Search Results (1,649)

Prolonged driver inattention significantly increases the risk of traffic accidents, necessitating continuous physiological monitoring for improved road safety and driver wellbeing. This study proposes a Self-Attention-based Hybrid Quantum Neural Network (SAHQNN), a novel framework integrating trainable Parameterized Quantum Circuits (PQCs) with selective self-attention for automated detection of phone call distraction-induced cognitive and emotional driver inattention from multimodal wearable biosignals. Multimodal physiological signals consisting of single-lead Electrocardiogram (ECG, 256 Hz) and Respiration (RSP, 128 Hz) were acquired from $N=20$ participants under Normal and Distracted-Inattention driving conditions using a textile wearable smart shirt. The Distracted-Inattention condition was induced through a hands-free phone call that simultaneously imposed cognitive load, emotional arousal, and secondary task engagement on the driver through active questioning, reflecting the multidimensional nature of driver inattention beyond speech activity alone. Multi-domain features reduced via Random Forest Feature Importance (RFF) were angle-encoded into 10-qubit PQCs with 20 trainable variational $R_Y\left(\theta \right)$ gates optimized via the parameter-shift rule, establishing inter-qubit correlations through Hadamard and Controlled-NOT (CNOT) entanglement layers. Pauli-Z measurement outputs were processed through a selective self-attention layer, producing Attentive Quantum Features (AQF) that were subsequently classified by fully connected layers. The proposed SAHQNN achieves 77.50% accuracy and 70% weighted F-measure under Leave One Subject Out Cross-Validation (LOSOCV), with statistically significant improvements over all standard classical baselines ($p<0.001$, Cohen’s $d>1.5$) and 61% fewer parameters than the strongest classical competitor, demonstrating the feasibility of parameter-efficient trainable hybrid quantum neural networks for subject-independent driver inattention detection. Full article

Ransomware detection remains challenging because modern variants exhibit diverse, elusive, and partly benign behaviors and can propagate rapidly across interconnected enterprises and sensor-enabled cyber-physical systems, causing cascading operational failures. These characteristics undermine signature-based and static-detection methods. Although machine learning has improved detection, many approaches still rely on fixed objectives that weight samples uniformly, limiting their adaptation to heterogeneity and overlaps between ransomware and benign activities. To address this challenge, we introduce TL-RL-FusionNet, a reinforcement learning (RL)-guided hybrid framework that combines dual transfer learning (TL) backbones, EfficientNetB0 and InceptionV3, with a lightweight residual multi-Layer perceptron (MLP) classifier. The framework converts sandbox reports into RGB grids, extracts features using frozen CNN backbone networks, and fuses embeddings for classification. Training is guided by a tabular Q-learning sample-weighting agent, formulated as a per-sample bandit over discrete weight actions. To prevent cross-fold information leakage, the Q-table is freshly initialized in each cross-validation fold and updated only using the fold-local training partition, whereas the held-out fold is used for the final evaluation. The framework was evaluated using two datasets. On our dataset, TL-RL-FusionNet achieved the best overall performance on Dataset 1, with 99.20% accuracy, 99.40% recall, and 99.84% AUC. On the public EldeRan benchmark, it achieved 90.36% accuracy using the full dynamic feature space and 92.08% using a Mutual Information-selected compact subset. Paired Wilcoxon tests across five folds were used to assess the RL contribution, while additional grid-order sensitivity analysis showed that the image-based representation remained robust under five random 10 × 10 feature-grid permutations. Interpretability analysis using t-distributed stochastic neighbor embedding (t-SNE) and gradient-weighted class activation mapping feature-grid mapping further showed that the model captured discriminative behavioral patterns. Overall, these results demonstrate that RL-guided sample reweighting improves adaptive ransomware detection while maintaining efficiency and interpretability. The dataset and supporting code are publicly available on GitHub. Full article

Background/Objectives: Melanoma is a life-threatening skin cancer characterized by aggressive progression and high metastatic potential, making early diagnosis essential for improving patient survival and treatment outcomes. However, accurate automated skin lesion classification remains challenging due to variations in lesion appearance, illumination, image quality, and the presence of artifacts. This study proposes a unified framework for robust multi-class skin cancer classification by integrating preprocessing, lesion segmentation, feature extraction, optimization, and classification within a single end-to-end architecture. Methods: The proposed framework employs an iterative hair artifact removal strategy based on the fusion of Frangi vesselness filtering, Gabor texture filtering, morphological refinement, and Telea inpainting to preserve lesion integrity. A novel dermoscopic lesion segmentation network (CutisNet) is introduced to accurately delineate lesion boundaries. Hybrid representation learning combines deep features extracted using MobileNetV2 with uniquely selected handcrafted descriptors to capture complementary texture, structural, and contextual information. Gray Wolf Optimization is utilized for feature fusion and refinement, while a hybrid GNN–CNN classifier performs robust multi-class skin lesion classification. Results: Extensive experiments conducted on multiple benchmark dermoscopic datasets demonstrate the effectiveness and generalization capability of the proposed framework. The proposed model consistently outperformed existing state-of-the-art methods, achieving a maximum classification accuracy of 96.7% on the PH² dataset while maintaining competitive performance across other benchmark datasets. Conclusions: The proposed framework effectively integrates novel preprocessing, segmentation, hybrid feature representation, feature optimization, and classification strategies to improve the robustness and accuracy of automated skin cancer classification. These results demonstrate its potential to support reliable computer-aided diagnosis and assist clinicians in the early detection of skin cancer. Full article

Rapid and accurate identification of mine water inrush sources is critical for hazard control in underground coal mining. Conventional Fisher discriminant analysis is often limited by feature redundancy and multicollinearity when applied to small-sample, high-dimensional hydrochemical data. To address this, we propose GWO–Fisher, a hybrid model integrating the Grey Wolf Optimizer (GWO) with Fisher discriminant analysis. The model employs correlation-based pre-screening followed by global optimization, using a fitness function that combines Fisher accuracy with a feature-size penalty, to achieve a compact and interpretable feature set. Trained on data from the Xiegou Coal Mine (Shanxi, China), it reduced 17 hydrochemical indicators to 12 key features, achieving 92.98% training accuracy and 86.21% test accuracy—an improvement of 10.35 percentage points over conventional Fisher. When independently validated across four mines in three spring domains, the model maintained over 83% accuracy, consistently selecting TDS, K⁺, and HCO₃⁻ as core features. Misclassification patterns were cross-domain consistent and linked to hydrogeological conditions. The proposed GWO–Fisher model balances predictive accuracy with hydrogeological interpretability, demonstrating reliable performance across both single-mine and cross-spring-domain scenarios. Full article

Prostate adenocarcinoma is characterized by substantial inter-patient heterogeneity, limiting the clinical reliability of conventional diagnostic tools, including prostate-specific antigen testing. This limitation underscores the need for robust molecular biomarkers that may complement conventional diagnostic tools, highlighting the urgent need for biomarkers capable of enhancing diagnostic accuracy and enabling more precise risk stratification. In the present study, transcriptomic data from The Cancer Genome Atlas (TCGA) were analyzed using an integrative bioinformatics and machine learning pipeline., The proposed workflow was designed as a stepwise and reproducible biomarker prioritization framework in which differential expression analysis, functional enrichment, protein–protein interaction (PPI) based network interpretation, graph-convolutional feature selection, and hybrid ensemble machine learning were sequentially integrated. Differential gene expression analysis was combined with pathway enrichment (Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Reactome), protein–protein interaction network construction, and graph-convolutional feature selection. Multiple machine learning algorithms, including Random Forest, Gradient Boosting Machine, Support Vector Classifier, Artificial Neural Network, and AdaBoost, were systematically evaluated. A hybrid ensemble model integrating Gradient Boosting Machine and Random Forest (GBM+RF) was subsequently developed. Model performance was assessed using accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic (ROC) and externally validated using the independent GSE14206 dataset. The analysis revealed a coordinated molecular pattern characterized by dysregulated cell cycle activity and enhanced interferon-mediated immune signaling. Protein–protein interaction analysis identified STAT1 and PLK1 as highly connected network hub genes within immune-related and cell-cycle-associated modules. Among the evaluated models, the hybrid GBM+RF framework achieved the highest predictive performance on the TCGA dataset, with AUC: 0.9526; Accuracy: 97.49%. External validation using the GSE14206 dataset confirmed the robustness of this model (AUC: 0.9156; Accuracy: 91.53%). These findings support a broader multi-gene candidate signature in prostate adenocarcinoma, in which machine learning prioritized genes such as XAF1, APP, RPA3, IFIH1, UBE2D2, RSAD2, KIF2C, and PLK1, while STAT1 and PLK1 provided complementary network-level biological relevance. The proposed framework provides a robust and transferable strategy for biomarker discovery and precision oncology. Full article

Natural products featuring a direct σ-bond between a cyclic monoterpene and an aromatic moiety provide a vast source of biological activities, such as antimicrobial, anticancer, antiviral, anticoagulant and cannabinoid regulatory, among others. Only few methods exist for synthetically accessing such hybrid structures and their analogs, all of which are prone to limitations, most notably the reliance on sensitive organometallic intermediates and the difficulty in furnishing certain stereoisomers. An efficient, three-stage synthetic methodology is described herein, that enables the production of hybrid structures featuring a C(sp³)-C(sp²) bond between six-membered cyclic monoterpenes and aromatic moieties. This process combines: enol triflate formation from a terpenoid ketone precursor, that introduces most of the stereochemical information; Suzuki–Miyaura C-C cross-coupling of the enol triflate with a pool of (hetero)arylboronic acids, to establish the terpene–aromatic link, initially in the form of a C(sp²)-C(sp²) bond; and a stereoselective hydrogenation of the resulting adducts to afford the target compounds, establishing the stereoconfiguration of the last chiral center. Enantiomeric terpenoid scaffolds derived from menthone and trans-tetrahydrocarvone have been combined with six (6) (hetero)arylboronic acids, including medicinally relevant moieties, such as methoxyphenyl, pyridine, quinoline and benzofuran. The power of this method, apart from circumventing the need for in situ-formed sensitive organometallic intermediates, resides in providing access, for the first time, to menthyl- and trans-tetrahydrocarvoneyl-type stereoisomers, that were unattainable by any previously described method. The resulting compound library members exhibit drug-like features, based on the computational assessment of 11 selected physicochemical parameters (molecular weight, polarity, aqueous solubility, degree of unsaturation, conformational flexibility, lipophilicity, BBB permeability, skin permeability, gastrointestinal absorption, P-glycoprotein substrate behavior and Lipinski compatibility), using the platforms SwissADME, ADMETLab 3.0 and pkCSM. A computational docking study employing AutoDock Vina further identified promising candidates for targeting the known binding sites of human cannabinoid receptors CB1 and CB2, with calculated binding affinities comparable to those of established ligands. Full article

Accurate lithofacies identification in carbonate reservoirs is essential for reservoir characterization and development decision-making. However, the strong heterogeneity of carbonate rocks, nonlinear responses of well logging parameters, and imbalance among lithofacies samples significantly limit the performance of conventional machine learning methods. To address these challenges, an improved K-Nearest Neighbor (KNN) lithofacies identification method is proposed in this study using logging data from the Mishrif Formation in the Halfaya Oilfield, Iraq. A total of 600 samples from five wells (X1–X5) were used for model construction and validation. Four carbonate lithofacies types, including grainstone, packstone, wackestone, and marl, were identified based on core observation and thin-section analysis. Five logging parameters, including GR, AC, CNL, DEN, and RT, were selected to construct the feature space. A hybrid SMOTE–NearMiss-1 sampling strategy was introduced to alleviate class imbalance, while a feature-weighted Manhattan distance and distance-weighted voting mechanism were developed to improve the discrimination capability of KNN. The results show that the improved KNN model achieved an overall accuracy of 84.44%, outperforming the baseline KNN model (78.89%) as well as other comparison models, including Random Forest (RF, 76.67%) and Backpropagation Neural Network (BPNN, 75.56%). The area under the ROC curve (AUC) values for all lithofacies classes range from 0.917 to 0.989, indicating robust classification performance. In addition, balanced accuracy and macro-F1 score demonstrate improved recognition performance for minority lithofacies. The predicted lithofacies profiles show good agreement with the core interpretation results and effectively capture vertical lithofacies variations. This study demonstrates that the improved KNN method provides an effective data-driven approach for carbonate reservoir lithofacies characterization, especially under conditions of heterogeneous geological environments and limited labeled samples. Full article

Material Extrusion (MEX) additive manufacturing (AM) of ABS polymer components often requires post-process machining to achieve the necessary dimensional precision and surface quality. However, the influence of printing parameters and tool–material interaction in hybrid manufacturing remains insufficiently explored. This study investigates the impact of initial hole size (D_start), build orientation, and cutting parameters (cutting speed and feed rate) on the dimensional accuracy and surface roughness of machined holes in ABS-M30 specimens. Samples were fabricated in vertical and horizontal orientations and subjected to drilling in solid material and enlargement of printed pilot holes using a twist drill on a 5-axis machining center. Dimensional deviation and surface roughness (Ra, Rz) were evaluated using coordinate metrology and profilometry. The results showed that the smallest machining allowance (0.062 mm per side) was insufficient to completely remove the printing-induced surface texture, resulting in significantly higher and more variable Ra and Rz values. This distinct low-machining-allowance regime was confirmed by statistical analysis and representative optical observations. Conversely, a machining allowance of 0.565 mm per side (corresponding to D_start = 9 mm) resulted in substantially lower surface roughness (Ra ≈ 1.6 µm). Vertical build orientation generally provided better surface quality than the horizontal orientation, which was consistent with fewer visible surface features in the selected optical fields of view. All machining conditions resulted in negative dimensional deviations, indicating elastic recovery of the ABS material after machining. An exploratory multi-response ranking showed that the lowest composite quality scores for overall final hole quality were associated with D_start = 10 mm (machining allowance of 0.062 mm per side). When the analysis was limited to the machining-dominated regime, the lowest score was obtained for the vertical build orientation, D_start = 9 mm, a cutting speed of 40 m/min, and a feed rate of 0.2 mm/rev. These findings provide preliminary guidelines for selecting hybrid manufacturing conditions for MEX-manufactured ABS-M30 components. Full article

Modern power transmission grids are increasingly operated under volatile load, variable generation, and near-limit line-flow conditions. In such environments, deterministic line-flow forecasting is insufficient for operational decision support because operators require calibrated risk probabilities, uncertainty intervals, and reliable early warning signals. This article proposes B-TGPRF, a Bayesian Temporal Graph Probabilistic Risk Forecaster for calibrated overload-risk forecasting in power transmission grids. The proposed framework is positioned as a hybrid probabilistic graph-temporal forecasting system rather than as a new end-to-end graph neural network; its novelty lies in the leakage-controlled sequential combination of temporal forecasting, electrical graph descriptors, calibrated Bayesian risk estimation, residual correction, and compact interval uncertainty assessment. The model integrates temporal line-flow, load, and generation features with graph-topological descriptors, operating-regime indicators, residual correction, conformal interval estimation, probability calibration, and a Bayesian risk layer. A leakage-controlled data preparation pipeline was built using an open large-scale benchmark for machine learning applications in transmission grids. The final modeling dataset contains more than 3.48 million observations, 100 selected critical lines, train-only risk thresholds, and chronological train, validation, test, and external-like scenario splits. B-TGPRF was compared with persistence baselines, linear models, Bayesian baselines, tree ensembles, boosting models, neural temporal models, and compact state-of-the-art-style temporal and graph-temporal architectures. On the strict external-like test, B-TGPRF achieved MAE = 0.3650, RMSE = 0.5478, R² = 0.9962, Brier Score = 0.0147, and ECE = 0.0064. The results show that the proposed model provides a strong overall balance between line-flow forecasting accuracy, calibrated risk estimation, compact interval prediction, and low false-positive risk-signaling, while boosting models remain highly competitive for pure risk-class detection. Full article

As organizations lean more heavily on their IT systems, managing cyber risk is gaining increasing importance. Organizations are often challenged to determine which cybersecurity risk framework they should adopt. Choosing the right framework can have a significant impact on the quality of governance, operational resilience, and assurance in risk reporting. However, most prevalent cybersecurity risk frameworks vary significantly in their intent, design, and analytical approach. This makes it difficult for organizations to understand how each framework may meet their business needs. This study presents an AI-enhanced multi-criteria decision support approach for evaluating cybersecurity risk frameworks. The model incorporates machine learning-driven risk scoring as a conceptual input layer, enhancing the objectivity and analytical rigor of the comparison without executing new predictive algorithms. The methodology includes a hybrid approach of literature review, document analysis, and multi-criteria decision analysis (MCDA) to compare and rank NIST CSF, ISO 27001, FAIR, OCTAVE, and CRAMM based on eight criteria that are designed to represent modern requirements for risk frameworks, including governance, scalability, quantitative focus, and interoperability. These criteria also reflect differences in security metrics supported by each framework to provide an organized means to compare qualitative versus quantitative measurement methodologies. The results indicate that NIST CSF performs the best overall in agility, business alignment, and interoperability. ISO 27001 outperforms all others in established governance and compliance. FAIR outperforms all others in quantitative risk analysis and provides superior analytical depth that other frameworks do not offer. OCTAVE and CRAMM function well in legacy systems but lack scalability and are not well-suited for modern distributed systems. Robustness analysis shows that the ranking of NIST CSF, ISO 27001, and FAIR is consistent under different weighting combinations and industry types. The result of this research demonstrates that a combined or hybrid approach to cybersecurity risk framework selection, such as using NIST CSF with FAIR, can give organizations a more well-rounded foundation for applying machine learning-enabled risk analytics with cyber controls. This research also offers a reusable decision support tool that organizations can leverage when aligning their risk priorities to the features of cybersecurity risk frameworks. Full article

Image super-resolution (SR) is a fundamental task in computer vision that aims to recover high-fidelity details from low-resolution images. To address the limitations of existing Transformer-based SR methods, this paper introduces GSDAT-Net, a grid-spatial dual-attention-driven residual hybrid Transformer. By integrating Grid Attention Block (GAB), an Enhanced Spatial Attention (ESA) module, and SwinV2 Transformer layers (S2TL), GSDAT-Net extracts multi-scale features and improves local and global feature representation. Extensive experiments demonstrate that GSDAT-Net achieves competitive reconstruction accuracy and visual quality compared with the selected methods, with a maximum PSNR improvement of up to 0.15 dB on benchmark datasets. Full article

High-speed Unmanned Aerial Vehicles (UAVs), characterized by high velocity and maneuverability, represent critical strategic threats within the aerospace security domain. Accurate trajectory prediction is a fundamental prerequisite for effective early warning and decision-making in defense. Despite increasing research in the domain, model-, data-, and hybrid-driven methods have not yet been comprehensively examined under a unified framework, limiting the understanding of their relative strengths and applicability. To address this gap, this paper systematically reviews the evolution and current technical status of these paradigms, categorized by the core logic underlying prediction methods. The principles and applicability limits of physical process modeling and state estimation algorithms are analyzed, along with emerging applications of machine learning and deep learning for trajectory feature extraction and pattern recognition. State-of-the-art architectures involving the integration of physical constraints and data-driven learning are discussed. Standard evaluation metrics are introduced to facilitate performance benchmarking of existing methods. Comparative analysis reveals that no single technical route can fully address the coupled challenges of uncertainty, accuracy, and real-time performance, underscoring that hybrid frameworks are essential for balancing these competing requirements. Lastly, key challenges are summarized, and future research directions are outlined to advance trajectory prediction methodologies. The provided insights can inform method selection and promote the development of high-accuracy prediction systems. Full article

Network Intrusion Detection Systems (NIDS) face a trade-off between detection accuracy and computing efficiency, particularly in the edge environment with strict real-time requirements and limited resources. Current approaches rely on complicated models, which are computationally demanding, or simple ones, which sacrifice detection performance. To deal with this issue, we propose a lightweight cloud-edge cooperative two-stage NIDS architecture, which separates the real-time detection and detailed classification. At the edge, a decision tree based on feature selection is used for rapid binary classification by using only the top 10 most informative features, thus efficiently screening out abnormal traffic with minimum processing cost. Meanwhile, the cloud server identifies attack classification accurately by using a hybrid CNN-BiLSTM-Attention model to capture the spatial structures, temporal relationships, and semantic relevance. This hierarchical design effectively balances detection performance and system efficiency. Experiments conducted on UNSW-NB15, NSL-KDD, and CIC-IDS2017 datasets indicate that our suggested scheme can obtain competitive performance both at the edge and in the cloud. The edge model obtains binary classification accuracy of 86.04%, 95.27%, and 99.01%, respectively, with very low processing cost (less than 100 FLOPs per sample). The cloud model achieves multi-class accuracy of 92.23%, 97.18%, and 98.66%, respectively, with AUC values higher than 0.98. The hierarchical cloud–edge collaborative design provides an efficient and accurate solution for intrusion detection under resource-restricted situations. Full article

Timely graduation, time-to-degree, and degree completion are key indicators of student progression and institutional effectiveness in higher education. This study presents a PRISMA-based systematic literature review of machine learning approaches for graduation-related prediction, with attention to predictive targets, pipeline components, scalability, and bio-inspired optimization. Searches in Web of Science Core Collection and Scopus identified 278 records, of which 25 studies published between 2021 and 2025 met the eligibility criteria. The findings show that most studies formulated graduation prediction as a supervised classification task, relied heavily on academic performance variables, and frequently used tree-based or ensemble models. Feature selection, explainability, and hyperparameter optimization were commonly reported, but bio-inspired optimization was actively implemented in only two studies through Particle Swarm Optimization, Genetic Algorithms, or Ant Colony Optimization. The evidence base also remains limited in scalability, as most studies used single-institution datasets and provided little external validation. These findings identify an opportunity for Bio-Inspired Educational Analytics through scalable feature selection, efficient hyperparameter optimization, model simplification, and multi-objective trade-off analysis. Future research should evaluate whether lightweight, hybrid, and multi-objective metaheuristics can support accurate, interpretable, fair, and transferable graduation prediction systems. Full article

In response to the challenge of insufficient accuracy in short-term air temperature prediction under severe changes in agricultural microclimate, a hybrid prediction model based on GABP-Net (Gated-Attention and BP Parallel Network) neural network and attention mechanism is proposed. The proposed GABP-Net provides a comprehensive feature fusion framework through two parallel branches: the Gated-Attention branch, built on a GRU followed by multi-head attention, captures local temporal dependencies, with the multi-head attention component adaptively reweighting the GRU outputs across multiple heads to capture diverse temporal patterns; meanwhile, the BP branch, a Backpropagation neural network operating on the flattened input, extracts global contextual features. Their parallel combination enables the model to simultaneously leverage both local dynamics and global representations. Taking 28.2 hectares of farmland in Pingdu, Qingdao as the research object, based on observation data collected every 2 h from September to October 2025, combined with meteorological station measurements and background meteorological prediction data, key meteorological factors such as temperature, radiation, and pressure were selected as input features. The results showed that in the 6-h, 12 h, and 24-h prediction tasks, the model’s R² reached 0.9654, 0.9759, and 0.9622, respectively. The MAE was 0.95 °C, 0.84 °C, and 1.04 °C, respectively, and the RMSE was ≤1.32 °C, significantly better than the single BP (Backpropagation) and GRU (Gated Recurrent Unit) models. Research has shown that this hybrid model effectively improves prediction stability under realistic field conditions with naturally imperfect sensor data and wide temperature variations (overall range 39 °C, maximum diurnal difference 21.6 °C), providing reliable technical support for microclimate regulation in precision agriculture. Full article