Search Results (570)

Urban street greening structure plays a crucial role in promoting environmental justice and enhancing residents’ daily well-being, yet existing studies have primarily focused on vegetation quantity while neglecting how perception and governance interact to shape fairness. This study develops an integrated analytical framework that combines deep learning, machine learning, and spatial analysis to examine the impact of perceptual experience and socio-economic indicators on the equity of greening structure distribution in urban streets, and to reveal the underlying mechanisms driving this equity. Using DeepLabV3+ semantic segmentation, perception indices derived from street-view imagery, and population-weighted Gini coefficients, the study quantifies both the structural and perceptual dimensions of greening equity. XGBoost regression, SHAP interpretation, and Partial Dependence Plot analysis were applied to reveal the influence mechanism of the “Matthew effect” of perception and the Site governance responsiveness on the fairness of the green structure. The results identify two key findings: (1) perception has a positive driving effect and a negative vicious cycle effect on the formation of fairness, where positive perceptions such as beauty and safety gradually enhance fairness, while negative perceptions such as depression and boredom rapidly intensify inequality; (2) Site management with environmental sensitivity and dynamic mutual feedback to a certain extent determines whether the fairness of urban green structure can persist under pressure, as diverse Tree–Bush–Grass configurations reflect coordinated management and lead to more balanced outcomes. Policy strategies should therefore emphasize perceptual monitoring, flexible maintenance systems, and transparent public participation to achieve resilient and equitable urban street greening structures. Full article

Robust detection of emergency vehicle sirens remains difficult due to modern soundproofing, competing audio, and variable traffic noise. Although many simulation-based studies have been reported, relatively few systems have been realized in hardware, and many proposed approaches rely on complex or artificial intelligence-based processing with limited interpretability. This work presents a physical implementation of a low-complexity yelp siren detector that leverages the symmetries of the yelp signal, together with its characterization under realistic conditions. The design is not based on conventional signal processing or machine learning pipelines. Instead, it uses a simple analog envelope-based principle with threshold-crossing rate analysis and a fixed comparator threshold. Its performance was evaluated using an open dataset of more than 1000 real-world audio recordings spanning different road conditions. Detection accuracy, false-positive behavior, and robustness were systematically evaluated on a real hardware implementation using multiple deployable decision rules. Among the evaluated detection rules, a representative operating point achieved a true positive rate of 0.881 at a false positive rate of 0.01, corresponding to a Matthews correlation coefficient of 0.899. The results indicate that a fixed-threshold realization can provide reliable yelp detection with very low computational requirements while preserving transparency and ease of implementation. The study establishes a pathway from conceptual detection principle to deployable embedded hardware. Full article

Support Vector Machines (SVMs) are widely used in critical decision-making applications, such as precision agriculture, due to their strong theoretical foundations and their ability to construct an optimal separating hyperplane in high-dimensional spaces. However, the effectiveness of SVMs is highly dependent on the efficiency of the optimization algorithm used to solve their underlying dual problem, which is often complex and constrained. Classical solvers, such as Sequential Minimal Optimization (SMO) and Stochastic Gradient Descent (SGD), present inherent limitations: SMO ensures numerical stability but lacks scalability and is sensitive to heuristics, while SGD scales well but suffers from unstable convergence and limited suitability for nonlinear kernels. To address these challenges, this study proposes a novel hybrid optimization framework based on Open Competency Optimization and Particle Swarm Optimization (OCO–PSO) to enhance the training of SVMs. The proposed approach combines the global exploration capability of PSO with the adaptive competency-based learning mechanism of OCO, enabling efficient exploration of the solution space, avoidance of local minima, and strict enforcement of dual constraints on the Lagrange multipliers. Across multiple datasets spanning medical (diabetes), agricultural yield, signal processing (sonar and ionosphere), and imbalanced synthetic data, the proposed OCO-PSO–SVM consistently outperforms classical SVM solvers (SMO and SGD) as well as widely used classifiers, including decision trees and random forests, in terms of accuracy, macro-F1-score, Matthews correlation coefficient (MCC), and ROC-AUC. On the Ionosphere dataset, OCO-PSO achieves an accuracy of $95.71\%$, an F1-score of $0.954$, and an MCC of $0.908$, matching the accuracy of random forest while offering superior interpretability through its kernel-based structure. In addition, the proposed method yields a sparser model with only 66 support vectors compared to 71 for standard SVC (a reduction of approximately $7\%$), while strictly satisfying the dual constraints with a near-zero violation of $1.3\times {10}^{-3}$. Notably, the optimal hyperparameters identified by OCO-PSO ($\mathrm{C}=2$, $\gamma \approx 0.062$) differ substantially from those obtained via Bayesian optimization for SVC ($\mathrm{C}=10$, $\gamma \approx 0.012$), indicating that the proposed approach explores alternative yet equally effective regions of the hypothesis space. The statistical significance and robustness of these improvements are confirmed through extensive validation using 1000 bootstrap replications, paired Student’s t-tests, Wilcoxon signed-rank tests, and Holm–Bonferroni correction. These results demonstrate that the proposed metaheuristic hybrid optimization framework constitutes a reliable, interpretable, and scalable alternative for training SVMs in complex and high-dimensional classification tasks. Full article

Understanding residents’ perceptions of ecosystem services (ES) and ecosystem disservices (EDS) is crucial for protected areas governance. This study, conducted in China’s Three-River-Source National Park (TNP), employed participatory rural appraisal and household questionnaires to examine local cognitive patterns of ES and EDS, along with their socio-spatial heterogeneity and perceived synergies and trade-offs among them. The key findings are as follows: (1) Cultural services received the highest scores, followed by regulating services, whereas provisioning services, especially food provisioning, were rated as relatively inadequate. Safety threats were considered the most severe EDS. Overall, a Matthew Effect emerged: services with high current perception scores showed an improving trend, while those with low scores deteriorated. (2) Spatially, ES/EDS evaluation scores exhibited a “core zone < general control zone < peripheral zone” gradient. Socio-demographic and economic factors also influenced residents’ perceptions; women and the elderly were especially more concerned about food and energy supply shortages and safety issues. (3) The relationships among the various ES and EDS are primarily synergistic rather than trade-offs. Specifically, gains in regulating services were associated with enhanced cultural services, while declines in provisioning services and intensified safety threats coincided with the deterioration of material EDS. These findings offer a scientific basis for managing protected areas in high-altitude, ecologically fragile regions and provide practical insights for balancing ecological conservation with community development. Full article

This study re-evaluates ROC-AUC for binary classification under severe class imbalance (<3% positives). Despite its widespread use, ROC-AUC can mask operationally salient differences among classifiers when the costs of false positives and false negatives are asymmetric. Using three benchmarks, credit-card fraud detection (0.17%), yeast protein localization (1.35%), and ozone level detection (2.9%), we compare ROC-AUC with Matthews Correlation Coefficient, F2-score, H-measure, and PR-AUC. Our empirical analyses span 20 classifier–sampler configurations per dataset, combined with four classifiers (Logistic Regression, Random Forest, XGBoost, and CatBoost) and four oversampling methods plus a no-resampling baseline (no resampling, SMOTE, Borderline-SMOTE, SVM-SMOTE, ADASYN). ROC-AUC exhibits pronounced ceiling effects, yielding high scores even for underperforming models. In contrast, MCC and F2 align more closely with deployment-relevant costs and achieve the highest Kendall’s τ rank concordance across datasets; PR-AUC provides threshold-independent ranking, and H-measure integrates cost sensitivity. We quantify uncertainty and differences using stratified bootstrap confidence intervals, DeLong’s test for ROC-AUC, and Friedman–Nemenyi critical-difference diagrams, which collectively underscore the limited discriminative value of ROC-AUC in rare-event settings. The findings recommend a shift to a multi-metric evaluation framework: ROC-AUC should not be used as the primary metric in ultra-imbalanced settings; instead, MCC and F₂ are recommended as primary indicators, supplemented by PR-AUC and H-measure where ranking granularity and principled cost integration are required. This evidence encourages researchers and practitioners to move beyond sole reliance on ROC-AUC when evaluating classifiers in highly imbalanced data. Full article

Background/Objectives: While previous studies have evaluated AI algorithms for cervical spine fracture (CSFx) detection on CT, many have lacked validation on diverse, multinational datasets or have focused primarily on overall case-level classification This study aimed to evaluate the performance of an AI application for acute CSFx detection in case-level classification, fracture localization, and spinal level labeling on multicenter, multinational, and multivendor CT data. Methods: Non-enhanced CTs were retrospectively collected from a U.S. teleradiology company, a French teleradiology company, and a U.S. university hospital. Four radiologists independently labeled the presence and location (including the spinal level) of acute CSFx to establish the reference standard. Per-case diagnostic performance, per-bounding box positive predictive value (PPV) for localization, and overall agreement of cervical vertebral level labeling of the AI were assessed. Results: A total of 155 patients (60.6 years ± 21.2 years, 104 men) with acute CSFx and 173 patients (51.9 years ± 22.7 years, 91 men) without acute CSFx were evaluated. Data were acquired using scanners from five manufacturers. For acute CSFx diagnosis, the AI achieved a per-case sensitivity of 90.3%, a specificity of 91.9%, an accuracy of 91.2%, an area under the receiver operating characteristic curve (AUC) of 0.91, and Matthews correlation coefficient of 0.82. Among 192 bounding boxes representing acute CSFx generated for 154 positive cases by the AI, 162 were true positives (per-bounding box PPV, 84.4%). Of the 186 bounding boxes for which the AI displayed cervical spinal level, 181 were labeled correctly (overall agreement, 97.3%). Conclusions: The AI application for detecting acute CSFx demonstrated high diagnostic performance on multicenter, multinational, and multivendor data, with high performance in fracture localization and spinal level labeling. Full article

Oral cancer (OC) remains a major global health concern with survival often limited by late diagnosis. Early and accurate detection is essential to improve patient outcomes and guide treatment decisions. In this study we propose a computer aided diagnostic (CAD) framework for classifying oral squamous cell carcinoma from histopathology images. The model combines Swin transformer for hierarchical feature extraction with vision transformer (ViT) to capture long range dependencies across image regions. SHapley Additive exPlanations (SHAP) based feature selection enhances interpretability by highlighting the most informative features while preprocessing steps such as stain normalization and contrast enhancement improve model generalization and reduce sample variability. Evaluated on a publicly available dataset the framework achieved 99.25% accuracy (ACC) 99.21% sensitivity and a matthews correlation coefficient (MCC) of 98.21% outperforming existing methods. Ablation studies highlighted the importance of positional encoding and statistical analyses confirmed the robustness and reliability of results. To support real-time inference and scalable deployment the proposed model has been integrated into a FastAPI-based web application. This framework offers a powerful interpretable and practical tool for early OC detection and has potential for integration into routine clinical workflows. Full article

Background: Accurate recognition of promoter sequences in Escherichia coli is fundamental for understanding gene regulation and engineering synthetic biological systems. However, existing computational methods struggle to simultaneously model long-range genomic dependencies and fine-grained local motifs, particularly the degenerate −10 and −35 elements of $\sigma 70$ promoters. To address this gap, we propose DNABERT2-CAMP, a novel hybrid deep learning framework designed to integrate global contextual understanding with high-resolution local motif detection for robust promoter identification. Methods: We constructed a balanced dataset of 8720 experimentally validated and negative 81-bp sequences from RegulonDB, literature, and the E. coli K-12 genome. Our model combines a pre-trained DNABERT-2 Transformer for global sequence encoding with a custom CAMP module (CNN-Attention-Mean Pooling) for local feature refinement. We evaluated performance using 5-fold cross-validation and an independent external test set, reporting standard metrics including accuracy, ROC AUC, and Matthews correlation coefficient (MCC). Results: DNABERT2-CAMP achieved 93.10% accuracy and 97.28% ROC AUC in cross-validation, outperforming existing methods including DNABERT. On an independent test set, it maintained strong generalization (89.83% accuracy, 92.79% ROC AUC). Interpretability analyses confirmed biologically plausible attention over canonical promoter regions and CNN-identified AT-rich/-35-like motifs. Conclusions: DNABERT2-CAMP demonstrates that synergistically combining pre-trained Transformers with convolutional motif detection significantly improves promoter recognition accuracy and interpretability. This framework offers a powerful, generalizable tool for genomic annotation and synthetic biology applications. Full article

Background: Dental caries is a prevalent global oral health issue. The early detection of enamel caries, the initial stage of decay, is critical to preventive dentistry but is often limited by the subjectivity and variability of conventional diagnostic methods. Objective: This study aims to develop and evaluate two explainable deep learning models for the automated classification of enamel caries from intraoral images. Dataset and Methodology: A publicly available dataset of 2000 intraoral images showing early-stage enamel caries, advanced enamel caries, no-caries was used. The dataset was split into training, validation, and test sets in a 70:15:15 ratio, and data preprocessing and augmentation were applied to the training set to balance the dataset and prevent model overfitting. Two models were developed, ExplainableDentalNet, a custom lightweight CNN, and Interpretable ResNet50-SE, a fine-tuned ResNet50 model with Squeeze-and-Excitation blocks, and both were integrated with Gradient-Weighted Class Activation Mapping (Grad-CAM) for visual interpretability. Results: As evaluated on the test set, ExplainableDentalNet achieved an overall accuracy of 96.66% and a Matthews Correlation Coefficient [MCC] = 0.95, while Interpretable ResNet50-SE achieved 98.30% accuracy (MCC = 0.975). McNemar’s test indicated no significant prediction bias, with p > 0.05, and internal bootstrap and cross-validation analyses indicated stable performance. Conclusions: The proposed explainable models demonstrated high diagnostic accuracy in enamel caries classification on the studied dataset. While the present findings are promising, future clinical applications will require external validation on multi-center datasets. Full article

Background/Objectives: Colombia harbors exceptional plant diversity, comprising over 31,000 formally identified species, of which approximately 6000 are classified as useful plants. Among these, 2567 species possess documented food and medicinal applications, with several traditionally utilized for managing febrile illnesses. Despite the global burden of dengue virus infection affecting millions annually, no specific antiviral therapy has been established. This study aimed to identify potential anti-dengue compounds from Colombian medicinal flora through machine learning-based quantitative structure–activity relationship (QSAR) modeling. Methods: An optimized XGBoost algorithm was developed through Bayesian hyperparameter optimization (Optuna, 50 trials) and trained on 2034 ChEMBL-derived activity records with experimentally validated anti-dengue activity (IC₅₀/EC₅₀). The model incorporated 887 molecular features comprising 43 physicochemical descriptors and 844 ECFP4 fingerprint bits selected via variance-based filtering. IC₅₀ and EC₅₀ endpoints were modeled independently based on their pharmacological distinction and negligible correlation (r = −0.04, p = 0.77). Through a systematic literature review, 2567 Colombian plant species from the Humboldt Institute’s official checklist were evaluated (2501 after removing duplicates and infraspecific taxa), identifying 358 with documented antiviral properties. Phytochemical analysis of 184 characterized species yielded 3267 unique compounds for virtual screening. A dual-endpoint classification strategy categorized compounds into nine activity classes based on combined potency thresholds (Low: pActivity ≤ 5.0, Medium: 5.0 < pActivity ≤ 6.0, High: pActivity > 6.0). Results: The optimized model achieved robust performance (Matthews correlation coefficient: 0.583; ROC-AUC: 0.896), validated through hold-out testing (MCC: 0.576) and Y-randomization (p < 0.01). Virtual screening identified 276 compounds (8.4%) with high predicted potency for both endpoints (“High-High”). Structural novelty analysis revealed that all 276 compounds exhibited Tanimoto similarity < 0.5 to the training set (median: 0.214), representing 145 unique Murcko scaffolds of which 144 (99.3%) were absent from the training data. Application of drug-likeness filtering (QED ≥ 0.5) and applicability domain assessment identified 15 priority candidates. In silico ADMET profiling revealed favorable pharmaceutical properties, with Incartine (pIC₅₀: 6.84, pEC₅₀: 6.13, QED: 0.83), Bilobalide (pIC₅₀: 6.78, pEC₅₀: 6.07, QED: 0.56), and Indican (pIC₅₀: 6.73, pEC₅₀: 6.11, QED: 0.51) exhibiting the highest predicted potencies. Conclusions: This systematic computational screening of Colombian medicinal flora demonstrates the untapped potential of regional biodiversity for anti-dengue drug discovery. The identified candidates, representing structurally novel chemotypes, are prioritized for experimental validation. Full article

Background/Objectives: Acute respiratory distress syndrome (ARDS) represents a critical complication in polytrauma patients, characterized by diffuse lung inflammation and bilateral pulmonary infiltrates with mortality rates reaching 45% in intensive care units (ICU). The heterogeneous nature of ARDS and complex clinical presentation in severely injured patients poses substantial diagnostic challenges, necessitating early prediction tools to guide timely interventions. Machine learning (ML) algorithms have emerged as promising approaches for clinical decision support, demonstrating superior performance compared to traditional scoring systems in capturing complex patterns within high-dimensional medical data. Based on the identified research gaps in early ARDS prediction for polytrauma populations, our study aimed to: (i) develop a balanced random forest (BRF) ML model for early ARDS prediction in critically ill polytrauma patients, (ii) identify the most predictive clinical features using ANOVA-based feature selection, and (iii) evaluate model performance using comprehensive metrics addressing class imbalance challenges. Methods: This retrospective cohort study analyzed 407 polytrauma patients admitted to the ICU of the Center of Traumatology and Major Burns of Ben Arous, Tunisia, between 2017 and 2021. We implemented a comprehensive ML pipeline that incorporates Tomek Links undersampling, ANOVA F-test feature selection for the top 10 predictive variables, and SMOTE oversampling with a conservative sampling rate of 0.3. The BRF classifier was trained with class weighting and evaluated using stratified 5-fold cross-validation. Performance metrics included AUROC, PR-AUC, sensitivity, specificity, F1-score, and Matthews correlation coefficient. Results: Among 407 patients, 43 developed ARDS according to the Berlin definition, representing a 10.57% incidence. The BRF model demonstrated exceptional predictive performance with an AUROC of 0.98, a sensitivity of 0.91, a specificity of 0.80, an F1-score of 0.84, and an MCC of 0.70. Precision–recall AUC reached 0.86, demonstrating robust performance despite class imbalance. During stratified cross-validation, AUROC values ranged from 0.93 to 0.99 across folds, indicating consistent model stability. The top 10 selected features included procalcitonin, PaO₂ at ICU admission, 24-h pH, massive transfusion, total fluid resuscitation, presence of pneumothorax, alveolar hemorrhage, pulmonary contusion, hemothorax, and flail chest injury. Conclusions: Our BRF model provides a robust, clinically applicable tool for early prediction of ARDS in polytrauma patients using readily available clinical parameters. The comprehensive two-step resampling approach, combined with ANOVA-based feature selection, successfully addressed class imbalance while maintaining high predictive accuracy. These findings support integrating ML approaches into critical care decision-making to improve patient outcomes and resource allocation. External validation in diverse populations remains essential for confirming generalizability and clinical implementation. Full article

Against the backdrop of China’s “dual carbon” strategy and regional integration, enhancing green innovation efficiency (GIE) has become a core issue for the Yangtze River Delta Urban Agglomeration (YRDUA) in achieving sustainable and high-quality development. This study employs the Super EBM model to measure the GIE of 41 cities in the YRDUA from 2012 to 2022 and further integrates a modified gravity model with social network analysis to uncover the structural complexity and spatial directionality of its spatial association network. In addition, the Exponential Random Graph Model (ERGM) is applied to explore the formation mechanisms of the green innovation efficiency network. Results show the following: (1) GIE presents a fluctuating upward trend, with the mean rising from 0.747 in 2012 to 0.906 in 2022 and disparities gradually narrowing, but provincial gradients persist, implying potential “Matthew effect” risks. (2) Network density continues to increase, with S-density rising from 0.0061 in 2012 to 0.0335 in 2022; supporting and basic connections serve as key drivers of network complexity, whereas the significant decline of edge connections may weaken the network’s extensibility. (3) Node connections display preference and attachment, causing polarization; transitivity and triadic cooperation rise markedly, increasing by 41.89% and 40.86%, respectively, reflecting strong self-organization. (4) Reciprocity and agglomeration drive network formation, and economic and technological differences promote it, while disparities in innovation input and government roles vary across periods. Geographic distance hinders formation, though its effect is weakening. These findings enhance the methodological approaches to sustainability research and provide insights for optimizing regional cooperation and advancing green integration in the YRDUA. Full article

Human beings are affected by different types of skin diseases worldwide. Automatic identification of skin disease from Dermoscopy images has proved effective for diagnosis and treatment to reduce fatality rate. The objective of this work is to demonstrate efficiency of three deep learning pre-trained models, namely MobileNet, EfficientNetB0, and DenseNet121 with ensembling techniques for classification of skin lesion images. This study considers HAM1000 dataset which consists of n = 10,015 images of seven different classes, with a huge class imbalance. The study has two-fold contributions for the classification methodology of skin lesions. First, modification of three pre-trained deep learning models for grouping of skin lesion into seven types. Second, Weighted Grid Search algorithm is proposed to address the class imbalance problem for improving the accuracy of the base classifiers. The results showed that the weighted ensembling method achieved a 3.67% average improvement in Accuracy, Precision, and Recall, 3.33% average improvement for F1-Score, and 7% average improvement for Matthews Correlation Coefficient (MCC) when compared to base classifiers. Evaluation of the model’s efficiency and performance shows that it obtained the highest ROC-AUC score of 92.5% for the modified MobileNet model for skin lesion categorization in comparison to EfficientNetB0 and DenseNet121, respectively. The implications of the results show that deep learning methods and classification techniques are effective for diagnosis and treatment of skin lesion diseases to reduce fatality rate or detect early warnings. Full article

The Sanjiangyuan Region (SJYR), located in the core of the Qinghai–Tibet Plateau, is a key ecological barrier where grasslands, the dominant land cover, are undergoing continuous degradation due to climate change and human activities. Accurate characterization of grassland is essential for ecological monitoring, yet existing land-cover products show substantial discrepancies in alpine environments. This study systematically evaluated the spatial consistency and accuracy of six publicly medium resolution land cover products: GLC_FCS30, GlobeLand30, FROM_GLC10, ESA WorldCover (ESA), ESRI Land Cover (ESRI), and Dynamic World. We evaluated these products by comparing them with the Third National Land Survey data, performing Jaccard similarity and spatial consistency analyses, and validating their accuracy using five metrics: Overall Accuracy (OA), Producer’s Accuracy (PA), User’s Accuracy (UA), F1-score, and Matthews Correlation Coefficient (MCC). Results show large variations in estimated grassland area, ranging from 91,105 km² (Dynamic World) to 325,669 km² (GLC_FCS30). Pixel-level comparison revealed significant spatial heterogeneity, with only 54.3% of the region showing the desired high consistency. Accuracy validation indicated that ESA achieved the best classification results (OA = 74.24%, MCC = 0.80), while Dynamic World performed the worst (OA = 57.45%, F1 = 0.28). These products showed lower consistency in high-altitude western areas, and classification accuracy for most products varied with elevation and slope, indicating that topographic factors significantly influence remote sensing classification capabilities. These results provide a quantitative basis for product selection in the SJYR and highlight the need for improved calibration, data fusion, and classification approaches that better account for sparse vegetation and complex topography. Full article

As technology advances, developers continually create innovative solutions to enhance smartphone security. However, the rapid spread of Android malware poses significant threats to devices and sensitive data. The Android Operating System (OS)’s open-source nature and Software Development Kit (SDK) availability mainly contribute to this alarming growth. Conventional malware detection methods, such as signature-based, static, and dynamic analysis, face challenges in detecting obfuscated techniques, including encryption, packing, and compression, in malware. Although developers have created several visualization techniques for malware detection using deep learning (DL), they often fail to accurately identify the critical malicious features of malware. This research introduces MalVis, a unified visualization framework that integrates entropy and N-gram analysis to emphasize meaningful structural and anomalous operational patterns within the malware bytecode. By addressing significant limitations of existing visualization methods, such as insufficient feature representation, limited interpretability, small dataset sizes, and restricted data access, MalVis delivers enhanced detection capabilities, particularly for obfuscated and previously unseen (zero-day) malware. The framework leverages the MalVis dataset introduced in this work, a publicly available large-scale dataset comprising more than 1.3 million visual representations in nine malware classes and one benign class. A comprehensive comparative evaluation was performed against existing state-of-the-art visualization techniques using leading convolutional neural network (CNN) architectures, MobileNet-V2, DenseNet201, ResNet50, VGG16, and Inception-V3. To further boost classification performance and mitigate overfitting, the outputs of these models were combined using eight distinct ensemble strategies. To address the issue of imbalanced class distribution in the multiclass dataset, we employed an undersampling technique to ensure balanced learning across all types of malware. MalVis achieved superior results, with 95% accuracy, 90% F1-score, 92% precision, 89% recall, 87% Matthews Correlation Coefficient (MCC), and 98% Receiver Operating Characteristic Area Under Curve (ROC-AUC). These findings highlight the effectiveness of MalVis in providing interpretable and accurate representation features for malware detection and classification, making it valuable for research and real-world security applications. Full article