Search Results (192)

The automated classification of Hebrew, a morphologically rich language (MRL), presents unique challenges, particularly when high-quality labeled data are scarce. This study investigates the interplay between handcrafted feature engineering and transformer-based representations in a low-resource news classification setting (n = 306). We evaluate a multi-task classification across four distinct dimensions: domain, sentiment, gender, and source. Our methodology employs an extensive feature space of 2149 stylistic and content-based attributes, optimized through a systematic Hill-Climbing selection process. We contrast five classical machine learning architectures with five BERT-based models, integrating five oversampling strategies to mitigate class imbalance. The results reveal that in scenarios of extreme data scarcity, the performance gap between deep learning and optimized classical ML becomes marginal, with stylistic features providing critical stability and interpretability. This study contributes a curated Hebrew news dataset and establishes a robust benchmark, demonstrating that linguistically aware feature engineering remains a vital component for MRL processing when large-scale fine-tuning is impractical. Full article

The industrial X-ray inspection of turbine blade castings requires reliable and auditable decision support, yet defect indications are subtle, and data availability is limited. This study quantitatively assesses the diagnostic potential of handcrafted image descriptors by evaluating class separability in feature space, independently of any trained classifier. The dataset comprises 1600 16-bit DICOM radiograms of 200 blades (eight views per blade), including 156 defective images with 207 localized defects. Standardized 32 × 32 ROI patches were sampled randomly in the vicinity of indications and from defect-free regions to reduce sample correlation and to emulate localization uncertainty. Feature vectors were extracted using five descriptor families—first-order statistics, GLCM/Haralick, FFT and wavelet (DWT) features, Gabor filters, and LBP—and the standardized z-score. Separability was ranked using complementary distribution-based and distance-based metrics grouped into three sets, and the results were min–max-normalized to enable TOP-5 comparisons. Spectral descriptors, particularly DWT wavelets and FFT combined with DWT, consistently achieved the highest scores in distributional metrics, supporting a lightweight screening profile. In contrast, richer combinations dominated multidimensional geometric metrics, indicating benefits from multi-perspective representations for offline analysis. The proposed metric-driven framework provides an interpretable basis for representation selection prior to classifier development under industrial constraints. Full article

Gliomas are generally readily detected and broadly characterized using conventional MRI; however, substantial challenges remain in accurately delineating tumor extent, grading heterogeneous disease, and translating imaging findings into consistent, reproducible clinical decisions. Despite reported Dice coefficients of 0.85–0.91 for whole-tumor segmentation and classification AUC values exceeding 0.90 for glioma grading in curated datasets, most AI systems remain limited by validation design, dataset bias, and inadequate external generalizability. This narrative review synthesizes current AI applications for MRI-based glioma detection and segmentation, highlighting the evolution from radiomics-based classical machine learning approaches relying on handcrafted features to deep learning models capable of end-to-end representation learning. Commonly used MRI sequences, algorithmic paradigms, and reported performance trends are reviewed, with particular emphasis on tumor segmentation as a foundational enabling task. Key limitations that hinder clinical translation are examined, including limited dataset diversity, validation practices that inflate reported performance, domain shift across institutions, acquisition-related bias, and inadequate model interpretability. Emerging strategies to address these challenges, such as multi-institutional training, harmonization techniques, explainable AI frameworks, and workflow-integrated validation, are also discussed. While AI-based models demonstrate strong technical performance in research settings, their clinical impact will depend on rigorous external validation, transparency, and alignment with real-world neuro-oncology workflows. Full article

Automated identification of lumbar vertebrae plays a key role in modern spine analysis, offering valuable assistance for diagnostic assessment and preoperative decision-making. Despite recent progress in deep learning-based detection methods, accurately localizing vertebral structures remains challenging due to anatomical variability and heterogeneous image quality. To address the difficulty of capturing subtle vertebral structures, we introduce a Multi-Scale Channel Attention Block (MSCABlock) integrated into the YOLO11 backbone. Unlike conventional attention-based or multi-scale convolutional designs, MSCABlock jointly exploits channel-wise feature interaction and multi-scale receptive fields to enhance both local detail sensitivity and contextual representation, while preserving computational efficiency. The proposed approach is designed to improve detection performance without significantly increasing model complexity. Our model is trained and validated using only the AP-view images from the Burapha University Lumbar-Spine Dataset (BUU-LSPINE), which provides well-annotated lumbar spine X-ray images from 400 unique patients. The proposed approach operates in a fully end-to-end manner, allowing vertebrae to be identified directly from input images without relying on handcrafted feature engineering or complex preprocessing pipelines. Experimental evaluations show that the proposed model achieves strong detection performance, with mAP@0.5 and mAP@0.5–0.95 reaching 0.982 and 0.79, respectively, alongside a precision of 0.93 and a recall of 0.975. Compared with the YOLO11 baseline, ablation and efficiency analyses demonstrate that MSCABlock consistently improves detection performance. It introduces only marginal increases in model parameters and computational cost, thereby preserving a lightweight architecture and maintaining efficient inference. These results show that the optimized YOLO11-based system generalizes well across lumbar levels. It maintains reliable detection under challenging conditions, providing robust automated localization to support large-scale clinical spine analysis. Full article

The proliferation of Resident Space Objects (RSOs), including satellites, rocket bodies, and debris, poses escalating challenges for Space Situational Awareness (SSA). Optical light curves capture temporal brightness variations influenced by factors such as attitude variation, viewing geometry, and surface properties. When appropriately processed and analyzed, these data can support RSO characterization and classification. This paper presents a scoping review of machine learning (ML) and deep learning (DL) methods for RSO classification using light-curve data. From 297 peer-reviewed studies published between 2014 and 2025, a screened subset of 29 works is selected for detailed methodological comparison. We trace the methodological evolution from handcrafted feature engineering toward convolutional, recurrent, and self-supervised models that learn representations directly from photometric time series. An analysis of three publicly accessible databases, Mini Mega TORTORA, Space Debris Light-Curve Database, and Ukrainian Database, reveals pronounced class imbalance, with payloads comprising over 80% of observations. While models trained on simulated data routinely achieve 95 to 99% accuracy, performance on measured light curves degrades to 75 to 92%, exposing a persistent gap between simulation and observation. We further identify data scarcity, repeated observations of the same objects, and inconsistent evaluation protocols as key barriers to reproducible benchmarking. Future progress will require benchmark-ready, sensor-aware datasets spanning diverse orbital regimes and viewing geometries, alongside physics-informed and transfer-learning approaches that improve robustness across sensors and between synthetic and observational domains. Full article

Influenza A virus remains a major cause of respiratory disease worldwide and poses a persistent challenge to vaccine development due to its rapid genetic evolution and antigenic variability. T-cell-based immunity has therefore gained increasing importance, as it can provide broader and more durable protection by targeting conserved viral regions. Accurate identification of T-cell epitopes (TCEs) is a fundamental requirement for epitope-based vaccine design and immunological research. Although numerous computational methods have been proposed, many existing approaches rely on handcrafted physicochemical features, which offer limited ability to capture contextual sequence dependencies. In this study, a transformer-based viroinformatics framework is proposed for the binary prediction of TCEs from Influenza A virus peptide sequences. The framework employs a pretrained Evolutionary Scale Modeling-2 (ESM-2) protein language model (PLM) to generate rich, contextualized embeddings directly from raw amino acid sequences, eliminating the need for manual feature engineering. These embeddings are processed using a lightweight attention-based transformer classifier to learn epitope-specific sequence patterns. The model achieves strong and stable predictive performance, attaining an accuracy of approximately 97% and an AUC close to 0.99 under stratified cross-validation. Ablation analysis further confirms that protein language model representations and self-attention contribute substantially to performance gains over classical machine learning baselines. To enhance practical reliability, Monte Carlo dropout is incorporated during inference to provide uncertainty-aware predictions, enabling differentiation between high-confidence and ambiguous peptide candidates. In addition, attention-based interpretability is used to identify residue-level contributions to model decisions, offering biologically meaningful insights into epitope recognition. Overall, this study demonstrates that PLMs combined with Transformer architectures provide an effective, interpretable, and a promising computational framework for Influenza A TCE discovery and vaccine research. Full article

The Traveling Salesman Problem (TSP) remains a central benchmark in combinatorial optimization, with applications in logistics, manufacturing, and network design. While exact solvers and classical heuristics offer strong performance, they rely on handcrafted design and show limited adaptability. Recent advances in deep learning have introduced a new paradigm: learning heuristics directly from data, with Transformers standing out for capturing global dependencies and scaling effectively via parallelism. This survey offers a component-wise analysis of Transformer-based TSP models, serving as both a structured review and a tutorial for new researchers. We classify solution paradigms—including constructive autoregressive and non-autoregressive models, local-search refinement, and hyperheuristics—and examine state representations, architectural variants (pointer networks, efficient attention, hierarchical or dual-aspect designs), and resolution strategies such as decoding heuristics and integrations with classical refiners. We also highlight hybrid models combining Transformers with CNNs, GNNs, or hierarchical decomposition, alongside training methods spanning supervised imitation and reinforcement learning. By organizing the literature around these building blocks, we clarify where Transformers excel, where classical heuristics remain essential, and how hybridization can bridge the gap. Our goal is to provide a critical roadmap and tutorial-style reference connecting classical optimization with modern Transformer-based methods. Full article

Network intrusion detection is a core component of modern cybersecurity, but it remains challenging due to highly imbalanced traffic, heterogeneous feature types, and a presence of short-term temporal dependencies in network flows. Traditional machine learning models often rely on handcrafted features and struggle with complex attack patterns, while deep learning approaches may become overly complex or difficult to interpret. In this paper, we propose a neural intrusion detection method that combines structured feature preprocessing with a compact hybrid architecture. Numerical and categorical traffic features are processed separately using robust normalisation and trainable embeddings, and then merged into an unified representation. The proposed model builds on a multi-scale feature interaction block, followed by channel-wise attention and a single bidirectional gated recurrent unit layer with attention pooling to capture short-term temporal behavior. The method is evaluated on two widely used benchmark datasets, i.e., the CIC-IDS2017 and CSE-CIC-IDS2018 dataset. Experimental results show that the proposed approach consistently outperforms the classical machine learning baselines and achieves competitive or superior performance compared to the recent deep learning methods proposed in the literature. The results confirm that the proposed architectural choices effectively capture both feature interactions and temporal patterns in network traffic. Full article

Automated electrocardiogram (ECG) arrhythmia classification remains challenging due to signal noise, inter-patient variability, and limited annotated data, which constrain the generalization of supervised learning approaches. This study presents a self-supervised ECG representation learning framework that combines contrastive pretraining with ensemble-based supervised classification. A signal-to-noise ratio criterion is applied during self-supervised pretraining to stabilize contrastive optimization, while all extracted ECG beats, including noisy segments, are retained during downstream evaluation. The learned representations are classified using a hybrid ensemble composed of convolutional encoders and tree-based models. Model evaluation follows strict patient-level partitioning with stratified 10-fold cross-validation and bootstrap-based uncertainty estimation on a held-out test set. Under this evaluation protocol, the framework achieved high beat-level performance on curated datasets (internal and external). Class-wise performance shows precision and recall values between 0.99 and 0.999 across normal, supraventricular, ventricular, fusion, and paced beat categories. External validation is conducted on independent ECG cohorts, including PTB-XL, Chapman–Shaoxing, and INCART 12-lead datasets. On these datasets, the hybrid model attains macro-F₁ scores ranging from 0.91 to 0.94, compared with standalone convolutional and handcrafted feature-based Random Forest classifiers evaluated under identical conditions. These results characterize the behavior of the proposed representation learning framework across heterogeneous patient populations and recording configurations. Full article

Accurate assessment of nitrogen content in maize leaves is crucial for scientific fertilization and environmental protection in agricultural production. Traditional nutrient diagnosis methods are inefficient, costly, and destructive, while machine learning approaches based on handcrafted features rely heavily on manual design, leading to limited generalization ability and suboptimal prediction accuracy. To address these issues, this paper proposes a convolutional neural network model named SCBI-EfficientNetV2, which adopts EfficientNetV2-S as the backbone to overcome the limitations of manual feature engineering through automatic feature extraction. Furthermore, a Spatial and Channel Synergistic Attention (SCSA) module is introduced to enhance the modeling of critical regions and informative channels, and a Bidirectional Feature Pyramid Network (BiFPN) is incorporated to achieve effective multi-scale feature fusion, thereby improving the representation of hierarchical structural features in maize leaves. Experimental results show that SCBI-EfficientNetV2 achieves a coefficient of determination (R²) of 0.9417 on the test set, representing a 5.25% improvement over the baseline model and outperforming five classical deep learning approaches. In addition, the proposed model maintains high prediction accuracy with relatively low computational cost, demonstrating good adaptability for edge deployment. This study provides a feasible solution for non-destructive intelligent diagnosis of maize nutrition and offers technical support for precision fertilization and sustainable agricultural development. Full article

As network environments become increasingly interconnected, ensuring robust cyber-security has become critical, particularly with the growing sophistication of modern cyber threats. Intrusion detection systems (IDSs) play a vital role in identifying and mitigating unauthorized or malicious activities; however, conventional machine learning-based IDSs often rely on handcrafted features and are limited in their ability to detect diverse attack types across disparate network domains. To address these limitations, this paper introduces a novel unified intrusion detection framework that implements “Structural Dualism” to integrate three heterogeneous benchmark datasets (CSE-CIC-IDS2018, NF-BoT-IoT-v2, and IoT-23) into a harmonized, protocol-agnostic representation. The framework employs a shared autoencoder architecture with dataset-specific projection layers to learn a unified latent manifold. This 15-dimensional space captures the underlying semantics of attack patterns (e.g., volumetric vs. signaling) across multiple domains, while dataset-specific decoders preserve reconstruction fidelity through alternating multi-domain training. To identify complex micro-signatures within this manifold, the framework utilizes a synergistic hybrid convolutional neural network–deep neural network (CNN–DNN) classifier, where the CNN extracts spatial latent patterns and the DNN performs global classification across twenty-five distinct classes. Class imbalance is addressed through resampling strategies such as adaptive synthetic sampling (ADASYN) and edited nearest neighbors (ENN). Experimental results demonstrate remarkable performance, achieving 99.76% accuracy for binary classification and 99.54% accuracy for multi-class classification on the merged dataset, with strong generalization confirmed on individual datasets. These findings indicate that the shared autoencoder-based CNN–DNN framework, through its unique feature alignment and spatial extraction capabilities, significantly strengthens intrusion detection across diverse and heterogeneous environments. Full article

Accurate and timely classification of skin lesions is critical for early cancer detection, yet current deep learning approaches suffer from high computational costs, limited interpretability, and poor transparency for clinical deployment. This study presents HCHS-Net, a lightweight and interpretable multimodal framework for six-class skin lesion classification on the PAD-UFES-20 dataset. The proposed framework extracts a 116-dimensional visual feature vector through three complementary handcrafted modules: a Color Module employing multi-channel histogram analysis to capture chromatic diagnostic patterns, a Haralick Module deriving texture descriptors from the gray-level co-occurrence matrix (GLCM) that quantify surface characteristics correlated with malignancy, and a Shape Module encoding morphological properties via Hu moment invariants aligned with the clinical ABCD rule. The architectural design of HCHS-Net adopts a biomimetic approach by emulating the hierarchical information processing of the human visual system and the cognitive diagnostic workflows of expert dermatologists. Unlike conventional black-box deep learning models, this framework employs parallel processing branches that simulate the selective attention mechanisms of the human eye by focusing on biologically significant visual cues such as chromatic variance, textural entropy, and morphological asymmetry. These visual features are concatenated with a 12-dimensional clinical metadata vector encompassing patient demographics and lesion characteristics, yielding a compact 128-dimensional multimodal representation. Classification is performed through an ensemble of three gradient boosting algorithms (XGBoost, LightGBM, CatBoost) with majority voting. HCHS-Net achieves 97.76% classification accuracy with only 0.25 M parameters, outperforming deep learning baselines, including VGG-16 (94.60%), ResNet-50 (94.80%), and EfficientNet-B2 (95.16%), which require 60–97× more parameters. The framework delivers an inference time of 0.11 ms per image, enabling real-time classification on standard CPUs without GPU acceleration. Ablation analysis confirms the complementary contribution of each feature module, with metadata integration providing a 2.53% accuracy gain. The model achieves perfect melanoma and nevus recall (100%) with 99.55% specificity, maintaining reliable discrimination at safety-critical diagnostic boundaries. Comprehensive benchmarking against 13 published methods demonstrates that domain-informed handcrafted features combined with clinical metadata can match or exceed deep learning fusion approaches while offering superior interpretability and computational efficiency for point-of-care deployment. Full article

Accurate and robust visual localization under changing environments remains a fundamental challenge in autonomous driving and mobile robotics. Traditional handcrafted features often degrade under long-term illumination and viewpoint variations, while recent CNN-based methods, although more robust, typically rely on coarse semantic cues and remain vulnerable to dynamic objects. In this paper, we propose a fine-grained semantics-guided feature extraction framework that adaptively selects stable keypoints while suppressing dynamic disturbances. A fine-grained semantic refinement module subdivides coarse semantic categories into stability-homogeneous sub-classes, and a dual-attention mechanism enhances local repeatability and semantic consistency. By integrating physical priors with self-supervised clustering, the proposed framework learns discriminative and reliable feature representations. Extensive experiments on the Aachen and RobotCar-Seasons benchmarks demonstrate that the proposed approach achieves state-of-the-art accuracy and robustness while maintaining real-time efficiency, effectively bridging coarse semantic guidance with fine-grained stability estimation. Quantitatively, our method achieves strong localization performance on Aachen (up to 88.1% at night under the $(0.2^{°},0.25 \mathrm{m})$ threshold) and on RobotCar-Seasons (up to 57.2%/28.4% under the same threshold for day/night), demonstrating improved robustness to seasonal and illumination changes. Full article

Driving style recognition plays a crucial role in improving the operational safety, fuel efficiency, and intelligent control of commercial vehicles. Under real-world driving conditions, Controller Area Network (CAN) bus data from commercial vehicles simultaneously contain rapid transient variations induced by pedal and braking operations, as well as long-term behavioral trends reflecting driving habits, exhibiting pronounced multi-temporal characteristics. In addition, such data are typically affected by high noise levels, high dimensionality, and highly variable operating conditions, which makes it difficult for methods relying on single-scale features or handcrafted rules difficult to maintain robust and stable performance in complex scenarios. To address these challenges, this paper proposes a driving style classification network, termed the Multi-Scale Convolution and Efficient Channel Attention Network (MSCA-Net). By employing parallel convolutional branches with different temporal receptive fields, the proposed network is able to capture fast driver responses, local temporal dependencies, and long-term behavioral evolution, enabling unified modeling of cross-scale temporal patterns in driving behavior. Meanwhile, the Efficient Channel Attention mechanism adaptively emphasizes CAN signal channels that are highly relevant to driving style discrimination, thereby enhancing the discriminative capability and robustness of the learned feature representations. Experiments conducted on real-world multi-dimensional CAN time-series data collected from commercial vehicles demonstrate that the proposed MSCA-Net achieves improved classification performance in driving style recognition. Furthermore, the potential application of the recognized driving styles in adaptive Automated Manual Transmission shift strategy adjustment is discussed, providing a feasible engineering pathway toward behavior-aware intelligent control of commercial vehicle powertrains. Full article

Agent-based models of financial markets often rely on a small set of hand-crafted trading rules, making it difficult to relate model heterogeneity to information that is observable in market data. We take a different standpoint and treat the design of heterogeneity as a representation problem under limited observations. In our framework, each agent’s decision rule is implemented as a neural-network mapping from recent price histories to order decisions, trained on historical index or stock price series. To describe and manipulate heterogeneity without pre-assigning mechanism labels, we introduce Fit Quality (FQ), an ex post effect-defined index summarizing how strongly each learned rule fits the price patterns it was trained on, and we use FQ solely as a coordinate for organizing agent populations and constructing controlled changes in agent composition, rather than as a measure of forecasting skill or economic performance. Using this representation, we examine whether simulations can reproduce several stylized features of return series. We also perform simple ablation experiments to assess how far the observed properties depend on the data-trained decision rules rather than on the market mechanism alone. Taken together, the framework is intended as a step toward more data-linked, representation-conscious agent-based models, in which alternative ways of organizing heterogeneity can be compared within a common market environment. Full article