Search Results (529)

Accurate weld defect detection is critical for ensuring structural safety and evaluating welding quality in industrial applications. Manual inspection methods have inherent limitations, including inefficiency and inadequate sensitivity to subtle defects. Existing detection models, primarily designed for natural images, struggle to adapt to the characteristic challenges of weld X-ray images, such as high noise, low contrast, and inter-defect similarity, particularly leading to missed detections and false positives for small defects. To address these challenges, a multi-dimensional feature fusion model (MADet), which is a multi-branch deep fusion network for weld defect detection, was proposed. The framework incorporates two key innovations: (1) A multi-scale feature fusion network integrated with lightweight attention residual modules to enhance the perception of fine-grained defect features by leveraging low-level texture information. (2) An anchor-based feature-selective detection head was used to improve the discrimination and localization accuracy for five typical defect categories. Extensive experiments on both public and proprietary weld defect datasets demonstrated that MADet achieved significant improvements over the state-of-the-art YOLO variants. Specifically, it surpassed the suboptimal model by 7.41% in mAP@0.5, indicating strong industrial applicability. Full article

The Internet of Things (IoT) is transforming how devices communicate, with more than 30 billion connected units today and projections exceeding 40 billion by 2025. Despite this growth, the integration of heterogeneous systems remains a significant challenge, particularly in sensitive domains like healthcare, where proprietary standards and isolated ecosystems hinder interoperability. This paper presents an extended version of the Share design pattern, a lightweight and contract-based mechanism for dynamic service composition, tailored for resource-constrained IoT devices. Share enables decentralized, peer-to-peer integration by exchanging executable code in our examples written in the LUA programming language. This approach avoids reliance on centralized infrastructures and allows services to discover and interact with each other dynamically through pattern-matching and contract validation. To assess its suitability, we developed an emulator that directly implements the system under test in LUA, allowing us to verify both the structural and behavioral constraints of service interactions. Our results demonstrate that Share is scalable and effective, even in constrained environments, and supports formal correctness via design-by-contract principles. This makes it a promising solution for lightweight, interoperable IoT systems that require flexibility, dynamic configuration, and resilience without centralized control. Full article

Detecting manipulated document images is essential for verifying the authenticity of official records and preventing document forgery. However, forgery artifacts are often subtle and localized in fine-grained regions, such as text boundaries or character outlines, where visual symmetry and structural regularity are typically expected. These manipulations can disrupt the inherent symmetry of document layouts, making the detection of such inconsistencies crucial for forgery identification. Conventional CNN-based models face limitations in capturing such edge-level asymmetric features, as edge-related information tends to weaken through repeated convolution and pooling operations. To address this issue, this study proposes an edge-focused method composed of two components: the Edge Attention (EA) layer and the Edge Concatenation (EC) layer. The EA layer dynamically identifies channels that are highly responsive to edge features in the input feature map and applies learnable weights to emphasize them, enhancing the representation of boundary-related information, thereby emphasizing structurally significant boundaries. Subsequently, the EC layer extracts edge maps from the input image using the Sobel filter and concatenates them with the original feature maps along the channel dimension, allowing the model to explicitly incorporate edge information. To evaluate the effectiveness and compatibility of the proposed method, it was initially applied to a simple CNN architecture to isolate its impact. Subsequently, it was integrated into various widely used models, including DenseNet121, ResNet50, Vision Transformer (ViT), and a CAE-SVM-based document forgery detection model. Experiments were conducted on the DocTamper, Receipt, and MIDV-2020 datasets to assess classification accuracy and F1-score using both original and forged text images. Across all model architectures and datasets, the proposed EA–EC method consistently improved model performance, particularly by increasing sensitivity to asymmetric manipulations around text boundaries. These results demonstrate that the proposed edge-focused approach is not only effective but also highly adaptable, serving as a lightweight and modular extension that can be easily incorporated into existing deep learning-based document forgery detection frameworks. By reinforcing attention to structural inconsistencies often missed by standard convolutional networks, the proposed method provides a practical solution for enhancing the robustness and generalizability of forgery detection systems. Full article

Thermal resilience is critical for building safety in cold climates during heating outages. This study presents full-scale experimental data from two residential buildings in Poland, tested during the winter of 2024–2025 under both typical and extreme outdoor conditions. The buildings—a lightweight timber-frame structure and a mediumweight masonry structure with ground coupling—were exposed to multi-day heating blackouts, and their thermal responses were monitored at a high temporal resolution. Several resilience indicators were used, including the resistance time (RT), degree of disruption (DoD), and hours of safety threshold (HST). Additionally, two time-based metrics—the time to threshold (T_x) and temperature at X-hours (T(t_x))—were introduced to improve classification in long-duration scenarios. The weighted unmet thermal performance (WUMTP) index was also implemented and validated using experimental data. The results show that thermal mass and ground coupling significantly improved passive resilience, enabling the mediumweight building to maintain temperatures above 15 °C for over 60 h without heating. This study provides new empirical evidence of passive survivability in blackout conditions and supports the development of time-sensitive assessment tools for cold climates. The findings may inform future updates to building codes and retrofit guidelines. Full article

The Industrial Internet of Things (IIoT), a key enabler of Industry 4.0, integrates advanced communication technologies with the industrial economy to enable intelligent manufacturing and interconnected systems. Secure and reliable identity authentication in the IIoT becomes essential as connectivity expands across devices, systems, and domains. Blockchain technology presents a promising solution due to its decentralized, tamper-resistant, and traceable characteristics, facilitating secure and transparent identity verification. However, current blockchain-based cross-domain authentication schemes often lack a lightweight design, rendering them unsuitable for latency-sensitive and resource-constrained industrial environments. This paper proposes a lightweight cross-domain authentication scheme that combines blockchain with Chebyshev chaotic mapping. Unlike existing schemes relying heavily on Elliptic Curve Cryptography or bilinear pairing, our design circumvents such computationally intensive primitives entirely through the algebraic structure of Chebyshev polynomials. A formal security analysis using the Real-Or-Random (ROR) model demonstrates the scheme’s robustness. Furthermore, performance evaluations conducted with Hyperledger Fabric and the MIRACL cryptographic library validate the method’s effectiveness and superiority over existing approaches in terms of both security and operational efficiency. Full article

Recent advances in precision manufacturing and high-end equipment technologies have imposed ever more stringent requirements on the accuracy, real-time performance, and lightweight design of online steel strip surface defect detection systems. To reconcile the persistent trade-off between detection precision and inference efficiency in complex industrial environments, this study proposes StripSurface–YOLO, a novel real-time defect detection framework built upon YOLOv8n. The core architecture integrates an Efficient Cross-Stage Local Perception module (ResGSCSP), which synergistically combines GSConv lightweight convolutions with a one-shot aggregation strategy, thereby markedly reducing both model parameters and computational complexity. To further enhance multi-scale feature representation, this study introduces an Efficient Multi-Scale Attention (EMA) mechanism at the feature-fusion stage, enabling the network to more effectively attend to critical defect regions. Moreover, conventional nearest-neighbor upsampling is replaced by DySample, which produces deeper, high-resolution feature maps enriched with semantic content, improving both inference speed and fusion quality. To heighten sensitivity to small-scale and low-contrast defects, the model adopts Focal Loss, dynamically adjusting to sample difficulty. Extensive evaluations on the NEU-DET dataset demonstrate that StripSurface–YOLO reduces FLOPs by 11.6% and parameter count by 7.4% relative to the baseline YOLOv8n, while achieving respective improvements of 1.4%, 3.1%, 4.1%, and 3.0% in precision, recall, mAP₅₀, and mAP_50:95. Under adverse conditions—including contrast variations, brightness fluctuations, and Gaussian noise—SteelSurface-YOLO outperforms the baseline model, delivering improvements of 5.0% in mAP₅₀ and 4.7% in mAP_50:95, attesting to the model’s robust interference resistance. These findings underscore the potential of StripSurface–YOLO to meet the rigorous performance demands of real-time surface defect detection in the metal forging industry. Full article

The body-in-white (BIW) is an important part of the electric vehicle body, its mass accounts for about 30% of the vehicle mass, and reducing its mass can significantly contribute to energy savings and emission reduction. In this paper, a collaborative optimization method combining the response surface method and genetic algorithm (RSM-GA) is developed to perform the lightweight optimization of the body-in-white of an electric vehicle. Seventeen design variables were screened by relative sensitivity calculations based on modal and stiffness sensitivity analysis, and the data samples were collected using the Taguchi experiment and Hammersley experiment during the designing of the experiment methods. To further maintain the accuracy rate, the least squares regression, moving least squares method, and radial basis function are applied to fitting data to obtain the response surface, and the error analysis of the fitting results is carried out to correct the response surface. Finally, the genetic algorithm based on the response surface is employed to optimize the structure of the body-in-white, and the results are compared with those of the adaptive response surface method and sequential quadratic programming method. Through comparison, the paper found that the optimization effect obtained by the proposed method has a relatively high accuracy rate. Full article

Ventricular arrhythmias (VAs) are critical cardiovascular diseases that require rapid and accurate detection. Conventional approaches relying on multi-lead ECG or deep learning models have limitations in computational cost, interpretability, and real-time applicability on wearable devices. To address these issues, a lightweight and interpretable framework based on multiple complex networks was proposed for the detection of life-threatening VAs using short-term single-lead ECG signals. The input signals were decomposed using the fixed-frequency-range empirical wavelet transform, and sub-bands were subsequently analyzed through multiscale visibility graphs, recurrence networks, cross-recurrence networks, and joint recurrence networks. Eight topological features were extracted and input into an XGBoost classifier for VA identification. Ten-fold cross-validation results on the MIT-BIH VFDB and CUDB databases demonstrated that the proposed method achieved a sensitivity of 99.02 ± 0.53%, a specificity of 98.44 ± 0.43%, and an accuracy of 98.73 ± 0.02% for 10 s ECG segments. The model also maintained robust performance on shorter segments, with 97.23 ± 0.76% sensitivity, 98.85 ± 0.95% specificity, and 96.62 ± 0.02% accuracy on 2 s segments. The results outperformed existing feature-based and deep learning approaches while preserving model interpretability. Furthermore, the proposed method supports mobile deployment, facilitating real-time use in wearable healthcare applications. Full article

Poultry feces, a critical biomarker for health assessment, requires timely and accurate pathological identification for food safety. Conventional visual-only methods face limitations due to environmental sensitivity and high visual similarity among feces from different diseases. To address this, we propose MMCD (Multimodal Chicken-feces Diagnosis), a ResNet50-based multimodal fusion model leveraging semantic complementarity between images and descriptive text to enhance diagnostic precision. Key innovations include the following: (1) Integrating MASA(Manhattan self-attention)and DSconv (Depthwise Separable convolution) into the backbone network to mitigate feature confusion. (2) Utilizing a pre-trained BERT to extract textual semantic features, reducing annotation dependency and cost. (3) Designing a lightweight Gated Cross-Attention (GCA) module for dynamic multimodal fusion, achieving a 41% parameter reduction versus cross-modal transformers. Experiments demonstrate that MMCD significantly outperforms single-modal baselines in Accuracy (+8.69%), Recall (+8.72%), Precision (+8.67%), and F1 score (+8.72%). It surpasses simple feature concatenation by 2.51–2.82% and reduces parameters by 7.5M and computations by 1.62 GFLOPs versus the base ResNet50. This work validates multimodal fusion’s efficacy in pathological fecal detection, providing a theoretical and technical foundation for agricultural health monitoring systems. Full article

The rapid development of deepfake technologies has led to the widespread proliferation of facial image forgeries, raising significant concerns over identity theft and the spread of misinformation. Although recent dual-domain detection approaches that integrate spatial and frequency features have achieved noticeable progress, they still suffer from limited sensitivity to local forgery regions and inadequate interaction between spatial and frequency information in practical applications. To address these challenges, we propose a novel forgery-aware guided spatial–frequency feature fusion network. A lightweight U-Net is employed to generate pixel-level saliency maps by leveraging structural symmetry and semantic consistency, without relying on ground-truth masks. These maps dynamically guide the fusion of spatial features (from an improved Swin Transformer) and frequency features (via Haar wavelet transforms). Cross-domain attention, channel recalibration, and spatial gating are introduced to enhance feature complementarity and regional discrimination. Extensive experiments conducted on two benchmark face forgery datasets, FaceForensics++ and Celeb-DFv2, show that the proposed method consistently outperforms existing state-of-the-art techniques in terms of detection accuracy and generalization capability. The future work includes improving robustness under compression, incorporating temporal cues, extending to multimodal scenarios, and evaluating model efficiency for real-world deployment. Full article

Structural Health Monitoring (SHM) is an essential technique for continuously assessing structural conditions using integrated sensor systems during operation. SHM technologies have evolved to address the increasing demand for efficient maintenance strategies in advanced engineering fields, such as civil infrastructure, aerospace, and transportation. However, developing a miniaturized, cost-effective, and multi-sensor solution based on Wireless Sensor Networks (WSNs) remains a significant challenge, particularly for SHM applications in weight-sensitive aerospace structures. To address this, the present study introduces a novel WSN-based Multi-Sensor System (MSS) that integrates multiple sensing capabilities onto a 3 × 3 cm flexible Printed Circuit Board (PCB). The proposed system combines a Piezoelectric Transducer (PZT) for impact detection; a strain gauge for mechanical deformation monitoring; an accelerometer for capturing dynamic responses; and an environmental sensor measuring temperature, pressure, and humidity. This high level of functional integration, combined with real-time Data Acquisition (DAQ) and precise time synchronization via Bluetooth Low Energy (LE), distinguishes the proposed MSS from conventional SHM systems, which are typically constrained by bulky hardware, single sensing modalities, or dependence on wired communication. Experimental evaluations on composite panels and aluminum specimens demonstrate reliable high-fidelity recording of PZT signals, strain variations, and acceleration responses, matching the performance of commercial instruments. The proposed system offers a low-power, lightweight, and scalable platform, demonstrating strong potential for on-board SHM in aircraft applications. Full article

Barnyard grass is a major noxious weed in paddy fields. Accurate and efficient identification of barnyard grass is crucial for precision field management. However, existing deep learning models generally suffer from high parameter counts and computational complexity, limiting their practical application in field scenarios. Moreover, the morphological similarity, overlapping, and occlusion between barnyard grass and rice pose challenges for reliable detection in complex environments. To address these issues, this study constructed a barnyard grass detection dataset using high-resolution images captured by a drone equipped with a high-definition camera in rice experimental fields in Haicheng City, Liaoning Province. A lightweight field barnyard grass detection model, YOLOv8n-SSDW, was proposed to enhance detection precision and speed. Based on the baseline YOLOv8n model, a novel Separable Residual Coord Conv (SRCConv) was designed to replace the original convolution module, significantly reducing parameters while maintaining detection accuracy. The Spatio-Channel Enhanced Attention Module (SEAM) was introduced and optimized to improve sensitivity to barnyard grass edge features. Additionally, the lightweight and efficient Dysample upsampling module was incorporated to enhance feature map resolution. A new WIoU loss function was developed to improve bounding box classification and regression accuracy. Comprehensive performance analysis demonstrated that YOLOv8n-SSDW outperformed state-of-the-art models. Ablation studies confirmed the effectiveness of each improvement module. The final fused model achieved lightweight performance while improving detection accuracy, with a 2.2% increase in mAP_50, 3.8% higher precision, 0.6% higher recall, 10.6% fewer parameters, 9.8% lower FLOPs, and an 11.1% reduction in model size compared to the baseline. Field tests using drones combined with ground-based computers further validated the model’s robustness in real-world complex paddy environments. The results indicate that YOLOv8n-SSDW exhibits excellent accuracy and efficiency. This study provides valuable insights for barnyard grass detection in rice fields. Full article

The generation of realistic electrical load profiles is essential for advancing smart grid analytics, demand forecasting, and privacy-preserving data sharing. Traditional approaches often rely on large, high-resolution datasets and complex recurrent neural architectures, which can be unstable or ineffective when training data are limited. This paper proposes a data-driven framework based on a lightweight 1D Convolutional Wasserstein GAN with Gradient Penalty (Conv1D-WGAN-GP) for generating high-fidelity synthetic 24 h load profiles. The model is specifically designed to operate on small- to medium-sized datasets, where recurrent models often fail due to overfitting or training instability. The approach leverages the ability of Conv1D layers to capture localized temporal patterns while remaining compact and stable during training. We benchmark the proposed model against vanilla GAN, WGAN-GP, and Conv1D-GAN across four datasets with varying consumption patterns and sizes, including industrial, agricultural, and residential domains. Quantitative evaluations using statistical divergence measures, Real-vs-Synthetic Distinguishability Score, and visual similarity confirm that Conv1D-WGAN-GP consistently outperforms baselines, particularly in low-data scenarios. This demonstrates its robustness, generalization capability, and suitability for privacy-sensitive energy modeling applications where access to large datasets is constrained. Full article

Electrospun nanofiber-based triboelectric nanogenerators (TENGs) have emerged as a highly promising class of self-powered sensors for a broad range of applications, particularly in intelligent sensing technologies. By combining the advantages of electrospinning and triboelectric nanogenerators, these sensors offer superior characteristics such as high sensitivity, mechanical flexibility, lightweight structure, and biocompatibility, enabling their integration into wearable electronics and biomedical interfaces. This review presents a comprehensive overview of recent progress in electrospun nanofiber-based TENGs, covering their working principles, operating modes, and material composition. Both pure polymer and composite nanofibers are discussed, along with various electrospinning techniques that enable control over morphology and performance at the nanoscale. We explore their practical implementations in both contact-type and non-contact-type sensing, such as human–machine interaction, physiological signal monitoring, gesture recognition, and voice detection. These applications demonstrate the potential of TENGs to enable intelligent, low-power, and real-time sensing systems. Furthermore, this paper points out critical challenges and future directions, including durability under long-term operation, scalable and cost-effective fabrication, and seamless integration with wireless communication and artificial intelligence technologies. With ongoing advancements in nanomaterials, fabrication techniques, and system-level integration, electrospun nanofiber-based TENGs are expected to play a pivotal role in shaping the next generation of self-powered, intelligent sensing platforms across diverse fields such as healthcare, environmental monitoring, robotics, and smart wearable systems. Full article

The rapid expansion of Internet of Things (IoT) devices has heightened the demand for lightweight and secure cryptographic mechanisms suitable for resource-constrained environments. While SHA-256 remains a widely used standard, the emergence of SHA-3 particularly the KangarooTwelve variant offers potential benefits in flexibility and post-quantum resilience for lightweight resource-constrained devices. This paper presents a comparative evaluation of the energy costs associated with SHA-256 and SHA-3 hashing in Contiki 3.0, using three generationally distinct IoT platforms: Sky Mote, Z1 Mote, and Wismote. Unlike previous studies that rely on hardware acceleration or limited scope, our work conducts a uniform, software-only analysis across all motes, employing consistent radio duty cycling, ContikiMAC (a low-power Medium Access Control protocol) and isolating the cryptographic workload from network overhead. The empirical results from the Cooja simulator reveal that while SHA-3 provides advanced security features, it incurs significantly higher CPU and, in some cases, radio energy costs particularly on legacy hardware. However, modern platforms like Wismote demonstrate a more balanced trade-off, making SHA-3 viable in higher-capability deployments. These findings offer actionable guidance for designers of secure IoT systems, highlighting the practical implications of cryptographic selection in energy-sensitive environments. Full article