Search Results (1,687)

Accurate detection of oil and gas (O&G) facilities in high-resolution remote sensing imagery is critical for infrastructure surveillance and sustainable resource management, yet conventional detectors struggle with severe class imbalance, extreme scale variation, and arbitrary orientation. In this work, we propose OGF Oriented R-CNN (Oil and Gas Facility Detection Oriented Region-based Convolutional Neural Network), an enhanced oriented detection model derived from Oriented R-CNN that integrates three improvements: (1) O&G Loss Function, (2) Class-Aware Hard Example Mining (CAHEM) module, and (3) Feature Pyramid Network with Feature Enhancement Attention (FPNFEA). Working in synergy, they resolve the coupled challenges more effectively than any standalone fix and do so without relying on rigid one-to-one matching between modules and individual issues. Evaluated on the O&G facility dataset comprising 3039 high-resolution images annotated with rotated bounding boxes across three classes (well sites: 3006, industrial and mining lands: 692, drilling: 244), OGF Oriented R-CNN achieves a mean average precision (mAP) of 82.9%, outperforming seven state-of-the-art (SOTA) models by margins of up to 27.6 percentage points (pp) and delivering a cumulative gain of +10.5 pp over Oriented R-CNN. 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

Credit card fraud detection remains a critical challenge for financial institutions, particularly due to extreme class imbalance and the continuously evolving nature of fraudulent behavior. This study investigates two complementary approaches: anomaly detection based on multivariate normal distribution and deep reinforcement learning using a Deep Q-Network. While anomaly detection effectively identifies deviations from normal transaction patterns, its static nature limits adaptability in real-time systems. In contrast, the DQN reinforcement learning model continuously learns from every transaction, autonomously adapting to emerging fraud strategies. Experimental results demonstrate that, although initial performance metrics of the DQN are modest compared to anomaly detection, its capacity for online learning and policy refinement enables long-term improvement and operational scalability. This work highlights reinforcement learning as a highly promising paradigm for dynamic, high-volume fraud detection, capable of evolving with the environment and achieving near-optimal detection rates over time. Full article

As edge computing becomes increasingly central to modern digital infrastructure, it also creates opportunities for sophisticated malware attacks that traditional security systems struggle to address. This study proposes a natural language processing (NLP) framework integrated with ensemble learning into next-generation firewalls (NGFWs) to detect and mitigate malware attacks in edge computing environments. The approach leverages unstructured threat intelligence (e.g., cybersecurity reports, logs) by applying NLP techniques, such as TF-IDF vectorization, to convert textual data into structured insights. This process uncovers hidden patterns and entity relationships within system logs. By combining Random Forest (RF) and Logistic Regression (LR) in a soft voting ensemble, the proposed model achieves 95% accuracy on a cyber threat intelligence dataset augmented with synthetic data to address class imbalance, and 98% accuracy on the CSE-CIC-IDS2018 dataset. The study was validated using ANOVA to assess statistical robustness and confusion matrix analysis, both of which confirmed low error rates. The system enhances detection rates and adaptability, providing a scalable defense layer optimized for resource-constrained, latency-sensitive edge environments. Full article

Accurate precipitation forecasting is paramount for water security and disaster mitigation, yet it remains formidable due to atmospheric stochasticity and the inherent class imbalance in rainfall datasets. This study proposes an integrated “architecture-feature-augmentation” framework to circumvent these limitations. Through a systematic evaluation of CNN-LSTM and Transformer architectures, we delineate distinct performance profiles: The Transformer model, when coupled with feature engineering and physics-informed augmentation, yields a peak F1-score of 0.1429, marking the optimal configuration for harmonizing precision and recall. Conversely, CNN-LSTM demonstrates superior robustness in extreme event detection, consistently maintaining high recall rates (up to 0.90) across diverse scenarios. We identify feature engineering as a critical performance modulator, substantially bolstering CNN-LSTM’s baseline metrics while enabling the Transformer to realize its maximum predictive capacity. Although synthetic oversampling techniques—such as SMOTE and GAN—effectively extend the detection range for heavy precipitation, physics-informed augmentation provides the most consistent performance gains, particularly in multi-class contexts. We conclude that the Transformer, augmented by physical constraints, is the optimal candidate for high-precision requirements, whereas CNN-LSTM, integrated with synthetic augmentation, offers a more sensitive alternative for early warning systems prioritizing recall. These findings provide empirical guidance for advancing extreme weather preparedness and strategic water resource management. Full article

The paper focuses on automated diagnosis of retinal diseases, particularly Age-related Macular Degeneration (AMD) and diabetic retinopathy (DR), using optical coherence tomography (OCT), while addressing three key challenges: disease comorbidity, severe class imbalance, and the lack of strictly paired OCT and fundus data. We propose a hierarchical modular deep learning system designed for multi-label OCT screening with conditional routing to specialized staging modules. To enable DR staging when fundus images are unavailable, we use cross-modal alignment between OCT and fundus representations. This approach involves training a latent bridge that projects OCT embeddings into the fundus feature space. We enhance clinical reliability through per-class threshold calibration and implement quality control checks for OCT-only DR staging. Experiments demonstrate robust multi-label performance (macro-F1 $=0.989\pm 0.006$ after per-class threshold calibration) and reliable calibration (ECE $=2.1\pm 0.4\%$), and OCT-only DR staging is feasible in 96.1% of cases that meet the quality control criterion. Full article

Background: Radiomics can provide quantitative descriptors of tumor phenotype, but translation is often limited by feature instability across scanners and protocols. We aimed to develop and internally validate a protocol-specific CT-radiomics model using preoperative imaging to predict 5-year recurrence in patients with stage I lung adenocarcinoma after complete surgical resection. Methods: The retrospective study included 270 patients with completely resected stage I lung adenocarcinoma from January 2010–December 2021, among whom 23 (8.5%) experienced recurrence within five years. Radiomic features were extracted from routine preoperative CT scans. After preprocessing to remove highly constant and highly correlated features, the Synthetic Minority Over-sampling Technique addressed class imbalance in the training set. Recursive Feature Elimination identified the most predictive radiomic features. An XGBoost classifier was trained using optimized hyperparameters identified through RandomizedSearchCV with cross-validation. Model performance was evaluated using the ROC curve and predictive metrics. Results: Five radiomic features differed significantly between recurrence groups (p = 0.007 to <0.001): Shape Sphericity, first-order 90Percentile, GLCM Autocorrelation, GLCM Cluster Shade, and GLDM Large Dependence Low Gray Level Emphasis. The radiomics model showed excellent discriminatory ability with AUC values of 0.99 (95% CI: 0.98–1.00), 0.97 (95% CI: 0.91–1.00), and 0.96 (95% CI: 0.85–1.00) on the training, validation, and test sets, respectively. On the test set, the model achieved sensitivity of 100% (95% CI: 51–100%), specificity of 94% (95% CI: 81–98%), PPV of 67% (95% CI: 30–90%), NPV of 100% (95% CI: 90–100%), and overall accuracy of 95% (95% CI: 83–99%). Conclusions: Under protocol-homogeneous imaging conditions, CT radiomics accurately predicted recurrence in patients with completely resected stage I lung adenocarcinoma. External multi-vendor validation is needed before broader deployment. Full article

The ceramic defect detection technology based on deep learning suffers from the problems of scarce rare defect samples and class imbalance. However, the current deep generative image augmentation techniques are limited when applied to the task of augmenting rare ceramic defects due to issues such as uneven image brightness and insufficient features of small-sized defects, resulting in poor image quality and limited improvement in detection results. This paper proposes a ceramic rare defect image augmentation method based on TC-CycleGAN. TC-CycleGAN is based on the CycleGAN framework and optimizes the generator and discriminator structures to make them more suitable for ceramic defect features, thereby improving the quality of generated images. The generator is TC-UNet, which introduces the scSE and DehazeFormer modules on the basis of UNet, effectively enhancing the model’s ability to learn the subtle defect features on the ceramic surface; the discriminator is the TC-PatchGAN architecture, which replaces the original BatchNorm module with the ContraNorm module, effectively increasing the discriminator’s sensitivity to the representation of tiny ceramic defect features and enhancing the diversity of generated images. The image quality assessment experiments show that the method proposed in this paper significantly improves the quality of generated defective images. For the concave type images, the FID and KID values have decreased by 49% and 73%, respectively, while for the smoke stains type images, the FID and KID values have decreased by 57% and 63% respectively. The further defect detection experiments results show that when using the data set expanded by the method in this paper for training, the recognition accuracy of the detection model for rare defects has significantly improved. The detection accuracy of the concave and smoke stains types of defects has increased by 1.2% and 3.9% respectively. Full article

Non-invasive and intelligent technologies have been utilized to monitor agricultural systems in real time, facilitating expedient decision-making and the reduction in animal stress in diverse climatic conditions. The objective of this study was to develop a deep learning supervised model to classify Nelore cattle (Bos indicus) into two groups: those in comfort and those under thermal stress. Thirty cattle, aged between 18 and 20 months, were evaluated between June and December 2023, resulting in 676 samples collected across four daily periods (6:00, 12:00, 18:00, and 24:00). Biotic variables included rectal temperature (RT) and respiratory rate (RR), while abiotic variables included air temperature (AT) and relative humidity (RH). The neural network model exhibited an accuracy and recall of 72% but a low specificity of 42%. These metrics indicate that while the model is effective in detecting stress situations, it faces challenges in correctly identifying animals in thermal comfort, likely due to class imbalance and the need for additional input features to capture environmental adaptability. Consequently, it can be posited that supervised learning models are valuable tools for precision livestock farming, provided that discriminatory limitations are mitigated by refining input characteristics and data balancing. Full article

Hyperspectral image (HSI) classification is pivotal for remote sensing applications, including environmental monitoring, precision agriculture, and urban land-use analysis. However, its accuracy is often limited by scarce labeled data, class imbalance, and domain discrepancies between standard RGB and HSI imagery. Although recent deep learning approaches, such as 3D convolutional neural networks (3D-CNNs), transformers, and generative adversarial networks (GANs), show promise, they struggle with spectral fidelity, computational efficiency, and cross-domain adaptation in label-scarce scenarios. To address these challenges, we propose the Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation (TGDHTL) framework. This framework integrates domain-adaptive alignment of RGB and HSI data, efficient synthetic data generation, and multi-scale spectral–spatial modeling. Specifically, a lightweight transformer, guided by Maximum Mean Discrepancy (MMD) loss, aligns feature distributions across domains. A class-conditional diffusion model generates high-quality samples for underrepresented classes in only 15 inference steps, reducing labeled data needs by approximately 25% and computational costs by up to 80% compared to traditional 1000-step diffusion models. Additionally, a Multi-Scale Stripe Attention (MSSA) mechanism, combined with a Graph Convolutional Network (GCN), enhances pixel-level spatial coherence. Evaluated on six benchmark datasets including HJ-1A and WHU-OHS, TGDHTL consistently achieves high overall accuracy (e.g., 97.89% on University of Pavia) with just 11.9 GFLOPs, surpassing state-of-the-art methods. This framework provides a scalable, data-efficient solution for HSI classification under domain shifts and resource constraints. Full article

The Altai Mountains rank among the world’s most notable and valuable archaeological regions. Within the sprawling Altai Mountains area, burial mounds (kurgans) of past civilizations, which are sometimes well preserved in permafrost, are a particularly precious trove of archaeological insights. This study investigates the application of deep learning-based object detection techniques for automatic kurgan identification in high-resolution satellite imagery. We compare the performance of various object detection methods utilizing both convolutional neural network and Transformer backbones. Our results validate the effectiveness of different approaches, especially with larger models, in the challenging task of detecting small archaeological structures. Techniques addressing the class imbalance can further improve performance of off-the-shelf methods. These findings demonstrate the feasibility of employing deep learning techniques to automate kurgan identification, which can improve archaeological surveying processes. It suggests the potential of deep learning technology for constructing a comprehensive inventory of Altai Mountain kurgans, particularly relevant in the context of global warming and archaeological site preservation. Full article

Insider threats remain a serious concern for organisations in both public and private sectors. Detecting anomalous behaviour in enterprise environments is critical for preventing insider incidents. While many prior studies demonstrate promising results using deep learning on offline datasets, few address real-time operationalisation or calibrated alert control within a Security Information and Event Management (SIEM) workflow. This paper presents a SIEM-integrated prototype that fuses the Computer Emergency Response Team Insider Threat Test Dataset (CERT) enterprise logs (Logon, Device, HTTP, and Email) with behavioural biometrics from the Balabit mouse dynamics dataset. Per-modality one-dimensional convolutional neural network (1D CNN) branches are trained independently using imbalance-aware strategies, including downsampling, class weighting, and focal loss. A unified 20 × N feature schema ensures train–serve parity and consistent feature validation during live inference. Post-training calibration using Platt and isotonic regression enables analyst-controlled threshold tuning and stable alert budgeting inside the SIEM. The models are deployed in Splunk’s Machine Learning Toolkit (MLTK), where dashboards visualise anomaly timelines, risky users or hosts, and cross-stream overlaps. Evaluation emphasises operational performance, precision–recall balance, calibration stability, and throughput rather than headline accuracy. Results show calibrated, controllable alert volumes: for Device, precision ≈0.70 at recall ≈0.30 (PR-AUC = 0.468, ROC-AUC = 0.949); for Logon, ROC-AUC = 0.936 with an ultra-low false-positive rate at a conservative threshold. Batch CPU inference sustains ≈70.5 k windows/s, confirming real-time feasibility. This study’s main contribution is to demonstrate a calibrated, multi-modal CNN framework that integrates directly within a live SIEM pipeline. It provides a reproducible path from offline anomaly detection research to Security Operations Centre (SOC)-ready deployment, bridging the gap between academic models and operational Cybersecurity practice. Full article

Stress is a pervasive global health concern that adversely contributes to morbidity and reduced productivity, yet it often remains unquantified due to its subjective and variant presentation. Although artificial intelligence offers an encouraging path toward automated monitoring of mental states, current state-of-the-art approaches are challenged by the reliance on single-source data, sparsity of labeled samples, and significant class imbalance. This paper proposes NeuroStrainSense, a novel deep multimodal stress detection model that integrates three complementary datasets—WESAD, SWELL-KW, and TILES—through a Transformer-based feature fusion architecture combined with a Variational Autoencoder for generative data augmentation. The Transformer architecture employs four encoder layers with eight multi-head attention heads and a hidden dimension of 512 to capture complex inter-modal dependencies across physiological, audio, and behavioral modalities. Our experiments demonstrate that NeuroStrainSense achieves a state-of-the-art performance with accuracies of 87.1%, 88.5%, and 89.8% on the respective datasets, with F1-scores exceeding 0.85 and AUCs greater than 0.89, representing improvements of 2.6–6.6 percentage points over existing baselines. We propose a robust evaluation framework that quantifies discrimination among stress types through clustering validity metrics, achieving a Silhouette Score of 0.75 and Intraclass Correlation Coefficient of 0.76. Comprehensive ablation experiments confirm the utility of each modality and the VAE augmentation module, with physiological features contributing most significantly (average performance decrease of 5.8% when removed), followed by audio (2.8%) and behavioral features (2.1%). Statistical validation confirms all findings at the p < 0.01 significance level. Beyond binary classification, the model identifies five clinically relevant stress profiles—Cognitive Overload, Burnout, Acute Stress, Psychosomatic, and Low-Grade Chronic—with an expert concordance of Cohen’s κ = 0.71 (p < 0.001), demonstrating the strong ecological validity for personalized well-being and occupational health applications. External validation on the MIT Reality Mining dataset confirms the generalizability with minimal performance degradation (accuracy: 0.785, F1-score: 0.752, AUC: 0.849). This work underlines the potential of integrated multimodal learning and demographically aware generative AI for continuous, precise, and fair stress monitoring across diverse populations and environmental contexts. Full article

With the widespread deployment of the Advanced Metering Infrastructure (AMI) in Power Industrial Control Systems (PICS), a significant and inherent property of network traffic data is its pronounced class imbalance. The continuous emergence of new types of cyberattacks significantly limits the detection accuracy of Intrusion Detection Systems (IDS). To overcome the limitations of traditional methods—particularly their poor adaptability in complex conditions and vulnerability to emerging threats—this paper introduces a novel hybrid intrusion detection framework. This framework synergistically combines data augmentation and a discriminative classification model for improved performance. Within this framework, a Multi-feature Constrained Conditional Generative Adversarial Network (MC-CGAN) is proposed. Its multi-feature constraint module (MC) preserves protocol-related invariant features, while the CGAN is responsible for conditionally generating the remaining continuous features based on class labels. By preserving the core semantic information of samples, this method reduces the risk of generating unrealistic data and decreases computational overhead. Furthermore, we develop ADS-Net, a lightweight Convolutional Neural Network that not only replaces traditional convolutions with depth-wise separable ones for efficiency, but also incorporates an attention mechanism to adaptively weight feature channels, thus improving discriminative focus. Extensive experiments demonstrate that, under conditions of extreme data imbalance, the proposed hybrid framework can generate industrially valid synthetic data while achieving accurate intrusion detection with an accuracy of 98.35%. Full article

In nuclear power plant fault diagnosis, traditional machine learning models (e.g., SVM and KNN) require full retraining on the entire dataset whenever new fault categories are introduced, resulting in prohibitive computational overhead. Deep learning models, on the other hand, are prone to catastrophic forgetting under incremental learning settings, making it difficult to simultaneously preserve recognition performance on both old and newly added classes. In addition, nuclear power plant fault data typically exhibit significant class imbalance, further constraining model performance. To address these issues, this study employs SHAP-XGBoost to construct a feature evaluation system, enabling feature extraction and interpretable analysis on the NPPAD simulation dataset, thereby enhancing the model’s capability to learn new features. To mitigate insufficient temporal feature capture and sample imbalance among incremental classes, we propose a cascaded spatiotemporal feature extraction network: LSTM is used to capture local dependencies, and its hidden states are passed as position-aware inputs to a Transformer for modeling global relationships, thus alleviating Transformer overfitting on short sequences. By further integrating frequency-domain analysis, an improved Adaptive Time–Frequency Network (ATFNet) is developed to enhance the robustness of discriminating complex fault patterns. Experimental results show that the proposed method achieves an average accuracy of 91.36% across five incremental learning stages, representing an improvement of approximately 20.7% over baseline models, effectively mitigating the problem of catastrophic forgetting. Full article