Search Results (1,697)

Small and medium-sized enterprises (SMEs) chronically face financing frictions. While supply chain finance (SCF) can help, reliable credit risk assessment in SCF is hindered by redundant features, heterogeneous data sources, small samples, and class imbalance. Using 360 A-share–listed SMEs from 2019–2023, we build a 77-indicator, multidimensional system covering SME and core-firm financials, supply chain stability, and macroeconomic conditions. To reduce dimensionality and remove low-contribution variables, feature selection is performed via a genetic algorithm enhanced LightGBM (GA-LightGBM). To mitigate class imbalance, we employ TabDDPM for data augmentation, yielding consistent improvements in downstream performance. For modeling, we propose a two-stage predictive framework that integrates TabNet-based feature engineering with a stacking ensemble (TabNet-Stacking). In our experiments, TabNet-Stacking outperforms strong machine-learning baselines in accuracy, recall, F1 score, and AUC. Full article

Background: Multimodal Deep learning has emerged as a crucial method for automated patient-specific quality assurance (PSQA) in radiotherapy research. Integrating image-based dose matrices with tabular plan complexity metrics enables more accurate prediction of quality indicators, including the Gamma Passing Rate (GPR) and dose difference (DD). However, modality imbalance remains a significant challenge, as tabular encoders often dominate training, suppressing image encoders and reducing model robustness. This issue becomes more pronounced under task heterogeneity, with GPR prediction relying more on tabular data, whereas dose difference prediction (DDP) depends heavily on image features. Methods: We propose BMMQA (Balanced Multi-modal Quality Assurance), a novel framework that achieves modality balance by adjusting modality-specific loss factors to control convergence dynamics. The framework introduces four key innovations: (1) task-specific fusion strategies (softmax-weighted attention for GPR regression and spatial cascading for DD prediction); (2) a balancing mechanism supported by Shapley values to quantify modality contributions; (3) a fast network forward mechanism for efficient computation of different modality combinations; and (4) a modality-contribution-based task weighting scheme for multi-task multimodal learning. A large-scale multimodal dataset comprising 1370 IMRT plans was curated in collaboration with Peking Union Medical College Hospital (PUMCH). Results: Experimental results demonstrate that, under the standard 2%/3 mm GPR criterion, BMMQA outperforms existing fusion baselines. Under the stricter 2%/2 mm criterion, it achieves a 15.7% reduction in mean absolute error (MAE). The framework also enhances robustness in critical failure cases (GPR < 90%) and achieves a peak SSIM of 0.964 in dose distribution prediction. Conclusions: Explicit modality balancing improves predictive accuracy and strengthens clinical trustworthiness by mitigating overreliance on a single modality. This work highlights the importance of addressing modality imbalance for building trustworthy and robust AI systems in PSQA and establishes a pioneering framework for multi-task multimodal learning. Full article

Early detection of network traffic anomalies is critical for cybersecurity, as a single compromised host can cause data breaches, reputational damage, and operational disruptions. However, traditional systems based on signatures and static rules are often ineffective against sophisticated and evolving threats. This study proposes a hybrid deep learning architecture for proactive anomaly detection in local and metropolitan networks. The dataset underwent an extensive process of cleaning, transformation, and feature selection, including normalization of numerical fields, encoding of ordinal variables, and derivation of behavioral metrics. The EFMS-KMeans algorithm was applied to pre-label traffic as normal or anomalous by estimating dense centers and computing centroid distances, enabling the training of a sequential CNN-GRU network, where the CNN captures spatial patterns and the GRU models temporal dependencies. To address class imbalance, the SMOTE technique was integrated, and the loss function was adjusted to improve training stability. Experimental results show a substantial improvement in accuracy and generalization compared to conventional approaches, validating the effectiveness of the proposed method for detecting anomalous traffic in dynamic and complex network environments. Full article

Progressive Fibrosing Interstitial Lung Disease (PF-ILD) is a severe phenotype of Interstitial Lung Disease (ILD) with a poor prognosis, typically requiring prolonged clinical observation and multiple CT examinations for diagnosis. Such requirements delay early detection and treatment initiation. To enable earlier identification of PF-ILD, we propose ILD-Slider, a parameter-efficient and lightweight deep learning framework that enables accurate PF-ILD identification from a limited number of CT slices. ILD-Slider introduces anatomy-based position markers (PMs) to guide the selection of representative slices (RSs). A PM extractor, trained via a multi-class classification model, achieves high PM detection accuracy despite severe class imbalance by leveraging a peak slice mining (PSM)-based strategy. Using the PM extractor, we automatically select three, five, or nine RSs per case, substantially reducing computational cost while maintaining diagnostic accuracy. The selected RSs are then processed by a slice-level 3D Adapter (Slider) for PF-ILD identification. Experiments on 613 cases from The University of Osaka Hospital (UOH) and the National Hospital Organization Osaka Toneyama Medical Center (OTMC) demonstrate the effectiveness of ILD-Slider, achieving an AUPRC of 0.790 (AUROC 0.847) using only five automatically extracted RSs. ILD-Slider further validates the feasibility of diagnosing PF-ILD from non-contiguous slices, which is particularly valuable for real-world and public datasets where contiguous volumes are often unavailable. These results highlight ILD-Slider as a practical and efficient solution for early PF-ILD identification. Full article

Background/Objectives: Machine learning has been suggested as a way to improve how we predict anesthesia-related complications after surgery. However, many studies report overly optimistic results due to issues like data leakage and not fully using information from clinical notes. This study provides a transparent comparison of different machine learning models using both structured data and preoperative notes, with a focus on avoiding data leakage and involving clinicians throughout. We show how high reported metrics in the literature can result from methodological pitfalls and may not be clinically meaningful. Methods: We used a dataset containing both structured patient and surgery information and preoperative clinical notes. To avoid data leakage, we excluded any variables that could directly reveal the outcome. The data was cleaned and processed, and information from clinical notes was summarized into features suitable for modeling. We tested a range of machine learning methods, including simple, tree-based, and modern language-based models. Models were evaluated using a standard split of the data and cross-validation, and we addressed class imbalance with sampling techniques. Results: All models showed only modest ability to distinguish between patients with and without complications. The best performance was achieved by a simple model using both structured and summarized text features, with an area under the curve of 0.644 and accuracy of 60%. Other models, including those using advanced language techniques, performed similarly or slightly worse. Adding information from clinical notes gave small improvements, but no single type of data dominated. Overall, the results did not reach the high levels reported in some previous studies. Conclusions: In this analysis, machine learning models using both structured and unstructured preoperative data achieved only modest predictive performance for postoperative complications. These findings highlight the importance of transparent methodology and clinical oversight to avoid data leakage and inflated results. Future progress will require better control of data leakage, richer data sources, and external validation to develop clinically useful prediction tools. Full article

Ensuring secure and reliable communication in Vehicular Ad hoc Networks (VANETs) is critical for safe transportation systems. This paper presents Vehicular Misbehavior Network (VeMisNet), a deep learning framework for detecting misbehaving vehicles, with primary contributions in systematic feature engineering and scalability analysis. VeMisNet introduces domain-informed spatiotemporal features—including DSRC neighborhood density, inter-message timing patterns, and communication frequency analysis—derived from the publicly available VeReMi Extension Dataset. The framework evaluates Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM architectures across dataset scales from 100 K to 2 M samples, encompassing all 20 attack categories. To address severe class imbalance (59.6% legitimate vehicles), VeMisNet applies SMOTE post train–test split, preventing data leakage while enabling balanced evaluation. Bidirectional LSTM with engineered features achieves 99.81% accuracy and F1-score on 500 K samples, with remarkable scalability maintaining >99.5% accuracy at 2 M samples. Critical metrics include 0.19% missed attack rates, under 0.05% false alarms, and 41.76 ms inference latency. The study acknowledges important limitations, including reliance on simulated data, single-split evaluation, and potential adversarial vulnerability. Domain-informed feature engineering provides 27.5% relative improvement over dimensionality reduction and 22-fold better scalability than basic features. These results establish new VANET misbehavior detection benchmarks while providing honest assessment of deployment readiness and research constraints. Full article

As universities become increasingly open, campuses are no longer only places for study and daily life for students and faculty, but also essential spaces for public visits and cultural identity. Traditional perception evaluation methods that rely on manual surveys are limited by sample size and subjective bias, making it challenging to reveal differences in experiences between groups (students/visitors) and the complex relationships between spatial elements and perceptions. This study uses a comprehensive open university in China as a case study to address this. It proposes a research framework that combines street-view image semantic segmentation, perception survey scores, and interpretable machine learning with sample augmentation. First, full-sample modeling is used to identify key image semantic features influencing perception indicators (nature, culture, aesthetics), and then to compare how students and visitors differ in their perceptions and preferences across campus spaces. To overcome the imbalance in survey data caused by group–space interactions, the study applies the CTGAN method, which expands minority samples through conditional generation while preserving distribution authenticity, thereby improving the robustness and interpretability of the model. Based on this, attribution analysis with an interpretable decision tree algorithm further quantifies semantic features’ contribution, direction, and thresholds to perceptions, uncovering heterogeneity in perception mechanisms across groups. The results provide methodological support for perception evaluation of campus functional zones and offer data-driven, human-centered references for campus planning and design optimization. Full article

As network automation and self-organizing networks (SONs) rapidly evolve, edge devices increasingly demand lightweight, real-time, and high-precision classification algorithms to support critical tasks such as traffic identification, intrusion detection, and fault diagnosis. In recent years, cross-entropy (CE) loss has been widely adopted in deep learning classification tasks due to its computational efficiency and ease of optimization. However, traditional CE methods primarily focus on class separability without explicitly constraining intra-class compactness and inter-class boundaries in the feature space, thereby limiting their generalization performance on complex classification tasks. To address this issue, we propose a novel classification loss framework—Contrastive Geometric Cross-Entropy (CGCE). Without incurring additional computational or memory overhead, CGCE explicitly introduces learnable class representation vectors and constructs the loss function based on the dot-product similarity between features and these class representations, thus explicitly reinforcing geometric constraints in the feature space. This mechanism effectively enhances intra-class compactness and inter-class separability. Theoretical analysis further demonstrates that minimizing the CGCE loss naturally induces clear and measurable geometric class boundaries in the feature space, a desirable property absent from traditional CE methods. Furthermore, CGCE can seamlessly incorporate the prior knowledge of pretrained models, converging rapidly within only a few training epochs (for example, on the CIFAR-10 dataset using the ViT model, a single training epoch is sufficient to reach 99% of the final training accuracy.) Experimental results on both text and image classification tasks show that CGCE achieves accuracy improvements of up to 2% over traditional CE methods, exhibiting stronger generalization capabilities under challenging scenarios such as class imbalance, few-shot learning, and noisy labels. These findings indicate that CGCE has significant potential as a superior alternative to traditional CE methods. Full article

Open-vocabulary object detection in remote sensing aims to detect novel categories not seen during training, which is crucial for practical aerial image analysis applications. While some approaches accomplish this task through large-scale data construction, such methods incur substantial annotation and computational costs. In contrast, we focus on efficient utilization of limited datasets. However, existing methods such as CastDet struggle with inefficient data utilization and class imbalance issues in pseudo-label generation for novel categories. We propose an enhanced open-vocabulary detection framework that addresses these limitations through two key innovations. First, we introduce a selective masking strategy that enables direct utilization of partially annotated images by masking base category regions in teacher model inputs. This approach eliminates the need for strict data separation and significantly improves data efficiency. Second, we develop a dynamic frequency-based class weighting that automatically adjusts category weights based on real-time pseudo-label statistics to mitigate class imbalance issues. Our approach integrates these components into a student–teacher learning framework with RemoteCLIP for novel category classification. Comprehensive experiments demonstrate significant improvements on both datasets: on VisDroneZSD, we achieve 42.7% overall mAP and 41.4% harmonic mean, substantially outperforming existing methods. On DIOR dataset, our method achieves 63.7% overall mAP with 49.5% harmonic mean. Our framework achieves more balanced performance between base and novel categories, providing a practical and data-efficient solution for open-vocabulary aerial object detection. Full article

Specific emitter identification (SEI), which classifies radio transmitters by extracting hardware-intrinsic radio frequency fingerprints (RFFs), faces critical challenges in noise robustness, generalization under limited training data and class imbalance. To address these limitations, we propose adaptive deep ensemble learning (ADEL)—a framework that integrates heterogeneous neural networks including convolutional neural networks (CNN), multilayer perception (MLP) and transformer for hierarchical feature extraction. Crucially, ADEL also adopts adaptive weighted predictions of the three base classifiers based on reconstruction errors and hybrid losses for robust classification. The methodology employs (1) three heterogeneous neural networks for robust feature extraction; (2) the hybrid losses refine feature space structure and preserve feature integrity for better feature generalization; and (3) collaborative decision-making via adaptive weighted reconstruction errors of the base learners for precise inference. Extensive experiments are performed to validate the effectiveness of ADEL. The results indicate that the proposed method significantly outperforms other competing methods. ADEL establishes a new SEI paradigm through robust feature extraction and adaptive decision integrity, enabling potential deployment in space target identification and situational awareness under limited training samples and imbalanced classes conditions. Full article

Micro-expressions are facial movements with extremely short duration and small amplitude, which can reveal an individual’s potential true emotions and have important application value in public safety, medical diagnosis, psychotherapy and business negotiations. Since micro-expressions change rapidly and are difficult to detect, manual recognition is a significant challenge, so the development of automatic recognition systems has become a research hotspot. This paper reviews the development history and research status of micro-expression recognition and systematically analyzes the two main branches of micro-expression analysis: micro-expression detection and micro-expression recognition. In terms of detection, the methods are divided into three categories based on time features, feature changes and deep features according to different feature extraction methods; in terms of recognition, traditional methods based on texture and optical flow features, as well as deep learning-based methods that have emerged in recent years, including motion unit, keyframe and transfer learning strategies, are summarized. This paper also summarizes commonly used micro-expression datasets and facial image preprocessing techniques and evaluates and compares mainstream methods through multiple experimental indicators. Although significant progress has been made in this field in recent years, it still faces challenges such as data scarcity, class imbalance and unstable recognition accuracy. Future research can further combine multimodal emotional information, enhance data generalization capabilities, and optimize deep network structures to promote the widespread application of micro-expression recognition in practical scenarios. Full article

Hospital fraud detection has often relied on periodic audits that miss evolving, internet-mediated patterns in electronic claims. An artificial intelligence and machine learning pipeline is being developed that is leakage-safe, imbalance aware, and aligned with operational capacity for large healthcare datasets. The preprocessing stack integrates four tables, engineers 13 features, applies imputation, categorical encoding, Power transformation, Boruta selection, and denoising autoencoder representations, with class balancing via SMOTE-ENN evaluated inside cross-validation folds. Eight algorithms are compared under a fraud-oriented composite productivity index that weighs recall, precision, MCC, F1, ROC-AUC, and G-Mean, with per-fold threshold calibration and explicit reporting of Type I and Type II errors. Multilayer perceptron attains the highest composite index, while CatBoost offers the strongest control of false positives with high accuracy. SMOTE-ENN provides limited gains once representations regularize class geometry. The calibrated scores support prepayment triage, postpayment audit, and provider-level profiling, linking alert volume to expected recovery and protecting investigator workload. Situated in the Future Internet context, this work targets internet-mediated claim flows and web-accessible provider registries. Governance procedures for drift monitoring, fairness assessment, and change control complete an internet-ready deployment path. The results indicate that disciplined preprocessing and evaluation, more than classifier choice alone, translate AI improvements into measurable economic value and sustainable fraud prevention in digital health ecosystems. Full article

Bitcoin transaction anomaly detection is essential for maintaining financial market stability. A significant challenge is capturing the dynamically evolving transaction patterns within transaction networks. Dynamic graph models are effective for characterizing the temporal evolution of transaction systems. However, current methods struggle to mine long-range temporal dependencies and address the class imbalance caused by the scarcity of abnormal samples. To address these issues, we propose a novel approach, the Bidirectional EvolveGCN with Class-Balanced Learning Network (Balanced-BiEGCN), for Bitcoin transaction anomaly detection. This model integrates two key components: (1) a bidirectional temporal feature fusion mechanism (Bi-EvolveGCN) that enhances the capture of long-range temporal dependencies and (2) a Sample Class Transformation (CSCT) classifier that generates difficult-to-distinguish abnormal samples to balance the positive and negative class distribution. The generation of these samples is guided by two loss functions: the adjacency distance adaptive loss function and the symmetric space adjustment loss function, which optimize the spatial distribution and confusion of abnormal samples. Experimental results on the Elliptic dataset demonstrate that Balanced-BiEGCN outperforms existing baseline methods in anomaly detection. Full article

Background: Heart disease continues to be one of the foremost causes of mortality worldwide, emphasizing the urgent need for reliable and early diagnostic tools. Accurate prediction methods can support timely interventions and improve patient outcomes. Methods: This study presents the development and comparative evaluation of multiple machine learning models for heart disease prediction using a structured clinical dataset. Algorithms such as Logistic Regression, Random Forest, Support Vector Machine (SVM), XGBoost, and Deep Neural Networks were implemented. Additionally, a hybrid ensemble model combining XGBoost and SVM was proposed. Models were evaluated using key performance metrics including accuracy, precision, recall, and F1-score. Results: Among all models, the proposed hybrid model demonstrated the best performance, achieving an accuracy of 89.3%, a precision of 0.90, recall of 0.91, and an F1-score of 0.905, and outperforming all individual classifiers. These results highlight the benefits of combining complementary algorithms for improved generalization and diagnostic reliability. Conclusions: The findings underscore the effectiveness of ensemble and deep learning techniques in addressing key challenges such as data imbalance, feature selection, and model interpretability. The proposed hybrid model shows significant potential as a clinical decision-support tool, contributing to enhanced diagnostic accuracy and supporting medical professionals in real-world settings. Full article

Cardiac arrhythmias are among the leading causes of morbidity and mortality worldwide, and accurate classification of electrocardiogram (ECG) beats is critical for early diagnosis and follow-up. Supervised deep learning is effective but requires abundant labels and substantial computation, limiting practicality. We propose a simple, efficient framework that learns self-supervised ECG representations with SimCLR and uses a lightweight Multi-Layer Perceptron (MLP) for classification. Beat-centered 300-sample segments from MIT-BIH Arrhythmia are used, and imbalance is mitigated via SMOTE. Framed from a symmetry/asymmetry perspective, we exploit a symmetric beat window (150 pre- and 150 post-samples) to encourage approximate translation invariance around the R-peak, while SimCLR jitter/scale augmentations further promote invariance in the learned space; conversely, arrhythmic beats are interpreted as symmetry-breaking departures that aid discrimination. The proposed approach achieves robust performance: 97.2% overall test accuracy, 97.2% macro-average F1-score, and AUC > 0.997 across five beat classes. Notably, the challenging atrial premature beat (A) attains 94.1% F1, indicating effective minority-class characterization with low computation. These results show that combining SMOTE with SimCLR-based representations yields discriminative features and strong generalization under symmetry-consistent perturbations, highlighting potential for real-time or embedded healthcare systems. Full article