generate various renderings through projections and cross-sections of the model space as 3D surfaces or heatmap images. This method will be applied to two real-world datasets and applications: the diagnosis of Alzheimer's Disease (AD) using a human brain networks dataset and a real-world benchmark dataset for predicting home credit default risks. The visualizations show that different machine learning algorithms can behave quite differently under different conditions.

Speech recognition, also known as automatic speech recognition (ASR), is a technology that enables software to transcribe spoken language into text. However, existing Amharic ASR methods require multiple separate blocks, such as language, acoustic, and pronunciation models with dictionaries, which can be time-consuming and influence performance. This study proposes an approach that replaces much of the speech pipeline with a single recurrent neural network (RNN) architecture. Our proposed architecture is based on a hybrid approach that combines a convolutional neural network (CNN) with a recurrent neural network (RNN) and a connectionist temporal classification (CTC) loss function. We conducted several experiments with noisy audio data that contain 20,000 valid sentences. The model was evaluated using the word error rate (WER) metric, achieving impressive results of 7% WER on noisy data. This approach has significant implications for the field of speech recognition, as it reduces the human effort required to create dictionaries and improves the efficiency and accuracy of ASR systems, making them more practical for real-world applications.

Domain generalization has led to remarkable achievements in Hyperspectral Image (HSI) classification. Inspired by contrastive language-image pre-training (CLIP), the language-aware domain generalization method has been explored to learn cross-domain-invariant representation. However, existing methods face some challenges: 1) The weak capacity to extract long-range contextual information and inter-class correlation. 2) Due to the inadequacies of the large-scale pre-training for HSI data, the spatial-spectral features of HSI and linguistic features can not be straightforwardly alignment. To address the above problems, a novel network has been proposed with a CLIP framework, which consists of an image encoder, based on an encoder-only transformer to obtain the global contextual information and inter-class correlation, a frozen text encoder, and a cross-attention mechanism, named Linguistic-Interact-with-Visual Engager (LIVE), enhances the interaction between two modalities. Extensive experiments demonstrating superior performance over state-of-the-art methods in HSI Domain Generalization with a CLIP framework.

Transformer models have emerged as frontrunners in the field of natural language processing, primarily due to their adept use of self-attention mechanisms to grasp the semantic linkages between words in sequences. Despite their strengths, these models often face challenges in single-task learning scenarios, particularly when it comes to delivering top-notch performance and crafting strong latent feature representations. This challenge is more pronounced in the context of smaller datasets and is particularly acute for under-resourced languages such as Arabic. In light of these challenges, this study introduces a novel methodology for text classification of Arabic texts. This method harnesses the newly developed Reverse Positional Encoding (RPE) technique. It adopts inductive-transfer learning (ITL) framework combined with a switching self-attention shared encoder, thereby increasing the model's adaptability and improving its sentence representation accuracy. The integration of Mixture of Experts (MoE) and Reverse Positional Encoding (RPE) techniques empowers the model to process longer sequences more effectively. This enhancement is notably beneficial for Arabic text classification, adeptly supporting both the intricate five-point and the simpler ternary classification tasks. The empirical evidence points to its outstanding performance, achieving accuracy rates of 87.20% for the HARD dataset, 72.17% for the BRAD dataset, and 86.89% for the LABR dataset, as evidenced by the assessments conducted on these datasets.

With the growing awareness of entrepreneurs and consumers of the tourism market in the field of sustainable development, it seems necessary to base hotel classification systems on an integrated approach to management quality, including fulfilment of ecological and environmental criteria. The article aims to indicate how environmental standards are implemented in the European system of hotel classification- HotelstarsUnion and the one in force in Poland. With regards to these systems, the differences in the classification criteria taken into account within the systems of hotel categorization by certifying organizations in the European Union in relation to the administrative hotel categorization system in Poland were pointed out. Particular emphasis was placed on the criteria related to environmental management in the hotel industry. Criteria related to environmental management were identified through analysis of the content of criteria of eight environmental management systems that are applicable to the contemporary hotel market. The results of the research proved that even though the HotelstarsUnion system takes into account the principles of sustainable development to a much greater extent than the Polish one, its primary weakness is that most of its criteria related to environmental ones are optional. In addition, the optional ones have higher weights than the obligatory ones. In turn, the Polish classification system makes very little reference to environmental standards. Moreover, it is not detailed and the assessment criteria are not up to date. Therefore, it is recommended that a greater number of environmental criteria is included when updating the HotelstarsUnion system, which should be obligatory for hotels to meet. In addition, the sustainability criteria included in the HotelstarsUnion system should be adapted to the policy system aimed at the hotel industry in Poland and other EU countries.

In recent years, researches on combining wavelet decomposition and convolutional neural network (CNN) together to classify hyperspectral images (HSI) have emerged, and some effective classification models have been proposed and achieved good classification results. However, there are two problems for most of the proposed models. One is the heavy training parameters and the other is that there is no distinction between the classification effectiveness of low frequency and high frequency features after wavelet decomposition. In this paper, a new light-weighted HSI classification model (LLFWCNN) is proposed, which performs multi-layer wavelet decomposition for HSI after dimensionality reduction, and only arranges the low frequency features in a specific stack mode, then classifies them through a well-designed convolutional neural network. Compared with other classification models, the number of parameters is only 2.5% of that of other models. And only the low frequency features after wavelet decomposition are used, while the high frequency features are abandoned. The results showed that compared with the state-of-the-art classification models, LLFWCNN could obtain the same or even better classification results with fewer network parameters and proved that the low frequency features after wavelet decomposition provide LLFWCNN with more favorable information for HSI classification as well.

In recent times, using image-based deep learning techniques has been very useful for classifying fruits. However, mango is a particular challenge because its shelf life is directly related to the degree of maturity at the time of harvest, which is determined mainly through the visual assessment of the operators when sorting them, doing it incorrectly, coupled with the blows and compressions exposed during storage and transport, trigger the deterioration in their quality, hence the importance of this operation. In this sense, the purpose of this study focuses on designing a computational model based on Deep Learning that uses a convolutional neural network (CNN) parameterized to select mangoes according to their color tone based on their maturity stage. A dataset was established from 201 labeled images, then a CNN architecture was built, obtaining a model on which 3 criteria were evaluated: the number of convolution and grouping layers, the resolution of the input images and the number of training epochs required. As a result, an input image resolution of 32 x 32 pixels was achieved, the process included a convolution layer followed by pooling that fed another layer that processed the results and ended in an output layer with 2 neurons under the One Hot Encoding representation. The model required 20 epochs to perfect its training, achieving 96.04 % accuracy in mango image selection. This study supports the potential of CNNs in quality analysis through mango color selection, even in uncertainty scenarios.

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diag-nosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obsta-cles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate clas-sification. As such, skilled clinicians often struggle to differentiate benign moles from early ma-lignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to confront difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification which combines snake models of Active Contour (AC) Segmentation, ResNet50 for feature ex-traction and a Capsule Network with a fusion of lightweight attention mechanisms, to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimi-nation, and improve accuracy. We employed the Stochastic Gradient Descent (SGD) optimization algorithm to optimize the model's parameters. The proposed model is implemented on publicly available datasets, namely HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated derma-tological diagnosis and provide a helpful tool for medical practitioners.

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

Analyzing horse behavior is crucial for assessing training quality, particularly in accurately identifying actions like standing, walking, and running. Research has been conducted both domestically and internationally in this regard; however, challenges persist, including reliance on single sensors, poor real-time performance, and low identification accuracy. In view of these challenges, this study investigated real-time identification of horse behavior based on wearable devices. The system, centered around a microcontroller and utilizing a 4G network as a carrier, employs multi-axis IMU sensors as input sources to perceive horse posture. The study proposed a behavior classification method based on analysis of acceleration thresholds. The method consists primarily of two sequential stages: first, the resultant acceleration interval counting method, which employs a nonlinear segmentation approach for initial behavior classification; and second, the statistical analysis of variance parameters between segments, which when coupled with multi-level threshold processing, achieves a refined classification. Experimental results indicated that the interval counting method alone achieved an accuracy of 87.55%, while for the variance analysis method alone the accuracy was 90.87%. The proposed method, comprising the two stages, reached a classification accuracy of 91.57%, underpinning its usefulness in supporting future equine research.

In-depth insights into the profound impacts of climate change and human activities on water resources are garnered through the dynamic changes in surface water, a crucial aspect of effective water resource management and the preservation of aquatic ecosystems. This paper introduces an innovative approach employing the random forest algorithm for the systematic extraction and monitoring of surface water at large regional or national scales. This method integrates spectral bands, spectral indices, and digital elevation model data, offering a novel perspective on this critical task. A data filling model is proposed to mitigate the impact of missing data due to cloud cover. Leveraging the capabilities of the Google Earth Engine (GEE), detailed information on surface water dynamics during the rainy and dry seasons in the Yangtze River Basin (YRB) from 1991 to 2021 is extracted using Landsat time series imagery. The analysis encompasses spatial-temporal variation characteristics and trends, with a specific focus on the intricate interplay between the areal extent of surface water and hydro-meteorological factors in each sub-basin of the YRB. Importantly, this includes considerations of potential groundwater contributions to surface water. Key findings from our research include: (1) Achieving a remarkable overall accuracy of 0.96 ± 0.03 in obtaining reliable surface water datasets with the support of GEE. (2) Identifying significant trends, such as a noteworthy increase in rainy season surface water bodies (+248.0 km2·yr−1) and a concerning decrease in surface ice/snow cover during both rainy and dry seasons, with change rates of −39.7 km2·yr−1 and −651.3 km2·yr−1, respectively. (3) Uncovering the driving mechanisms behind these changes, revealing positive correlations between the areal extent of rainy season surface water bodies and precipitation, as well as negative correlations between surface ice/snow cover area and average surface skin temperature. It is crucial to note that these driving factors exhibit variation among secondary river systems, underscoring the complexity of surface water dynamics. Furthermore, comparative analyses with existing surface water products are conducted, contributing to a deeper understanding of the advantages and uncertainties inherent in our proposed extraction method. The proposed method for large-scale surface water extraction not only enhances the monitoring of spatio-temporal surface water dynamics in the YRB but also provides valuable insights for the sustainable utilization and protection of water resources, considering the potential role of groundwater in supplementing surface water.

When it comes to financial transactions and counterfeit detection systems, banknote classification is crucial. In this paper, we propose an approach for the classification of Kazakhstan banknote images integrating Learning Vector Quantization (LVQ) with Statistical Texture Feature Extraction using the Gray Level Co-occurrence matrix (GLCM). Our methodology demonstrates effectiveness in accurately classifying banknote images, as evidenced by experimental results. The comprehensive testing scenarios show promising outcomes, with the combination of GLCM and Color Histogram under the LVQ algorithm achieving a high accuracy of 94.87 percent at distance 1 and 90°. These findings indicate the robustness and practical viability of the proposed method for authenticating banknotes.

The electrical energy supply relies on the satisfactory operation of insulators. The ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty insulators. The random convolutional kernel transform (Rocket) algorithms use convolutional filters to extract various features from time series data. This paper proposes the combination of Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), empirical wavelet transform (EWT), and variational mode decomposition (VMD). The results show that the EMD methods combined with MiniRocket, significantly improve the accuracy of logistic regression in insulator fault diagnosis. The proposed strategy achieves respectively an accuracy of 0.992 using CEEMDAN, 0.995 with EWT, and 0.980 with VMD. These results highlight the potential of incorporating EMD methods in insulator failure detection models to enhance the safety and dependability of power systems.

Durum wheat is an important staple food used to obtain several products. At first the wheat is milled to obtain different products: bran, semolina and flour. These products are the base of several artifacts with varying properties both from a nutritional point of view and flavoring characteristics. It is known that most elements concentrate in the outer layers of the wheat seed (pericarp and aleurone) so that the content of the elements vary a lot in the ground products. The present study investigates the characterizing elements of the milled products and the effect of cultivation protocol applied. We measured, by ICP-OES, the concentration of 28 elements in the whole seed and in any grinding products; the results show that only few elements characterize each product. Few elements, but different for each product, permit to disclose the kind of agri-cultural method used: organic or conventional protocol. Five elements: B, Cd, Cu, K, Se, are the most important to distinguish between organic and conventional agriculture by PCA and PLS analysis; these elements also permit some differentiation of products.

Based on recent popular money priming research results, which conclude that money makes self-sufficient (e.g. less interest in other people), we assumed that people are less interested in finding out whether others are lying or telling the truth. In a laboratory experiment, 163 students (85 women, 78 men, M_Age = 23.08, ranging from 18 to 36 years) were primed by actively handling money (versus paper sheets). Afterwards, they classified 24 video statements as true or deceptive (senders describing their most/least favorite movie), rated their classification confidence for each decision and then answered control questions. Results revealed no influence of priming condition on judgmental bias, classification accuracy, and classification confidence. Also the level of self-reported motivation to find out who lied or told the truth did not differ between conditions. Higher motivation was correlated to higher classification confidence. Additionally, and in line with Reinhard (2010) and Reinhard et al. (2011), higher classification accuracy correlated to a higher use of verbal content cues for classification decisions. Thus, while we were able to replicate these findings, our results contradict the assumption of a money prime influence on lie detection ability. Concluding, our results make self-sufficiency in this context questionable and offer next steps for research.

To enhance the overall reliability of the power system, engineers have redirected their focus toward health monitoring and early detection of faults in transformers. Among these faults, transformer core defects demand particular attention. While fault simulation using software has traditionally been the preferred approach, these methods suffer from data inaccuracies in real-world conditions. Consequently, conducting actual experimental setups with induced faults is imperative to investigate core issues. This study uses Hilbert Transform (HT) as a signal processing technique to extract crucial data characteristics, thereby enhancing the performance of the classifier model. The research involves analyzing electric current signals from a single-phase 1kVA transformer. A comparative assessment of our proposed model was conducted using raw data and Fast Fourier Transform (FFT), evaluating accuracy, precision, recall, F1-score, and computational time. The results demonstrate a significant improvement in all metrics for the classifier models, particularly the k-nearest neighbor (KNN) algorithm, which exhibited values of 83.89%, 84.39%, 83.89%, 83.79%, and 0.0156 seconds, respectively. Future work aims to extend this analysis under different loading conditions.

Drones are being used more and more frequently and in various ways to attack people and critical infrastructures, which increases their level of danger and makes early detection and risk assessment even more difficult. There is no ultimate drone sensor. Rather, drones can only be effectively detected, if suitable sensor technologies are integrated within a system. Among the best suited sensorics for this purpose are radar and optical sensors, because the advantage of the radar, given by the long detection range, can be well combined with the additional visual-based information gained from a camera in the mid- and short-range, where usually the radar fails detecting micro drones. In this paper, a modular drone detection and assistance system MODEAS is presented, which can be used to automatically detect and track drones within a range up to some kilometers on the sky, but also in complex urban environments, where buildings and vegetation offer a perfect background for camouflage. The system provides an early detection of flying objects as potential drones, when those are not at all or only as small dots visible for the human eye. Main strengths of the system are the robust AI detection to differentiate such an object against clutter (birds, clouds) and its further classification by model and payload recognition, the latter aspect being considered as an indication of dangerousness. Moreover, once a drone is detected, the system follows it automatically, precisely and smoothly with a high-resolution pan-tilt-camera, measuring the distance to the sensor station with a laser rangefinder, compute the geocoordinates and visualize them live on a map. To improve the precision of the detection, a multisensorial fusion of all sensor detections is performed. Furthermore, alarms may be generated when a drone enters a restricted area.

In-wheel motor vehicles are gaining attention as a new type of electric vehicle due to their efficient power units located inside each wheel hub. However, they are more susceptible to wheel resonance due to the increase in unsprung mass caused by the motor's weight. This can result in decreased both the ride comfort and driving stability. To resolve this issue, this study aims to apply an optimal switching controller with a semi-active n actuator; magnetorheological (MR) damper. For the implementation of the optimal switching controller, a road type classification is also carried out. An acceleration sensor is used for road type classification, and control logics include a ride comfort controller; the linear quadratic regulator (LQR _Paved Road) and a wheel motion controller (LQR_Off Road) for improved driving stability. For paved roads, the LQR_Paved Road control input is applied to the MR damper. However, if a road type prone to wheel resonance is detected, the control logic switches to the LQR_Off Road. During the transition, a weighted average of both LQR_ Paved Road and LQR_Off Road control input is applied to the actuator. Computer simulations are undertaken to evaluate vibration control performance, including the ride comfort and driving stability at various road profiles.

Weeds are unwanted and invasive plants that proliferate and compete for resources such as space, water, nutrients, and sunlight, affecting the quality and productivity of the desired crops. Weed detection is crucial for the application of precision agriculture methods and for this purpose machine learning techniques can be used, specifically convolutional neural networks (CNN). This study focuses on the search for CNN architectures and technology used to detect and identify weeds in different crops; 61 articles applying CNN architectures and technology were analyzed in the last five years (2019-2023). The results show the used of different devices to acquire the image for training, such as digital cameras, smartphones, and drone cameras. Additionally, the YOLO family and algorithms are the most widely adopted architectures, followed by VGG, ResNet, Faster R-CNN, AlexNet, and MobileNet, respectively. This study provides an update on CNNs that will serve as a starting point for researchers wishing to implement these weed detection and identification techniques.

This narrative review aims to provide a comprehensive overview of the scientific literature on wheelchair badminton and its distinctive aspects, encompassing abilities and disabilities, propulsion technique, and the use of a racket. The relatively young history of wheelchair badminton is reflected in the scarcity of scientific studies within this domain, highlighting the need for further investigation. The review systematically covers existing articles on wheelchair badminton, offering a nearly exhaustive compilation of knowledge in this area. Findings suggest that WH2 athletes engage in more intense matches with a higher frequency of offensive shots compared to WH1 athletes. Moreover, backward propulsion induces distinct physiological responses and alterations in propulsion kinematics, potentially leading to performance decrements. The use of a badminton racket further influences propulsion kinetics and kinematics, potentially impacting performance and injury risk. Further research is imperative to explore additional perspectives, address existing gaps, and expand the scope of study within the wheelchair badminton domain. This narrative review serves as a foundation for future investigations, emphasizing the necessity of continued research to enhance our understanding of wheelchair badminton.

Evolutionary Machine Learning (EML) has demonstrated its effectiveness in modeling various real-world application domains, including the dynamics of diseases and the creation of predictive models across diverse fields. However, the challenge of data imbalance adversely impacts the performance of EML models. While strategies involving misclassification costs or cost-sensitive learning exist to address this issue, their integration into EML has yet to be thoroughly explored. This paper aims to fill this gap by investigating the application of cost-sensitive EML for intelligent health risk prediction. More specifically, this paper delves into the utilization of cost-sensitive genetic programming (CSGP) and cost-sensitive genetic algorithms (CSGA), which are among the most widely used algorithms in the EML category. The study entails training CSGP and CSGA to predict the early onset of three chronic conditions (hypertension, diabetes, and fatty acid-related disorders) through the development of an EML model. Subsequently, the model's performance is evaluated through standard fitness functions such as sensitivity, specificity, and F1-score. From the experimental results, EML models demonstrate promising results in identifying the occurrence of chronic diseases. Further optimization of the cost-sensitive EML model holds the potential for enhanced outcomes in modeling medical problems.

Vehicular traffic in urban areas continues to be a constant challenge today, due to the continuous population growth and the increase of vehicles in circulation. Vehicular congestion, as a recurrent problem, generates a negative impact on urban mobility and citizens’ quality of life. It is hypothesized that a dynamic clustering method of vehicle trajectory data can provide an accurate and up-to-date representation of real-time traffic behavior. To evaluate this hypothesis, data were collected from three different cities: San Francisco, Rome and Guayaquil. A dynamic clustering algorithm was applied to identify traffic congestion patterns and an indicator was applied to identify and evaluate the congestion conditions of the areas. The results show a high precision and recall in congestion classification compared to a method based on static cells.

Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot-spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point clouds by projecting them into 2D images and evaluating consistency with textual prompts. These methods benefit from the robust open-world understanding capabilities of visual-language pre-trained models and require no additional training. However, they face several challenges summarized as prompt ambiguity, image domain gap, view weights confusion, and feature deviation. In response to these challenges, we propose PointBLIP, a zero-training point cloud classification network based on the recently introduced BLIP-2 visual-language model. PointBLIP is adept at processing similarities between multi-images and multi-prompts. We separately introduce a novel method for point cloud zero-shot and few-shot classification, which involves comparing multiple features to achieve effective classification. Simultaneously, we enhance the input data quality for both the image and text sides of PointBLIP. In point cloud zero-shot classification tasks, we outperform state-of-the-art methods on three benchmark datasets. For few-shot classification tasks, to the best of our knowledge, we present the first zero-training few-shot point cloud method, surpassing previous works under the same conditions and showcasing comparable performance to full-training methods.

Existing reinforced concrete buildings with seismically-deficient column details affect the overall behavior depending on the failure type of column. The purpose of this study is to develop and validate a machine learning-based prediction model for the column failure modes (shear, flexure-shear and flexure failure modes). For this purpose, artificial neural network (ANN), K-nearest neighbor (KNN), decision tree (DT), and random forest (RF) models were used considering previously-collected experimental data. Using four machine learning methodologies, we developed a classification learning model that can predict the column failure modes in terms of the input variables using concrete compressive strength, steel yield strength, axial load ratio, height-to-dept aspect ratio, longitudinal reinforcement ratio, and transverse reinforcement ratio. The performance of each machine learning model was compared and verified by calculating accuracy, precision, recall, F1-Score, and ROC. Based on the performance measurements of the classification model, the RF model represents the highest average value of the classification model performance measurements among the considered learning methods, and it can conservatively predict the shear failure mode. Thus, the RF model can rapidly predict the column failure modes with the simple column details. Additionally, it was demonstrated that the predicted failure modes from the selected model were exactly same as the failure mode determined from a code-defined equation (traditional method)

Multispectral and 3D LiDAR remote sensing data sources are valuable tools for characterizing the 3D vegetation structure and thus understanding the relationship between forest structure, biodiversity and microclimate. This study focuses on mapping riparian forest species in the canopy strata using a fusion of Airborne LiDAR data and multispectral multi-sources and multi-resolution satellite imagery; Sentinel-2 and Pleiades at tree level. The idea is to assess the contribution of each data source in the tree species classification at the considered level. The data fusion was processed at feature-level and decision level. At feature level, LiDAR 2D attributes were derived and combined with vegetation indices. At decision level, LiDAR data was used for 3D tree crown delimitation providing unique trees or groups of trees that are used as a support for the species classification. Data augmentation techniques were used to improve the training process. Best results were obtained by the fusion of Sentinel-2 time series and LiDAR data with a Kappa of 0.66 thanks to red-edge based indices that better discriminate vegetation species and the temporal resolution of Sentinel-2 images that allows monitoring the phenological stages helping to discriminate the species.

This study advances the field of solar irradiance nowcasting by introducing a discrete-level classification approach, diverging from traditional continuous measurement methods. Grounded in a need for cost-effective and modular solutions, the research employs high-resolution computer vision coupled with a deep learning framework to predict Direct Normal Irradiance (DNI). By harnessing the capabilities of a Logitech C900 1080p HD camera and an NVIDIA Jetson module, the study achieves real-time data processing, pivotal for CSP systems' operational efficiency. The core of the methodology is the ResNet-50 convolutional neural network, refined via transfer learning on a bespoke dataset, culminating in a predictive accuracy of 85.78%. This discrete classification model contrasts with conventional, costly instruments like the MS-57, offering a novel and accessible alternative for DNI estimation. Such innovation not only demonstrates high predictive accuracy but also signifies a shift towards less resource-intensive and more adaptable solar energy forecasting tools, contributing a significant leap towards optimizing renewable energy systems.

This study assesses the applicability of different-resolution multispectral remote sensing images for mapping and estimating the aboveground biomass (AGB) of Carpobrotus edulis, a prominent invasive species in European coastal areas. The performance of three sets of multispectral images with different resolutions was compared: (i) 2.5 cm Ground Sample Distance (GSD), 5 cm GSD and 10 cm GSD images. The images were classified using the supervised classification algorithm Random Forest and later improved applying a sieve filter. The results show that the three tested image resolutions allow constructing reliable coverage maps of C. edulis, with Overall Accuracy values of 89%, 85% and 88% for the classification of the 2.5 cm, 5 cm and 10 cm GSD images, respectively. Samples were also collected, dried and weighed to estimate AGB using the relationship between the Dry Weight and Vegetation Indices (VI). The regressions were evaluated based on their R² and Normalised RMSE. The best-performing VI-DW regression models achieved: R² = 0.87 and NRMSE = 0.09 for the 2.5 cm resolution; R² = 0.77 and NRMSE = 0.12 for the 5 cm resolution; and, R² = 0.64 and NRMSE = 0.15 for the 10 cm resolution. C. edulis area and total AGB were: 3441.10 m² and 28,327.1 kg (with a Relative Error (RE) = 0.08), for the 2.5 cm resolution; 3070.04 m² and 29,170.8 kg (RE = 0.08), for the 5 cm resolution; and, 2305.06 m² and 22,135.7 kg (RE = 0.11), for the 10 cm resolution. Differences were analysed in detail, spatially, to determine their causes. Final analyses suggest that, for C. edulis, multispectral imagery of up to 5 cm GSD is adequate for the estimation of the species’ distribution and biomass.

In this paper, we propose a method for assessing the effectiveness of entropy features using several chaotic mappings. We anlyze fuzzy entropy (FuzzyEn) and neural network entropy (NNetEn) on four discrete mappings: the logistic map, the sine map, the Planck map, and the two-memristor-based map, with a base length time series of 300 elements. FuzzyEn is shown to have improved global efficiency (GEFMCC) in the classification task compared to NNetEn. At the same time, there are local areas of the time series dynamics in which the classification efficiency NNetEn is higher than FuzzyEn. The results of using horizontal visibility graphs (HVG) instead of the raw time series are also shown. GEFMCC decreases after HVG time series transformation, but there are local areas of the time series dynamics in which the classification efficiency increases after including the HVG. The scientific community can use the results to explore the efficiency of entropy-based classification of time series.

This paper proposes a new method for network screening on rural low-volume roads. These roads are important as they provide critical access to agricultural land and tourist attractions. Most low-volume roads belong to the lowest functional class (local rural roads) and thus are built to lower design standards. The conventional hot spot network screening techniques may not be appropriate for low-volume roads due to the sporadic nature of crashes occurring on these roads. Contrarily sophisticated network screening approaches require extensive roadway and traffic data that are often unavailable to local agencies for lack of resources, and/or lack of technical expertise. This research attempts to address these obstacles in low-volume roads network screening which aims to identify candidate sites for safety improvements. The research used an extensive low-volume road sample from the state of Oregon and the Empirical Bayes expected number of crashes in developing the proposed models for network screening. The proposed models do not require exact measurement of roadway geometric features as all geometric variables were classified into categories that are easy to compile by local agencies. Further, the method could be used with and without traffic data, without compromising the effectiveness of the network screening process.

Deep learning heavily relies on statistical correlations to drive artificial intelligence (AI) innovations, particularly in computer vision applications like autonomous driving and robotics. However, despite providing a solid foundation for deep learning, these statistical correlations can be vulnerable to unforeseen and uncontrolled factors. The lack of prior knowledge guidance can result in spurious correlations, introducing confounding factors and affecting the model's robustness. To address this challenge, recent research efforts have focused on integrating causal theory into deep learning methodologies. By modelling the inherent and unbiased causal structure, causal theory can potentially mitigate the impact of spurious correlations effectively. Hence, this paper explores the basics of causal methodologies in image classification.

The automated transcription of handwritten characters into a legible output is a multi-faceted process with diverse applications. In this paper, a novel approach to optical character recognition (OCR) for handwritten digits is proposed that, in certain components, exceeds current architectures in terms of accuracy, effectiveness, adjustability, temporal efficiency, and/or computational simplicity. This model succeeds in the adoption and enhancement of deprecated or obsolete algorithms across eight steps of image pre-processing—normalization, grayscaling, thresholding/binarization, noise removal, skew-correction, skeletonization/thinning, line separation, and character segmentation. The aforementioned model is evaluated with the use of a Convolutional Neural Network (CNN) leveraging the Balanced eMNIST dataset for training and testing. By suggesting contour-based feature extraction methods as alternatives to pixel-by-pixel iteration, the proposed paradigm demonstrates its capacity to serve as a suitable alternative to current, commonly used algorithms and computational techniques for textual image classification.

This study explores the application of the Fully Convolutional Network (FCN) algorithm to the field of meteorology, specifically for the short-term nowcasting of severe convective weather events such as hail, convective wind gust (CG) and thunderstorms, short-term heavy rain(STHR) in Gansu. Training data comes from the European Center for Medium-Range Weather Forecasts (ECMWF) and real-time ground observations, the performance of the proposed FCN model based on 2017 to 2021 training datasets demonstrate a high prediction accuracy, with an overall error rate of 16.6%. Furthermore, the model exhibited an error rate of 18.6% across both severe and non-severe weather conditions when testing against the 2022 dataset. Operational deployment in 2023 has yielded an average Critical Success Index (CSI) of 24.3%, a Probability of Detection (POD) of 62.6%, and a False Alarm Ratio (FAR) of 71.2% for these convective events. It is noteworthy that the predicting performance for STHR was particularly effective with the highest POD and CSI, as well as the lowest FAR. CG and hail predictions had comparable CSI and FAR scores, although the POD for CG surpassed that for hail. The FCN model’s optimal performance for hail prediction occurred at the 4th, 8th, and 10th forecast hours, while for CG, the 6th hour was most accurate, and for STHR, the 2nd and 4th hours were most effective. These findings underscore the FCN model's ideal suitability for short-term forecasting of severe convective weather, presenting extensive prospects for the automation of meteorological operations in the future.

The increasing importance of batteries in the 21st century and the challenges posed by the anticipated growth in end-of-life batteries, particularly in Europe, are addressed. Projections indicate a significant increase in battery waste, with a specific focus on the recycling of black mass (BM)—a complex and hazardous byproduct of the battery recycling process. The research employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to systematically analyze the hazardousness of BM derived from various types of batteries. The findings reveal the inherently hazardous nature of BM, classifying it under multiple hazardous properties (HPs) according to European regulations. The urgent need for a definitive legislative classification of the hazardousness of BM is emphasized, and the potential of innovative technologies and strategies to improve recycling performance while mitigating risks is highlighted. The research significantly contributes to understanding the complexities of BM recycling, providing a foundation for future advancements in this area and emphasizing the need for further exploration and economic feasibility analysis of recycling technologies.

The paper aims to develop and test an algorithm for classifying Russian-language text reviews of patients’ experiences with medical facilities and physicians, extracted from social media. This is motivated by the limitations of conventional methods of surveying consumers to assess their satisfaction with the quality of services, which are being replaced by automatic processing of text data from social media. This approach enables to get more objective results due to the increased representativeness and independence of the sample of service consumers. The authors have tested machine learning methods using various neural network architectures. A hybrid method was developed to classify text reviews of medical facilities posted by patients on the two most popular physician review websites in Russia. Overall, more than 60,000 reviews were analysed. The main results are as follows: 1) the classification algorithm developed by the authors has a high efficiency, the best result being achieved by the GRU-based architecture (val_accuracy = 0.9271); 2) applying the named entity search method to text messages following their partitioning improved the classification efficiency for each of the classifiers based on artificial neural networks. To further enhance the classification quality, reviews need to be semantically partitioned by target and sentiment and the resulting fragments need to be analysed separately.

Neurodegenerative illnesses, such as Parkinson’s disease (PD), have a substantial impact on the overall well-being of those who are affected. This study investigates and contrasts the capabilities of convolutional neural networks (CNN) in detecting Parkinson’s disease (PD) by utilising hand-drawn images alongside wave and spiral images as input data. This study employs pre-trained CNN models, specifically MobileNet, ResNet50, EfficientNet-B1, and InceptionV3, to classify Parkinson’s disease (PD). The findings demonstrate that MobileNet surpasses other architectural designs, as evidenced by the F1-Score of the four classes: Spiral Normal (0.87), Spiral Parkinson (0.86), Wave Normal (0.97), and Wave Parkinson (0.97). MobileNet has also shown a remarkable accuracy of 0.92 in diagnosing Parkinson’s disease. The result demonstrates the efficacy of MobileNet in extracting features from images. The results of this study enhance the application of deep learning methods in the early detection of PD, as well as help indicate the effectiveness of patient therapy and exercise, promising better patient outcomes through timely intervention and treatment.

We investigated how Artificial Intelligence (AI) reveals factors shaping COVID-19 vaccine hesitancy among healthcare providers by examining their open-text comments. We conducted a longitudinal survey starting in spring of 2020 with 38,788 current and former female nurses in three national cohorts to assess how the pandemic has affected their livelihood. In January and March-April 2021 surveys, participants were invited to contribute open-text comments and answer specific questions about COVID-19 vaccine uptake. A closed-ended question in the survey identified vaccine-hesitant (VH) participants who either had no intention or were unsure of receiving a COVID-19 vaccine. We collected 1,970 comments from VH participants and trained two Machine Learning (ML) algorithms to identify behavioral factors related to VH. The first predictive model classified each comment into one of three Health Belief Model (HBM) constructs (barriers, severity, and susceptibility) related to adopting disease prevention activities. The second predictive model used the words in January comments to predict the vaccine status of VH in March-April 2021; vaccine status was correctly predicted 89% of the time. Our results showed that 35% of VH participants cited barriers, 17% severity, and 7% susceptibility to receiving a COVID-19 vaccine. Out of the HBM constructs, the VH participants citing a barrier, such as allergic reactions and side effects, had the most associated change in vaccine status from VH to later receiving a vaccine.

The classification and summarization of online reviews using machine learning and deep learningbased approaches are the subject of this systematic literature review. Consumers, companies, and researchers can now find vital information from online reviews. Automatically categorizing and summarizing these reviews can offer useful information and facilitate decision-making. The purpose of this study is to offer a thorough overview of the current methodology, approaches, and developments in this area. The review concentrates on machine learning-based methods for categorization and summarizing tasks, highlighting their advantages, drawbacks, and new developments. This systematic review provides insights into the most recent methodologies and indicates prospective directions for further investigation by synthesizing the data from a wide range of pertinent research publications

Atrial Fibrillation (AF) is known as one of the dominant cardiac disease that is associated with severe consequences such as risk of strokes. This cardiac arrhythmia can be efficiently diagnosed using EEG signals. However, AF episodes in EEG records are not always permanent for all subjects. In addition, lengthy subject preparation and ECG recording sessions makes this practice time consuming and not attractive for efficient diagnosis. One attractive solution for this problem will be the use of wearable Internet of Medical Things IoMT devices for EEG recording and AF detection. From another side the use machine learning for efficient diagnosis could provide high accurate diagnosis. However, the deployment of these wireless wearable devices faces the problems of limited processing capabilities and of energy scarcity. In this context, the design of energy efficient accurate on-sensor AF detection scheme using machine learning algorithms still requires a focused research effort. This paper proposes a wearable solution for ECG-based processing scheme for embedded AF detection. The proposed method achieved 100% sensitivity and 94.5% of specificity and accuracy of around 97.4 % for wide range of subjects while showing low energy-consumption. The obtained results show the efficiency of using Logistic Regression algorithm for accurate AF detection and attest about practical feasibility of the proposed approach in wearable IoMT devices.

The paradigm of leveraging code as a dataset has recently gained traction, offering innovative solutions in domains such as automated commit message generation, pull request description automation, and program repair mechanisms. Consider the challenge in generating commit messages: traditional methods treat source code as a mere token sequence, applying neural machine translation models. This approach, however, overlooks the critical syntactic structures inherent in programming languages, which could offer deeper insights and improved accuracy. Building upon prior research, specifically the Code2Seq framework, which utilized Abstract Syntax Tree (AST) structural data for source code representation to automate method name generation, this paper extends and refines this concept. We introduce "CSR", a novel methodology adapted to represent code edits effectively. This paper investigates the impact of employing syntactic structure, focusing on the classification of code edits. Drawing inspiration from Code2Seq, "CSR" utilizes AST's structural properties, particularly the paths connecting leaf nodes, to enhance the task of code edit classification. This approach is rigorously evaluated on two distinct datasets, comprising fine-grained syntactic edits. Our comprehensive experiments reveal that incorporating syntactic structures does not significantly outperform simpler methodologies. While methods like Code2Seq and our proposed "CSR" show potential, our findings highlight that there is considerable scope for improvement and refinement before such techniques can be universally applied for learning representations of code edits. We anticipate that our findings will spark further research in this field, paving the way for more effective use of syntactic structures in code representation.

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.

Sleep disorder is a disease that can be categorized as both an emotional and physical problem. It imposes several difficulties and problems, such as distress during the day, sleep-wake disorders, anxiety, and several other problems. Hence, the main objective of this research is to utilize the strong capabilities of machine learning in the prediction of sleep disorders. In specific, this research aims to meet three main objectives. These objectives are to identify the best regression model, the best classification model, and the best learning strategy that highly suits sleep disorder datasets. Considering two related datasets and several evaluation metrics that are related to the tasks of regression and classification, the results revealed the superiority of the MultilayerPerceptron, SMOreg, and KStar regression models compared with the other twenty-three regression models. Also, IBK, RandomForest, and RandomizableFilteredClassifier showed superior performance compared with other classification models that belong to several learning strategies. Finally, the Function learning strategy showed the best predictive performance among the six considered strategies in both datasets and with respect to the most evaluation metrics.

In recent years, Synthetic Aperture Radar (SAR) has received attention in the Automatic Target Recognition (ATR) field due to its ability to acquire images both day and night, combined with the superior resolution offered by the latest sensors. However, despite advances, there remains a deficiency in dataset quality and quantity. This has necessitated the use of simulated data to overcome challenges associated with obtaining large quantities of high-quality images of targets and their subsequent labeling. In this study, we trained a Convolutional Neural Network (CNN) using a simulated dataset, subsequently employing it to classify real images from the MSTAR dataset. Traditional training methodologies often struggle with generalization when confronted with domain disparities between simulated and real data. To mitigate this, we exploited Margin Disparity Discrepancy (MDD), a domain adaptation technique not previously explored in SAR context. Findings from this study showcased a 13% increase in classification accuracy and improved generalization using MDD. Through Explainable AI (XAI) techniques such as t-SNE and other metrics like Kullback Leibler Divergence (KLD), we revealed a more distinct alignment of feature spaces between the two domains after domain adaptation, emphasizing MDD’s role in enhancing model accuracy and generalization.

Few-shot fine-grained image classification (FSFGIC) methods refer to machine learning methods which aim to classify images (e.g., bird species, flowers, and airplanes) belonging to subordinate object categories of the same entry-level category with only a few samples. It is worth to note that feature representation learning is used not only to represent training samples, but also to construct classifiers for performing various FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local or/and global deep feature representation learning, class representation learning, and task specific feature representation learning). The existing popular datasets and evaluation standards are introduced. Furthermore, a novel classification performance evaluation mechanism is designed with a 0.95 confidence interval for judging whether the classification accuracy obtained by a certain specified method is good or bad. Moreover, current challenges and future trends of feature representation learning on FSFGIC are elaborated.

This work develops a new method for vector data augmentation. The proposed method applies the Principal Component Analysis (PCA) and determines the Eigenvectors of a set of training vectors for a Machine Learning (ML) method and uses them to generate the distilled vectors. The training and the PCA distilled vectors have the same dimension. The user chooses the number of vectors to be distilled and augmented to the set of training vectors. A statistical approach determines the lowest number of vectors to be distilled such that when augmented to the original vectors the extended set trains a ML classifier to achieve a required accuracy. Hence, the novelty of this study is, the distillation of vectors with the PCA method and their use to augment the original set of vectors. The advantage that comes from the novelty is that it increases the statistics of ML classifiers. To validate the advantage, we conducted experiments with four public databases and applied four classifiers: Neural Network, Logistic Regression, Support Vector Machine with linear and polynomial kernels. For the purpose of augmentation, we conduct several distillations including nested (double distillation). The latter notion means that new vectors were distilled from already distilled vectors. We train the classifiers with three sets of vectors: original vectors; original augmented with vectors distilled by PCA; original augmented with distilled and double distilled, by PCA, vectors. The experimental results are presented in the paper, and they confirm the advantage that the PCA distilled vectors increase the classification statistics of ML methods, if the distilled vectors augment the original training vectors.

The field of program classification, a critical aspect of software engineering, facilitates understanding and categorization of code across various applications, including anomaly detection, and code quality assessment. The advancement of cross-language program classification opens up avenues for efficient code translation among different programming languages, significantly aiding developers in rapid coding and reducing development cycles. Existing research primarily focuses on semantic code analysis, with limited emphasis on cross-linguistic challenges. To address this, we introduce an innovative neural network model, CodeSemanticsNN, which leverages a refined Syntax Structure (SS) approach. This model consists of two integral mechanisms: first, it adopts a novel SS representation that combines sequential and graph-based SS structures, enhancing semantic feature capture. Second, it employs a 'unified vocabulary' strategy to bridge the gap between diverse programming languages, facilitating efficient cross-language classification. Additionally, we have compiled a comprehensive dataset of 20,000 files spanning five programming languages, serving as a benchmark for cross-language classification. Our experiments on this dataset demonstrate that CodeSemanticsNN surpasses existing models in four key metrics: Precision, Recall, F1-score, and Accuracy.

During geomagnetic storms, which are a result of solar wind interaction with the Earth’s magnetosphere, geomagnetically induced currents (GICs) begin to flow in the long-distance high-voltage power grids on the Earth’s surface. It causes a number of negative phenomena that affect the normal operation of the entire electric power system. To investigate the nature of the phenomenon and its possible effects on transformers, a GIC monitoring system was created in 2011, the devices of which were installed at five substations of the Kola-Karelian power transit in northwestern Russia. Over 12 years of operating the system a large amount of data has been accumulated, which cannot be analyzed manually within a reasonable amount of time. To analyze the constantly growing volume of recorded data effectively, a method for automatic classification of GIC in autotransformer neutral was proposed. The method is based on a continuous wavelet transform of the neutral current data combined with a convolutional neural network (CNN) to classify the obtained scalogram images. As the result of comparing four CNNs with different architectures, a model that showed excellent GIC classification performance on the validation set (100.00% accuracy and loss of 0.0115) was chosen.

Audio classification using deep learning models, essential for applications like voice assistants and music analysis, faces challenges when deployed on edge devices due to their limited computational resources and memory. Achieving a balance between performance, efficiency, and accuracy is a significant obstacle in optimizing these models for such constrained environments. In this investigation, we evaluate diverse deep learning architectures, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for audio classification tasks on the ESC 50, UrbanSound8k, and Audio Set datasets. Our empirical findings indicate that Mel Spectrograms outperform raw audio data, attributing this enhancement to their synergistic alignment with advanced image classification algorithms and their congruence with human auditory perception. To address the constraints of model size, we apply model compression techniques, notably magnitude pruning, Taylor Pruning, and 8-bit quantization. The research demonstrates that a hybrid pruned model achieves a commendable accuracy rate of 89 percent, which, although marginally lower than the 92 percent accuracy of the uncompressed CNN, strikingly illustrates an equilibrium between efficiency and performance. Subsequently, we deploy the optimized model on Raspberry Pi 4 and NVIDIA Jetson Nano platforms for audio classification tasks. These findings highlight the significant potential of model compression strategies in enabling effective deep learning applications on resource-limited devices, with minimal compromise on accuracy.

Hyperspectral (HS) imaging plays a pivotal role in various fields, including medical diagnostics, where precise human vein detection is crucial. Hyperspectral image data are very large and can cause computational complexities. Dimensionality reduction techniques are often employed to streamline HS image data processing. This paper investigates the effectiveness of three dimensionality reduction techniques, namely: Principal Component Analysis (PCA), Folded PCA (FPCA), and Ward’s Linkage Strategy using Mutual Information (WaLuMI) for vein detection using HS images. A HS image dataset, encompassing left and right-hand images captured from 100 subjects with varying skin tones was created and annotated using anatomical data to represent vein and non-vein areas within the images. To generate experimental results, the HS image dataset was divided into train and test datasets. Optimum performing parameters for each of the dimensionality reduction techniques in conjunction with The Support Vector Machine binary classification were determined using the Training dataset. The performance of the three dimensionality reduction based vein detection methods was then assessed and compared using the test image dataset. Results show that the FPCA-based method outperforms the other two methods in terms of accuracy. For visualization purposes, the classification prediction image for each technique is post-processed using morphological operators, and results show the significant potential of HS imaging in vein detection.

OSI model used to be common network model for years. In the case of ad hoc networks with dynamic topology and difficult radio communications conditions, gradual departure is happening from the classical kind of OSI network model with a clear delineation of layers (physical, channel, network, transport, application) to the cross-layer approach. The layers of the network model in ad hoc networks strongly influence each other. Thus, the cross-layer approach can improve the performance of an ad hoc network by jointly developing protocols using interaction and collaborative optimisation of multiple layers. The existing cross-layer methods classification is too complicated, because it’s based on the whole manifold of network model layers combinations, regardless their importance. In this work, we review ad hoc networks cross-layer methods, propose the new useful classification of cross-layer methods, and show future research directions in ad hoc networks cross-layer methods development. The proposed classification can help to simplify the goal-oriented cross-layer protocol development.