Search Results (191)

Surgical castration of male piglets is a common practice to prevent boar taint and reduce aggressive behaviour. However, it raises welfare concerns and alters carcass fat deposition. Immunocastration, a vaccine-based alternative targeting gonadotropin-releasing hormone (GnRH), mitigates these welfare issues. This study evaluated carcass traits and meat quality in surgically and immunocastrated pigs slaughtered at two weight classes (approximately 116 kg and 136 kg). We compared growth performance, carcass composition, fat quality, and key meat quality indicators among surgically castrated males, immunocastrated males, and immunocastrated females. Inclusion of uncastrated and immunocastrated females provides novel comparative data for mixed-sex production systems, where such information is scarce. This broader evaluation helps fill current gaps in knowledge about immunocastration effects in female pigs. Surgically castrated males showed higher backfat thickness and fat content, particularly at the heavier weight, while immunocastrated pigs exhibited intermediate traits. Ultimate pH, colour, marbling, water-holding capacity, and moisture loss varied with castration method, sex, and slaughter weight, though many differences were subtle. The findings confirm that immunocastration offers a favourable balance between animal welfare and production traits, producing pork quality comparable to surgical castration. These results provide valuable insights for optimizing pork production systems, balancing welfare, efficiency, and meat quality. Full article

The growing complexity of distribution-level virtual power plants (VPPs) demands a rethinking of how flexible demand is modeled, aggregated, and dispatched under uncertainty. Traditional optimization frameworks often rely on deterministic or homogeneous assumptions about end-user behavior, thereby overestimating controllability and underestimating risk. In this paper, we propose a behavior-aware, two-stage stochastic dispatch framework for VPPs that explicitly models heterogeneous user participation via integrated behavioral economics and social interaction structures. At the behavioral layer, user responses to demand response (DR) incentives are captured using a Prospect Theory-based utility function, parameterized by loss aversion, nonlinear gain perception, and subjective probability weighting. In parallel, social influence dynamics are modeled using a peer interaction network that modulates individual participation probabilities through local contagion effects. These two mechanisms are combined to produce a high-dimensional, time-varying participation map across user classes, including residential, commercial, and industrial actors. This probabilistic behavioral landscape is embedded within a scenario-based two-stage stochastic optimization model. The first stage determines pre-committed dispatch quantities across flexible loads, electric vehicles, and distributed storage systems, while the second stage executes real-time recourse based on realized participation trajectories. The dispatch model includes physical constraints (e.g., energy balance, network limits), behavioral fatigue, and the intertemporal coupling of flexible resources. A scenario reduction technique and the Conditional Value-at-Risk (CVaR) metric are used to ensure computational tractability and robustness against extreme behavior deviations. Full article

Micro-expressions are extremely subtle and short-lived facial muscle movements that often reveal an individual’s genuine emotions. However, micro-expression recognition (MER) remains highly challenging due to its short duration, low motion intensity, and the imbalanced distribution of training samples. To address these issues, this paper proposes a Global–Local Feature Fusion Network (GLFNet) to effectively extract discriminative features for MER. Specifically, GLFNet consists of three core modules: the Global Attention (LA) module, which captures subtle variations across the entire facial region; the Local Block (GB) module, which partitions the feature map into four non-overlapping regions to emphasize salient local movements while suppressing irrelevant information; and the Adaptive Feature Fusion (AFF) module, which employs an attention mechanism to dynamically adjust channel-wise weights for efficient global–local feature integration. In addition, a class-balanced loss function is introduced to replace the conventional cross-entropy loss, mitigating the common issue of class imbalance in micro-expression datasets. Extensive experiments are conducted on three benchmark databases, SMIC, CASME II, and SAMM, under two evaluation protocols. The experimental results demonstrate that under the Composite Database Evaluation protocol, GLFNet consistently outperforms existing state-of-the-art methods in overall performance. Specifically, the unweighted F1-scores on the Combined, SAMM, CASME II, and SMIC datasets are improved by 2.49%, 2.02%, 0.49%, and 4.67%, respectively, compared to the current best methods. These results strongly validate the effectiveness and superiority of the proposed global–local feature fusion strategy in micro-expression recognition tasks. Full article

The rapid advancement of generative models, such as GAN and diffusion architectures, has enabled the creation of highly realistic forged images, raising critical challenges in key domains. Detecting such forgeries is essential to prevent potential misuse in sensitive areas, including healthcare, financial documentation, and identity verification. This study addresses the problem by deploying a vision transformer (ViT)-based multiclass classification framework to identify image forgeries across three distinct domains: invoices, human faces, and medical images. The dataset comprises both authentic and AI-generated samples, creating a total of six classification categories. To ensure uniform feature representation across heterogeneous data and to effectively utilize pretrained weights, all images were resized to 224 × 224 pixels and converted to three channels. Model training was conducted using stratified K-fold cross-validation to maintain balanced class distribution in each fold. Experimental results of this study demonstrate consistently high performance across three folds, with an average training accuracy of 0.9983 (99.83%), validation accuracy of 0.9620 (96.20%), and test accuracy of 0.9608 (96.08%), along with a weighted F1 score of 0.9608 and exceeding 0.96 (96%) for all classes. These findings highlight the effectiveness of ViT architectures for cross-domain forgery detection and emphasize the importance of preprocessing standardization when working with mixed datasets. Full article

Deep learning (DL)-based multi-user physical layer authentication (PLA) in the Industrial Internet of Things (IIoT) requires frequent updates as new users join. Class incremental learning (CIL) addresses this challenge, but existing generative replay approaches depend on heavy parameterized models, causing high computational overhead and limiting deployment in resource-constrained environments. To address these challenges, we propose a parameter-free statistical generator-based CIL framework, PSG-CIL, for DL-based multi-user PLA in the IIoT. The parameter-free statistical generator (PSG) produces Gaussian sampling on user-specific means and variances to generate pseudo-data without training extra models, greatly reducing computational overhead. A confidence-based pseudo-data selection ensures pseudo-data reliability, while a dynamic adjustment mechanism for the loss weight balances the retention of old users’ knowledge and the adaptation to new users. Experiments on real industrial datasets show that PSG-CIL consistently achieves superior accuracy while maintaining a lightweight scale; for example, in the AAP outer loop scenario, PSG-CIL reaches 70.68%, outperforming retraining from scratch (58.57%) and other CIL methods. Full article

Reliable fault diagnosis of rotating machines under extreme conditions—strong speed, load variation, intense noise, and severe class imbalance—remains a critical industrial challenge. We develop an ultra-light yet robust framework to accurately detect weak bearing, and gear faults when less than 5% labels, 10 dB noise, 100:1 imbalance and plus or minus 20% operating-point drift coexist. Methods: The proposed Adaptive Feature Module–Conditional Dynamic GRU Auto-Encoder (AFM-CDGAE) first compresses 512 d spectra into 32/48 d “feature modules” via K-means while retaining 98.4% fault energy. A workload-adaptive multi-scale convolution with spatial attention and CPU-aware λ-scaling suppresses noise and adapts to edge–device load. A GRU-based auto-encoder, enhanced by self-attention, is trained with balanced-subset sampling and minority-F1-weighted voting to counter extreme imbalance. On Paderborn (5-class) and CWRU (7-class) benchmarks, the 0.87 M-parameter model achieves 99.12% and 98.83% Macro-F1, surpassing five recent baselines by 3.1% under normal and 5.4% under the above extreme conditions, with only 1.5 to 1.8% F1 drop versus 6.7% for baselines. AFM-CDGAE delivers state-of-the-art accuracy, minimal footprint and strong robustness, enabling real-time deployment at the edge. Full article

Concrete infrastructure inspection is essential for maintaining the safety and longevity of urban environments. Traditional manual crack detection methods are labor-intensive, inconsistent, and difficult to scale. Recent advancements in deep learning and computer vision offer automated alternatives, particularly when deployed via unmanned aerial vehicles (UAVs) for enhanced coverage and flexibility. However, achieving real-time performance on embedded systems requires models that are not only accurate but also lightweight and computationally efficient. This study presents CrackDetect-Lite, a comparative analysis of three deep learning architectures for binary crack detection using the SDNET2018 benchmark dataset: CNNSimple (a custom lightweight model), RSNet (a shallow residual network), and MobileVNet (a fine-tuned MobileNetV2). Class imbalance was addressed using a weighted cross-entropy loss function, and models were evaluated across multiple criteria including classification accuracy, crack-class F1-score, inference latency, and model size. Among the models, MobileVNet achieved the best balance between detection performance and deployability, with an accuracy of 90.5% and a crack F1-score of 0.73, while maintaining a low computational footprint suitable for UAV-based deployment. These findings demonstrate that carefully selected lightweight CNN architectures can deliver reliable, real-time crack detection, supporting scalable and autonomous infrastructure monitoring in smart city systems. Full article

Semantic segmentation of urban scenes from red–green–blue and thermal infrared imagery enables per-pixel categorization, delivering precise environmental understanding for autonomous driving and urban planning. However, existing methods suffer from inefficient fusion and insufficient boundary accuracy due to modal differences. To address these challenges, we propose a bidirectional dynamic adaptation framework with two complementary networks. The modality-aware network uses dual attention and multi-scale feature integration to balance modal contributions adaptively, improving intra-class semantic consistency and reducing modal disparities. The edge-texture guidance network applies pixel-level and feature-level weighting with Sobel and Gabor filters to enhance inter-class boundary discrimination, improving detail and boundary precision. Furthermore, the framework redefines multi-modal synergy using an adaptive cross-modal mutual learning mechanism. This mechanism employs information-driven dynamic alignment and probability-guided semantic consistency to overcome the fixed constraints of traditional mutual learning. This cohesive orchestration enhances multi-modal fusion efficiency and boundary delineation accuracy. Extensive experiments on the MFNet and PST900 datasets demonstrate the framework’s superior performance in urban road, vehicle, and pedestrian segmentation, surpassing state-of-the-art approaches. Full article

Accurately decoding human locomotion intention from physiological signals remains a significant hurdle for the seamless control of advanced rehabilitation devices like exoskeletons and intelligent prosthetics. Conventional recognition methods often falter, exhibiting limited accuracy and struggling to capture the complex, nonlinear dynamics inherent in biological data streams. Addressing these critical limitations, this study introduces a novel framework for lower-limb motion intent recognition, integrating Kernel Principal Component Analysis (KPCA) with a Support Vector Machine (SVM) optimized via an Improved Sparrow Search Algorithm (ISSA). Our approach commences by constructing a comprehensive high-dimensional feature space from synchronized surface electromyography (sEMG) and inertial measurement unit (IMU) data—a potent combination reflecting both muscle activation and limb kinematics. Critically, KPCA is employed for nonlinear dimensionality reduction; leveraging the power of kernel functions, it transcends the linear constraints of traditional PCA to extract low-dimensional principal components that retain significantly more discriminative information. Furthermore, the Sparrow Search Algorithm (SSA) undergoes three strategic enhancements: chaotic opposition-based learning for superior population diversity, adaptive dynamic weighting to adeptly balance exploration and exploitation, and hybrid mutation strategies to effectively mitigate premature convergence. This enhanced ISSA meticulously optimizes the SVM hyperparameters, ensuring robust classification performance. Experimental validation, conducted on a challenging 13-class lower-limb motion dataset, compellingly demonstrates the superiority of the proposed KPCA-ISSA-SVM architecture. It achieves a remarkable recognition accuracy of 95.35% offline and 93.3% online, substantially outperforming conventional PCA-SVM (91.85%) and standalone SVM (89.76%) benchmarks. This work provides a robust and significantly more accurate solution for intention perception in human–machine systems, paving the way for more intuitive and effective rehabilitation technologies by adeptly handling the nonlinear coupling characteristics of sEMG-IMU data and complex motion patterns. Full article

This study presents a unified machine learning strategy for identifying various degrees of sarcopenia severity in older adults. The approach combines three optimized algorithms (Random Forest, Gradient Boosting, and Multilayer Perceptron) into a stacked ensemble model, which is assessed with clinical data. A thorough data preparation process involved synthetic minority oversampling to ensure class balance and a dual approach to feature selection using Least Absolute Shrinkage and Selection Operator regression and Random Forest importance. The integrated model achieved remarkable performance with an accuracy of 96.99%, an F1 score of 0.9449, and a Cohen’s Kappa coefficient of 0.9738 while also demonstrating excellent calibration (Brier Score: 0.0125). Interpretability analysis through SHapley Additive exPlanations values identified appendicular skeletal muscle mass, body weight, and functional performance metrics as the most significant predictors, enhancing clinical relevance. The ensemble approach showed superior generalization across all sarcopenia classes compared to individual models. Although limited by dataset representativeness and the use of conventional multiclass classification techniques, the framework shows considerable promise for non-invasive sarcopenia risk assessments and exemplifies the value of interpretable artificial intelligence in geriatric healthcare. Full article

Data stream classification is a critical challenge in data mining, where models must rapidly adapt to evolving data distributions and concept drift in real time, while extreme learning machines offer fast training and strong generalization, most existing methods struggle to jointly address multi-class imbalance, concept drift, and the high cost of label acquisition in streaming settings. In this paper, we present the Adaptive Broad Learning System for Online Imbalanced Classification (ABLS-OIC), which introduces three core innovations: (1) a Class-Adaptive Weight Matrix (CAWM) that dynamically adjusts sample weights according to class distribution, sample density, and difficulty; (2) a Hybrid Memory Retention Mechanism (HMRM) that selectively retains representative samples based on importance and diversity; and (3) a Multi-Objective Adaptive Optimization Framework (MAOF) that balances classification accuracy, class balance, and computational efficiency. Extensive experiments on ten benchmark datasets with varying imbalance ratios and drift patterns show that ABLS-OIC consistently outperforms state-of-the-art methods, with improvements of 5.9% in G-mean, 6.3% in F1-score, and 3.4% in AUC. Furthermore, a real-world credit fraud detection case study demonstrates the practical effectiveness of ABLS-OIC, highlighting its value for early detection of rare but critical events in dynamic, high-stakes applications. Full article

Background. Severe left ventricular hypertrophy (SLVH) is a high-risk structural cardiac abnormality associated with increased risk of heart failure. It is typically assessed using echocardiography or cardiac magnetic resonance imaging, but these modalities are limited by cost, accessibility, and workflow burden. We introduce a deep learning framework that classifies SLVH directly from chest radiographs, without intermediate anatomical estimation models or demographic inputs. A key contribution of this work lies in interpretability. We quantify how clinically relevant attributes are encoded within internal representations, enabling transparent model evaluation and integration into AI-assisted workflows. Methods. We construct class-balanced subsets from the CheXchoNet dataset with equal numbers of SLVH-positive and negative cases while preserving the original train, validation, and test proportions. ResNet-18 is fine-tuned from ImageNet weights, and a Vision Transformer (ViT) encoder is pretrained via masked autoencoding with a trainable classification head. No anatomical or demographic inputs are used during training. We apply Mutual Information Neural Estimation (MINE) to quantify dependence between learned features and five attributes: age, sex, interventricular septal diameter (IVSDd), posterior wall diameter (LVPWDd), and internal diameter (LVIDd). Results. ViT achieves an AUROC of 0.82 [95% CI: 0.78–0.85] and an AUPRC of 0.80 [95% CI: 0.76–0.85], indicating strong performance in SLVH detection from chest radiographs. MINE reveals clinically coherent attribute encoding in learned features: age > sex > IVSDd > LVPWDd > LVIDd. Conclusions. This study shows that SLVH can be accurately classified from chest radiographs alone. The framework combines diagnostic performance with quantitative interpretability, supporting reliable deployment in triage and decision support. Full article

Citrus diseases severely impact fruit yield and quality. To facilitate in-field, non-destructive, and rapid detection of citrus leaf physiological and pathological conditions, this study proposes a classification method for citrus leaf physiological and pathological statuses that integrates visible/near-infrared multispectral technology with deep learning. First, a handheld spectrometer was employed to acquire spectral images of five sample categories—Healthy, Huanglongbing, Yellow Vein Disease, Magnesium Deficiency and Manganese Deficiency. Mean spectral data were extracted from regions of interest within the 350–2500 nm wavelength range, and various preprocessing techniques were evaluated. The Standard Normal Variate (SNV) transformation, which demonstrated optimal performance, was selected for data preprocessing. Next, we innovatively introduced an adaptive spectral positional encoding mechanism into the Transformer framework. A lightweight, learnable network dynamically optimizes positional biases, yielding the ASTransformer (Adaptive Spectral Transformer) model, which more effectively captures complex dependencies among spectral features and identifies critical wavelength bands, thereby significantly enhancing the model’s adaptive representation of discriminative bands. Finally, the preprocessed spectra were fed into three deep learning architectures (1D-CNN, 1D-ResNet, and ASTransformer) for comparative evaluation. The results indicate that ASTransformer achieves the best classification performance: an overall accuracy of 97.7%, underscoring its excellent global classification capability; a Macro Average of 97.5%, reflecting balanced performance across categories; a Weighted Average of 97.8%, indicating superior performance in classes with larger sample sizes; an average precision of 97.5%, demonstrating high predictive accuracy; an average recall of 97.7%, showing effective detection of most affected samples; and an average F1-score of 97.6%, confirming a well-balanced trade-off between precision and recall. Furthermore, interpretability analysis via Integrated Gradients quantitatively assesses the contribution of each wavelength to the classification decisions. These findings validate the feasibility of combining a handheld spectrometer with the ASTransformer model for effective citrus leaf physiological and pathological detection, enabling efficient classification and feature visualization, and offer a valuable reference for disease detection of physiological and pathological conditions in other fruit crops. Full article

Diabetes, a chronic condition caused by insufficient insulin production in the pancreas, presents significant health risks. Its increasing global prevalence necessitates the development of accurate and efficient predictive algorithms to support timely diagnosis. While recent advancements in deep learning (DL) have demonstrated potential for diabetes prediction, conventional models face limitations in handling class imbalance, capturing complex feature interactions, and providing interpretability for clinical decision-making. This paper proposes a DL framework for diabetes mellitus prediction. The framework ensures high predictive accuracy by integrating advanced preprocessing, effective class balancing, and a novel EchoceptionNet model. An analysis was conducted on a diabetes prediction dataset obtained from Kaggle, comprising nine features and 100,000 instances. The dataset is characterized by severe class imbalance, which is effectively addressed using a proximity-weighted synthetic oversampling technique, ensuring balanced class distribution. EchoceptionNet demonstrated notable performance improvements over state-of-the-art deep learning models, achieving a 4.39% increase in accuracy, 8.99% in precision, 2.19% in recall, 5.55% in F1-score, and a 7.77% in area under the curve score. Model robustness and generalizability were validated through 10-fold cross-validation, demonstrating consistent performance across diverse data splitting. To enhance clinical applicability, EchoceptionNet integrates explainable artificial intelligence techniques, Shapley additive explanations, and local interpretable model-agnostic explanations. These methods provide transparency by identifying the critical importance of features in the model’s predictions. EchoceptionNet exhibits superior predictive accuracy and ensures interpretability and reliability, making it a robust solution for accurate diabetes prediction. Full article

In recent years, graph neural networks (GNNs) have shown powerful performance in processing non-Euclidean data. However, similar to other machine-learning algorithms, GNNs can amplify data bias in high-risk decision-making systems, which can easily lead to unfairness in the final decision-making results. At present, a large number of studies focus on solving the fairness problem of GNNs, but the existing methods mostly rely on building complex model architectures or rely on technical means in the field of non-GNNs. To this end, this paper proposes FairCNCB (Fair Graph Neural Network based on Counterfactual and Category Balance) to address the problem of class imbalancing in minority sensitive attribute groups. First, we conduct a causal analysis of fair representation and employ the adversarial network to generate counterfactual node samples, effectively mitigating bias induced by sensitive attributes. Secondly, we calculate the weights for minority sensitive attribute groups, and reconstruct the loss function to achieve the fairness of sensitive attribute classes among different groups. The synergy between the two modules optimizes GNNs from multiple dimensions and significantly improves the performance of GNNs in terms of fairness. The experimental results on the three datasets show the effectiveness and fairness of FairCNCB. The performance metrics (such as AUC, F1, and ACC) have been improved by approximately 2%, and the fairness metrics (△sp, △eo) have been enhanced by approximately 5%. Full article