Search Results (1,535)

Addressing the carbon footprint in pig production is a fundamental technical basis for achieving carbon neutrality and peak carbon emissions. Only by systematically studying the carbon footprint can the goals of carbon neutrality and peak carbon emissions be effectively realized. This study aims to reduce the carbon footprint through optimized feeding strategies based on minimizing carbon emissions. To this end, this study conducted a full-lifecycle monitoring of the carbon footprint during pig growth from December 2024 to May 2025, optimizing feeding strategies using a real-time pig weight estimation model driven by deep learning to reduce resource consumption and the carbon footprint. We introduce EcoSegLite, a lightweight deep learning model designed for non-contact real-time pig weight estimation. By incorporating ShuffleNetV2, Linear Deformable Convolution (LDConv), and ACmix modules, it achieves high precision in resource-constrained environments with only 1.6 M parameters, attaining a 96.7% mAP50. Based on full-lifecycle weight monitoring of 63 pigs at the Pianguan farm from December 2024 to May 2025, the EcoSegLite model was integrated with a life cycle assessment (LCA) framework to optimize feeding management. This approach achieved a 7.8% reduction in feed intake, an 11.9% reduction in manure output, and a 5.1% reduction in carbon footprint. The resulting growth curves further validated the effectiveness of the optimized feeding strategy, while the reduction in feed and manure also potentially reduced water consumption and nitrogen runoff. This study offers a data-driven solution that enhances resource efficiency and reduces environmental impact, paving new pathways for precision agriculture and sustainable livestock production. Full article

Cardiovascular diseases are known as major contributors to death globally. Accurate identification and classification of cardiac arrhythmias from electrocardiogram (ECG) signals is essential for early diagnosis and treatment of cardiovascular diseases. This research introduces an innovative deep learning architecture that integrates Convolutional Neural Networks with a channel attention mechanism, enhancing the model’s capacity to concentrate on essential aspects of the ECG signals. Unlike most prior studies that depend on single-lead data or complex hybrid models, this work presents a novel yet simple deep learning architecture to classify five arrhythmia classes that effectively utilizes both 2-lead and 12-lead ECG signals, providing more accurate representations of clinical scenarios. The model’s performance was evaluated on the MIT-BIH and INCART arrhythmia datasets, achieving accuracies of 99.18% and 99.48%, respectively, along with F1 scores of 99.18% and 99.48%. These high-performance metrics demonstrate the model’s ability to differentiate between normal and arrhythmic signals, as well as accurately identify various arrhythmia types. The proposed architecture ensures high accuracy without excessive complexity, making it well-suited for real-time and clinical applications. This approach could improve the efficiency of healthcare systems and contribute to better patient outcomes. Full article

Heat stress severely impacts pig welfare and farm productivity. However, existing methods lack the capability to detect subtle physiological cues (e.g., skin erythema) in complex farm environments while maintaining real-time efficiency. This paper proposes PigStressNet, a novel lightweight detector designed for accurate and efficient heat stress recognition. Our approach integrates four key innovations: (1) a Normalization-based Attention Module (NAM) integrated into the backbone network enhances sensitivity to localized features critical for heat stress, such as posture and skin erythema; (2) a Rectangular Self-Calibration Module (RCM) in the neck network improves spatial feature reconstruction, particularly for occluded pigs; (3) an MBConv-optimized detection head (MBHead) reduces computational cost in the head by 72.3%; (4) the MPDIoU loss function enhances bounding box regression accuracy in scenarios with overlapping pigs. We constructed the first fine-grained dataset specifically annotated for pig heat stress (comprising 710 images across 5 classes: standing, eating, sitting, lying, and stress), uniquely fusing posture (lying) and physiological traits (skin erythema). Experiments demonstrate state-of-the-art performance: PigStressNet achieves 0.979 mAP for heat stress detection while requiring 15.9% lower computation (5.3 GFLOPs) and 11.7% fewer parameters compared to the baseline YOLOv12-n model. The system achieves real-time inference on embedded devices, offering a viable solution for intelligent livestock management. Full article

Modern wireless communication systems increasingly rely on Automatic Modulation Classification (AMC) to enhance reliability and adaptability, especially in the presence of severe signal degradation. However, despite significant progress driven by deep learning, many AMC models still struggle with high computational overhead, suboptimal performance under low-signal-to-noise conditions, and limited interpretability, factors that hinder their deployment in real-time, resource-constrained environments. To address these challenges, we propose the Convolutional Random Fourier Features with Denoising Thresholding Network (CRFFDT-Net), a compact and interpretable deep kernel architecture that integrates Convolutional Random Fourier Features (CRFFSinCos), an automatic threshold-based denoising module, and a hybrid time-domain feature extractor composed of CNN and GRU layers. Our approach is validated on the RadioML 2016.10A benchmark dataset, encompassing eleven modulation types across a wide signal-to-noise ratio (SNR) spectrum. Experimental results demonstrate that CRFFDT-Net achieves an average classification accuracy that is statistically comparable to state-of-the-art models, while requiring significantly fewer parameters and offering lower inference latency. This highlights an exceptional accuracy–complexity trade-off. Moreover, interpretability analysis using GradCAM++ highlights the pivotal role of the Convolutional Random Fourier Features in the representation learning process, providing valuable insight into the model’s decision-making. These results underscore the promise of CRFFDT-Net as a lightweight and explainable solution for AMC in real-world, low-power communication systems. Full article

The increasing demand for portable health monitoring has highlighted the need for automated sleep staging systems that are both accurate and computationally efficient. However, most existing deep learning models for electroencephalogram (EEG)-based sleep staging suffer from parameter redundancy, fixed dilation rates, and limited generalization, restricting their applicability in real-time and resource-constrained scenarios. In this paper, we propose ADG-SleepNet, a novel lightweight symmetry-aware multi-scale dilation-gated temporal convolutional network enhanced with adaptive attention mechanisms for EEG-based sleep staging. ADG-SleepNet features a structurally symmetric, parallel multi-branch architecture utilizing various dilation rates to comprehensively capture multi-scale temporal patterns in EEG signals. The integration of adaptive gating and channel attention mechanisms enables the network to dynamically adjust the contribution of each branch based on input characteristics, effectively breaking architectural symmetry when necessary to prioritize the most discriminative features. Experimental results on the Sleep-EDF-20 and Sleep-EDF-78 datasets demonstrate that ADG-SleepNet achieves accuracy rates of 87.1% and 85.1%, and macro F1 scores of 84.0% and 81.1%, respectively, outperforming several state-of-the-art lightweight models. These findings highlight the strong generalization ability and practical potential of ADG-SleepNet for EEG-based health monitoring applications. Full article

Accurate observations of Ocean Surface Wind Speed (OSWS) are vital for predicting extreme weather and understanding ocean–atmosphere interactions. However, spaceborne sensors (e.g., ASCAT, SMAP) often experience data loss due to harsh weather and instrument malfunctions. Existing inpainting methods often rely on reanalysis data that is released with delays, which restricts their real-time capability. Additionally, deep-learning-based methods, such as Transformers, face challenges due to their high computational complexity. To address these challenges, we present the Multimodal Wind Speed Inpainting Dataset (MWSID), which integrates 12 auxiliary forecasting variables to support real-time OSWS inpainting. Based on MWSID, we propose the MMamba framework, combining the Multimodal Feature Extraction module, which uses mutual information (MI) theory to optimize feature selection, and the OSWS Reconstruction module, which employs Attention-Mamba-2 within a Residual-in-Residual-Dense architecture for efficient OSWS inpainting. Experiments show that MMamba outperforms MambaIR (state-of-the-art) with an RMSE of 0.5481 m/s and an SSIM of 0.9820, significantly reducing RMSE by 21.10% over Kriging and 8.22% over MambaIR in high-winds (>15 m/s). We further introduce MMamba-L, a lightweight 0.22M-parameter variant suitable for resource-limited devices. These contributions make MMamba and MWSID powerful tools for OSWS inpainting, benefiting extreme weather prediction and oceanographic research. Full article

Early detection of pest damage and accurate assessment of fruit ripeness are essential for improving the quality, productivity, and sustainability of citrus production. Moreover, precisely assessing ripeness is crucial for establishing the optimal harvest time, preserving fruit quality, and enhancing yield. The simultaneous and precise early detection of pest damage and assessment of fruit ripeness greatly enhance the efficacy of contemporary agricultural decision support systems. This study presents a lightweight deep learning model based on an optimized YOLO12n-Seg architecture for the simultaneous detection of ripeness stages (unripe and fully ripe) and pest damage caused by Red Scale (Aonidiella aurantii). The model is based on an improved version of YOLO12n-Seg, where the backbone and head layers were retained, but the neck was modified with a GhostConv block to reduce parameter size and improve computational efficiency. Additionally, a Global Attention Mechanism (GAM) was incorporated to strengthen the model’s focus on target-relevant features and reduce background noise. The improvement procedure improved both the ability to gather accurate spatial information in several dimensions and the effectiveness of focusing on specific target object areas utilizing the attention mechanism. Experimental results demonstrated high accuracy on test data, with mAP@0.5 = 0.980, mAP@0.95 = 0.960, precision = 0.961, and recall = 0.943, all achieved with only 2.7 million parameters and a training time of 2 h and 42 min. The model offers a reliable and efficient solution for real-time, integrated pest detection and fruit classification in precision agriculture. Full article

Objectives: The persistent evolution of software vulnerabilities—spanning novel zero-day exploits to logic-level flaws—continues to challenge conventional cybersecurity mechanisms. Static rule-based scanners and opaque deep learning models often lack the precision and contextual understanding required for both accurate detection and analyst interpretability. This paper presents a hybrid framework for real-time vulnerability detection that improves both robustness and explainability. Methods: The framework integrates semantic encoding via Bidirectional Encoder Representations from Transformers (BERTs), structural analysis using Deep Graph Convolutional Neural Networks (DGCNNs), and lightweight prioritization through Kernel Extreme Learning Machines (KELMs). The architecture incorporates Minimum Intermediate Representation (MIR) learning to reduce false positives and fuses multi-modal data (source code, execution traces, textual metadata) for robust, scalable performance. Explainable Artificial Intelligence (XAI) visualizations—combining SHAP-based attributions and CVSS-aligned pair plots—serve as an analyst-facing interpretability layer. The framework is evaluated on benchmark datasets, including VulnDetect and the NIST Software Reference Library (NSRL, version 2024.12.1, used strictly as a benign baseline for false positive estimation). Results: Our evaluation reports that precision, recall, AUPRC, MCC, and calibration (ECE/Brier score) demonstrated improved robustness and reduced false positives compared to baselines. An internal interpretability validation was conducted to align SHAP/GNNExplainer outputs with known vulnerability features; formal usability testing with practitioners is left as future work. Conclusions: The framework, Designed with DevSecOps integration in mind, the system is packaged in containerized modules (Docker/Kubernetes) and outputs SIEM-compatible alerts, enabling potential compatibility with Splunk, GitLab CI/CD, and similar tools. While full enterprise deployment was not performed, these deployment-oriented design choices support scalability and practical adoption. Full article

The demand for robust safety monitoring in underground coal mines is increasing, yet traditional methods face limitations in long-term stability due to inadequate energy supply and high maintenance requirements. To address the critical challenges of high computational demand and energy constraints in this resource-limited environment, this paper proposes MineVisual, a battery-free visual sensing scheme specifically designed for underground coal mines. The core of MineVisual is an optimized lightweight deep neural network employing depthwise separable convolution modules to enhance computational efficiency and reduce energy consumption. Crucially, we introduce an energy-aware dynamic pruning network (EADP-Net) ensuring a sustained inference accuracy and energy efficiency across fluctuating power conditions. The system integrates supercapacitor buffering and voltage regulation for stable operation under wind intermittency. Experimental validation demonstrates that MineVisual achieves high accuracy (e.g., 91.5% Top-1 on mine-specific tasks under high power) while significantly enhancing the energy efficiency (reducing inference energy to 6.89 mJ under low power) and robustness under varying wind speeds. This work provides an effective technical pathway for intelligent safety monitoring in complex underground environments and conclusively proves the feasibility of battery-free deep learning inference in extreme settings like coal mines. Full article

The traditional detection of blueberry maturity relies on human experience, which is inefficient and highly subjective. Although deep learning methods have improved accuracy, they require large models and complex computations, making real-time deployment on resource-constrained edge devices difficult. To address these issues, a GLL-YOLO method based on the YOLOv8 network is proposed to deal with problems such as fruit occlusion and complex backgrounds in mature blueberry detection. This approach utilizes the GhostNetV2 network as the backbone. The LIMC module is suggested to substitute the original C2f module. Meanwhile, a Lightweight Shared Convolution Detection Head (LSCD) module is designed to build the GLL-YOLO model. This model can accurately detect blueberries at three different maturity stages: unripe, semi-ripe, and ripe. It significantly reduces the number of model parameters and floating-point operations while maintaining high accuracy. Experimental results show that GLL-YOLO outperforms the original YOLOv8 model in terms of accuracy, with mAP improvements of 4.29%, 1.67%, and 1.39% for unripe, semi-ripe, and ripe blueberries, reaching 94.51%, 91.72%, and 93.32%, respectively. Compared to the original model, GLL-YOLO improved the accuracy, recall rate, and mAP by 2.3%, 5.9%, and 1%, respectively. Meanwhile, GLL-YOLO reduces parameters, FLOPs, and model size by 50%, 39%, and 46.7%, respectively, while maintaining accuracy. This method has the advantages of a small model size, high accuracy, and good detection performance, providing reliable support for intelligent blueberry harvesting. Full article

Semantic segmentation of ultra-high-resolution remote sensing (UHR-RS) imagery plays a critical role in land use and land cover analysis, yet it remains computationally intensive due to the enormous input size and high spatial complexity. Existing studies have commonly employed strategies such as patch-wise processing, multi-scale model architectures, lightweight networks, and representation sparsification to reduce resource demands, but they have often struggled to maintain long-range contextual awareness and scalability for inputs of arbitrary size. To address this, we propose RingFormer-Seg, a scalable Vision Transformer framework that enables long-range context learning through multi-device parallelism in UHR-RS image segmentation. RingFormer-Seg decomposes the input into spatial subregions and processes them through a distributed three-stage pipeline. First, the Saliency-Aware Token Filter (STF) selects informative tokens to reduce redundancy. Next, the Efficient Local Context Module (ELCM) enhances intra-region features via memory-efficient attention. Finally, the Cross-Device Context Router (CDCR) exchanges token-level information across devices to capture global dependencies. Fine-grained detail is preserved through the residual integration of unselected tokens, and a hierarchical decoder generates high-resolution segmentation outputs. We conducted extensive experiments on three benchmarks covering UHR-RS images from 2048 × 2048 to 8192 × 8192 pixels. Results show that our framework achieves top segmentation accuracy while significantly improving computational efficiency across the DeepGlobe, Wuhan, and Guangdong datasets. RingFormer-Seg offers a versatile solution for UHR-RS image segmentation and demonstrates potential for practical deployment in nationwide land cover mapping, supporting informed decision-making in land resource management, environmental policy planning, and sustainable development. Full article

Anomaly detection plays a vital role in ensuring product quality and operational safety across various industrial applications, from manufacturing to infrastructure monitoring. However, current methods often struggle with challenges such as limited generalization to complex multimodal anomalies, poor adaptation to domain-specific patterns, and reduced feature discriminability due to domain gaps between pre-trained models and industrial data. To address these issues, we propose AnomNet, a novel deep anomaly detection framework that integrates a lightweight feature adapter module to bridge domain discrepancies and enhance multi-scale feature discriminability from pre-trained backbones. AnomNet is trained using a dual-stage centroid learning strategy: the first stage employs separation and entropy regularization losses to stabilize and optimize the centroid representation of normal samples; the second stage introduces a centroid-based contrastive learning mechanism to refine decision boundaries by adaptively managing inter- and intra-class feature relationships. The experimental results on the MVTec AD dataset demonstrate the superior performance of AnomNet, achieving a 99.5% image-level AUROC and 98.3% pixel-level AUROC, underscoring its effectiveness and robustness for anomaly detection and localization in industrial environments. Full article

Characters on liquid crystal display (LCD) interfaces often appear densely arranged, with complex image backgrounds and significant variations in target appearance, posing considerable challenges for visual detection. To improve the accuracy and robustness of character detection, this paper proposes an enhanced character detection algorithm based on the DBNet framework, named EBiDNet (EfficientNetV2 and BiFPN Enhanced DBNet). This algorithm integrates machine vision with deep learning techniques and introduces the following architectural optimizations. It employs EfficientNetV2-S, a lightweight, high-performance backbone network, to enhance feature extraction capability. Meanwhile, a bidirectional feature pyramid network (BiFPN) is introduced. Its distinctive symmetric design ensures balanced feature propagation in both top-down and bottom-up directions, thereby enabling more efficient multiscale contextual information fusion. Experimental results demonstrate that, compared with the original DBNet, the proposed EBiDNet achieves a 9.13% increase in precision and a 14.17% improvement in F1-score, while reducing the number of parameters by 17.96%. In summary, the proposed framework maintains lightweight design while achieving high accuracy and strong robustness under complex conditions. Full article

X-ray security screening is a well-established technology used in public spaces. The traditional method for detecting prohibited items in X-ray images relies on manual inspection, necessitating security personnel with extensive experience and focused attention to achieve satisfactory detection accuracy. However, the high-intensity and long-duration nature of the work leads to security personnel fatigue, which in turn reduces the accuracy of prohibited items detection and results in false alarms or missed detections. In response to the challenges posed by the coexistence of multiple prohibited items, incomplete identification information due to overlapping items, variable distribution positions in typical scenarios, and the need for portable detection equipment, this study proposes a lightweight automatic detection method for prohibited items. Based on establishment the sample database for prohibited items, a new backbone network with a residual structure and attention mechanism is introduced to form a deep learning algorithm. Additionally, a dilated convolutional spatial pyramid module and a depthwise separable convolution algorithm are added to fuse multi-scale features, to improve the accuracy of prohibited items detection. This study developed a lightweight automatic detection method for prohibited items, and its highest detection rate is 95.59%, which demonstrates a 1.86% mAP improvement over the YOLOv4-tiny baseline with 122 FPS. The study achieved high accurate detection of typical prohibited items, providing support for the assurance of public safety. Full article

This study presents a gradient-informed proxy initialization framework designed to improve training efficiency and predictive performance in deep learning models for time-series forecasting. The method extends the Laor Initialization approach by introducing backward gradient norm clustering as a selection criterion for input-layer weights, evaluated through a lightweight, architecture-agnostic proxy model. Only the numerical input layer adopts the selected initialization, while internal components retain standard schemes such as Xavier, Kaiming, or Orthogonal, maintaining compatibility and reducing overhead. The framework is evaluated on a real-world financial forecasting task: identifying high-risk equities from the Thai Market Surveillance Measure List, a domain characterized by label imbalance, non-stationarity, and limited data volume. Experiments across five architectures, including Transformer, ConvTran, and MMAGRU-FCN, show that the proposed strategy improves convergence speed and classification accuracy, particularly in deeper and hybrid models. Results in recurrent-based models are competitive but less pronounced. These findings support the method’s practical utility and generalizability for forecasting tasks under real-world constraints. Full article