Search Results (4,904)

To improve the efficiency and accuracy of steel surface defect detection while reducing computational complexity, this paper proposes a lightweight detection algorithm—Finite Element Method-YOLO (FEM-YOLO). The algorithm aims to enhance defect detection performance by optimizing the network architecture and minimizing computational overhead. Methodologically, FEM-YOLO is based on the YOLOv8n architecture, incorporating a lightweight Feature Net network as the backbone for feature extraction. Through efficient parameter sharing and feature extraction mechanisms, the algorithm reduces its complexity. Additionally, FEM-YOLO innovatively combines Enhance Conv with the C2f module to form the C2f-Enhance module, thereby improving the representation of fine details and edges within the feature maps. To further enhance detection performance, a multi-path shared convolutional detection head is designed. This design significantly reduces the number of parameters through parameter sharing, thereby improving detection accuracy while maintaining the lightweight nature of the algorithm. The experimental results demonstrate that, on the NEU-DET enhanced dataset, the FEM-YOLO algorithm achieves a parameter count of 1.4 M, which is reduced to 43.7% of the baseline algorithm, with a computational complexity of 4.6 GFLOPs, 52.9% lower than the baseline. Furthermore, the FPS reaches 256. When employing the Focal_EIoU loss function, the mean Average Precision (mAP) reaches 83.3%, validating the algorithm’s efficiency and accuracy in steel surface defect detection. Full article

This study presents a comprehensive and critical review of segmentation algorithms applied to digital fundus images, aiming to identify computational strategies that balance diagnostic accuracy with practical feasibility in clinical environments. A systematic search following PRISMA guidelines was conducted for studies published between 2014 and 2025, encompassing deep learning, classical machine learning, hybrid, and semi-supervised approaches. The review examines how each methodological family performs in segmenting key anatomical structures such as blood vessels, the optic disc, and the fovea, considering both algorithmic and clinical metrics. Findings reveal that advanced deep learning models—particularly U-Net and CNN-based architectures—achieve superior accuracy in delineating complex and low-contrast structures but demand high computational resources. In contrast, traditional and hybrid methods offer efficient alternatives for real-time or low-resource settings, maintaining acceptable precision while minimizing cost. Importantly, the analysis underscores the persistent gap between methodological innovation and clinical translation, emphasizing the need for lightweight, clinically interpretable models that integrate algorithmic performance with medical relevance. Full article

Understory ginseng, with superior quality compared to field-cultivated varieties, is highly susceptible to diseases, which negatively impact both its yield and quality. Therefore, this paper proposes a lightweight, high-precision leaf spot segmentation model, Lightweight DeepLabv3+ with a StarNet Backbone and Attention-guided Gaussian Edge Enhancement (LD-SAGE). This study first introduces StarNet into the DeepLabv3+ framework to replace the Xception backbone, reducing the parameter count and computational complexity. Secondly, the Gaussian-Edge Channel Fusion module uses multi-scale Gaussian convolutions to smooth blurry areas, combining Scharr edge-enhanced features with a lightweight channel attention mechanism for efficient edge and semantic feature integration. Finally, the proposed Multi-scale Attention-guided Context Modulation module replaces the traditional Atrous Spatial Pyramid Pooling. It integrates Multi-scale Grouped Dilated Convolution, Convolutional Multi-Head Self-Attention, and dynamic modulation fusion. This reduces computational costs and improves the model’s ability to capture contextual information and texture details in disease areas. Experimental results show that the LD-SAGE model achieves an mIoU of 92.48%, outperforming other models in terms of precision and recall. The model’s parameter count is only 4.6% of the original, with GFLOPs reduced to 22.1% of the baseline model. Practical deployment experiments on the Jetson Orin Nano device further confirm the advantage of the proposed method in the real-time frame rate, providing support for the diagnosis of leaf diseases in understory ginseng. Full article

Focusing on visual target detection for Autonomous Underwater Vehicles (AUVs), this paper investigates enhancement methods for weakly illuminated underwater images, which typically suffer from blurring, color distortion, and non-uniform illumination. Although deep learning-based approaches have received considerable attention, existing methods still face limitations such as insufficient feature extraction, poor detail detection, and high computational costs. To address these issues, we propose RECAD—a lightweight and efficient underwater image enhancement method based on Retinex theory. The approach incorporates a dark region detection mechanism to significantly improve feature extraction from low-light areas, along with an efficient channel attention module to reduce computational complexity. A residual learning strategy is adopted in the image reconstruction stage to effectively preserve structural consistency, achieving an SSIM value of 0.91. Extensive experiments on the UIEB and LSUI benchmark datasets demonstrate that RECAD outperforms state-of-the-art models including FUnIEGAN and U-Transformer, achieving a high SSIM of 0.91 and competitive UIQM scores (up to 3.19), while improving PSNR by 3.77 dB and 0.69–1.09 dB, respectively, and attaining a leading inference speed of 97 FPS, all while using only 0.42 M parameters, which substantially reduces computational resource consumption. Full article

As port operations rapidly evolve toward intelligent and heavy-duty applications, fault diagnosis for core equipment demands higher levels of real-time performance and robustness. Deep learning, with its powerful autonomous feature learning capabilities, demonstrates significant potential in mechanical fault prediction and health management. This paper first provides a systematic review of deep learning research advances in rotating machinery fault diagnosis over the past eight years, focusing on the technical approaches and application cases of four representative models: Deep Belief Networks (DBNs), Convolutional Neural Networks (CNNs), Auto-encoders (AEs), and Recurrent Neural Networks (RNNs). These models, respectively, embody four core paradigms, unsupervised feature generation, spatial pattern extraction, data reconstruction learning, and temporal dependency modeling, forming the technological foundation of contemporary intelligent diagnostics. Building upon this foundation, this paper delves into the unique challenges encountered when transferring these methods from generic laboratory components to specialized port equipment such as shore cranes and yard cranes—including complex operating conditions, harsh environments, and system coupling. It further explores future research directions, including cross-condition transfer, multi-source information fusion, and lightweight deployment, aiming to provide theoretical references and implementation pathways for the technological advancement of intelligent operation and maintenance in port equipment. Full article

Industrial bearing surface defect detection faces challenges such as complex image backgrounds, multi-scale defects, and insufficient feature extraction. To address these issues, this paper proposes an improved YOLOv8-GSS defect detection method. Initially, the network substitutes the standard convolution in the C2f module and Concat module within the neck module with lightweight convolutions, GsConv, thereby reducing computational costs. Subsequently, to better capture and represent crucial features in the images, an SENetV2 attention mechanism is integrated before the SPPF module at the backbone end, effectively enhancing the model’s accuracy and robustness in defect detection. Finally, a self-built dataset of surface images of bearing rings collected from industrial sites is utilized as the basis for extensive experimentation. Experimental results show that the network achieves 97.8% AP50, with detection accuracy for large-, medium-, and small-scale defects improved by 2.4%, 3.6%, and 2.3%, respectively.2.3% respectively. The detection speed reaches 115 frames per second (FPS). Compared to mainstream surface defect detection algorithms, the proposed method exhibits significant improvements in both accuracy and detection speed. Full article

The diameter of the sunflower flower head and the thickness of its margins are important crop phenotypic parameters. Traditional, single-dimensional two-dimensional imaging methods often struggle to balance precision with computational efficiency. This paper addresses the limitations of the YOLOv11n-seg model in the instance segmentation of floral disk fine structures by proposing the MBLA-YOLO instance segmentation model, achieving both lightweight efficiency and high accuracy. Building upon this foundation, a non-contact measurement method is proposed that combines an improved model with three-dimensional point cloud analysis to precisely extract key structural parameters of the flower head. First, image annotation is employed to eliminate interference from petals and sepals, whilst instance segmentation models are used to delineate the target region; The segmentation results for the disc surface (front) and edges (sides) are then mapped onto the three-dimensional point cloud space. Target regions are extracted, and following processing, separate models are constructed for the disc surface and edges. Finally, with regard to the differences between the surface and edge structures, targeted methods are employed for their respective calculations. Whilst maintaining lightweight characteristics, the proposed MBLA-YOLO model achieves simultaneous improvements in accuracy and efficiency compared to the baseline YOLOv11n-seg. The introduced CKMB backbone module enhances feature modelling capabilities for complex structural details, whilst the LADH detection head improves small object recognition and boundary segmentation accuracy. Specifically, the CKMB module integrates MBConv and channel attention to strengthen multi-scale feature extraction and representation, while the LADH module adopts a tri-branch design for classification, regression, and IoU prediction, structurally improving detection precision and boundary recognition. This research not only demonstrates superior accuracy and robustness but also significantly reduces computational overhead, thereby achieving an excellent balance between model efficiency and measurement precision. This method avoids the need for three-dimensional reconstruction of the entire plant and multi-view point cloud registration, thereby reducing data redundancy and computational resource expenditure. Full article

Laser melting deposition (LMD), one of the novel powder-to-powder welding technologies, has emerged as an ideal method for fabricating lightweight high-temperature Ti₂AlNb alloy. However, the high thermal gradients and heat accumulation during the LMD process typically promote grain growth along the deposition direction, resulting in coarse columnar grains and high internal residual stress. This study investigates the influence of prolonged aging treatment and internal cyclic heat on the microstructure and mechanical properties of Ti₂AlNb alloys. Both long-term aging and internal cyclic heat induce the columnar-to-equiaxed grain morphology transition. A 48 h aging heat treatment at 750 °C facilitates the formation of a B2 + O dual-phase lamellar structure, leading to a significant improvement in room-temperature strength. Internal cyclic heat effectively reduces the cooling rate, eliminates internal stress, and suppresses the precipitation of the brittle and detrimental α₂ phase. This results in a more homogeneous distribution of O-phase laths, raising the room-temperature tensile strength from 938 MPa to 1215 MPa and achieving a high-temperature strength of 1116 MPa at 650 °C. These improvements demonstrate a synergistic enhancement in both room- and high-temperature strength and ductility, which provides an efficient strategy for in situ regulation of the microstructure and mechanical properties of laser-deposited Ti₂AlNb alloys. Full article

To address the challenges of low illumination, heavy dust, and severe occlusion in fully mechanized mining faces, this paper proposes a shearer drum detection algorithm named DCS-YOLO. To enhance the model’s ability to effectively capture features under drum deformation and occlusion, a C3k2_DCNv4 module based on deformable convolution (DCNv4) is incorporated into the network. This module adaptively adjusts convolution sampling points according to the drum’s size and position, enabling efficient and precise multi-scale feature extraction. To overcome the limitations of conventional convolution in global feature modeling, a convolution and attention fusion module (CAFM) is constructed, which combines lightweight convolution with attention mechanisms to selectively reweight feature maps at different resolutions. Under low-light conditions, the Shape-IoU loss function is employed to achieve accurate regression of irregular drum boundaries while considering both positional and shape similarity. In addition, GSConv is adopted to achieve model lightweighting while maintaining efficient feature extraction capability. Experiments were conducted on a dataset built from shearer drum images collected in underground coal mines. The results demonstrate that, compared with YOLOv11n, the proposed method reduces Params and Flops by 7.7% and 4.6%, respectively, while improving precision, recall, mAP@0.5, and mAP@0.5:0.95 by 2.9%, 3.2%, 1.1%, and 3.3%, respectively. These findings highlight the significant advantages of the proposed approach in both model lightweighting and detection performance. Full article

Background/Objectives: Cardiovascular disease remains a leading cause of death worldwide, with chest pain often serving as an initial reason for emergency visits. However, the severity of chest pain does not necessarily correlate with the severity of myocardial infarction. Facial expressions are an essential medium to convey the intensity of pain, particularly in patients experiencing speech difficulties. Automating the recognition of facial pain expression may therefore provide an auxiliary tool for monitoring chest pain without replacing clinical diagnosis. Methods: Using streaming technology, the system captures real-time facial expressions and classifies pain levels using a deep learning framework. The PSPI scores were incorporated with the YOLO models to ensure precise classification. Through extensive fine-tuning, we compare the performance of YOLO-series models, evaluating both computational efficiency and diagnostic accuracy rather than focusing solely on accuracy or processing time. Results: The custom YOLOv4 model demonstrated superior performance in pain level recognition, achieving a precision of 97% and the fastest training time. The system integrates a web-based interface with color-coded pain indicators, which can be deployed on smartphones and laptops for flexible use in healthcare settings. Conclusions: This study demonstrates the potential of automating pain assessment based on facial expressions to assist healthcare professionals in observing patient discomfort. Importantly, the approach does not infer the underlying cause of myocardial infarction. Future work will incorporate clinical metadata and a lightweight edge computing model to enable real-time pain monitoring in diverse care environments, which may support patient monitoring and assist in clinical observation. Full article

Background/Objectives: Strawberry crops are vulnerable to fungal diseases that severely affect yield and quality. Deep learning has shown strong potential for plant disease recognition; however, most architectures rely on tens of millions of parameters, limiting their use in low-resource agricultural settings. This study presents Light-MobileBerryNet, a lightweight and interpretable model designed to achieve accurate strawberry disease classification while remaining computationally efficient for potential use on mobile and edge devices. Methods: The model, inspired by MobileNetV3-Small, integrates inverted residual blocks, depthwise separable convolutions, squeeze-and-excitation modules, and Swish activation to enhance efficiency. A publicly available dataset was processed using CLAHE and data augmentation, and split into training, validation, and test subsets under consistent conditions. Performance was benchmarked against state-of-the-art CNNs. Results: Light-MobileBerryNet achieved 96.6% accuracy, precision, recall, and F1-score, with a Matthews correlation coefficient of 0.96, while requiring fewer than one million parameters (~2 MB). Grad-CAM confirmed that predictions focused on biologically relevant lesion regions. Conclusions: Light-MobileBerryNet approaches state-of-the-art performance with a fraction of the computational cost, providing a practical and interpretable solution for precision agriculture. Full article

In recent years, drone-based wildfire detection technology has advanced rapidly, yet existing methods still encounter numerous challenges. For instance, high background complexity leads to frequent false positives and false negatives in models, which struggle to accurately identify both small-scale fire points and large-scale wildfires simultaneously. Furthermore, the complex model architecture and substantial parameter count hinder lightweight deployment requirements for drone platforms. To this end, this paper presents a lightweight drone-based wildfire detection model, DFE-YOLO. This model utilizes dynamic frequency domain enhancement technology to resolve the aforementioned challenges. Specifically, this study enhances small object detection capabilities through a four-tier detection mechanism; improves feature representation and robustness against interference by incorporating a Dynamic Frequency Domain Enhancement Module (DFDEM) and a Target Feature Enhancement Module (C2f_CBAM); and significantly reduces parameter count via a multi-scale sparse sampling module (MS3) to address resource constraints on drones. Experimental results demonstrate that DFE-YOLO achieves mAP50 scores of 88.4% and 88.0% on the Multiple lighting levels and Multiple wildfire objects Synthetic Forest Wildfire Dataset (M4SFWD) and Fire-detection datasets, respectively, whilst reducing parameters by 23.1%. Concurrently, mAP50-95 reaches 50.6% and 63.7%. Comprehensive results demonstrate that DFE-YOLO surpasses existing mainstream detection models in both accuracy and efficiency, providing a reliable solution for wildfire monitoring via unmanned aerial vehicles. Full article

Vertical axis wind turbines (VAWTs) have significant potential for renewable energy generation, yet their operational efficiency is often limited by reduced aerodynamic performance and difficulties during start-up. This study investigates the effect of passive flow control and material selection on the performance of H-Darrieus VAWT blades, with the aim of identifying design solutions that enhance start-up dynamics and overall efficiency. Two-dimensional numerical simulations were conducted using the Dynamic Mesh method with six degrees of freedom (6DOF) in ANSYS 19.2 Fluent, enabling a time-resolved assessment of rotor behavior under constant wind velocities. Two blade configurations were analyzed: a baseline NACA0012 geometry and a modified profile with inclined cavities on the extrados. In addition, the influence of blade material was examined by comparing 3D-printed resin blades with lighter 3D-printed polycarbonate blades. The results demonstrate that cavity-modified blades provide superior performance compared to the baseline, showing faster acceleration, higher tip speed ratios, and improved power coefficients, particularly at higher wind velocities. Furthermore, polycarbonate blades achieved more efficient energy conversion than resin blades, highlighting the importance of material properties in turbine optimization. These findings confirm that combining passive flow control strategies with advanced lightweight materials can significantly improve the aerodynamic and dynamic performance of VAWTs, offering valuable insights for future experimental validation and prototype development. Full article

Background: Knowledge distillation (KD) compresses deep neural networks by transferring knowledge from a high-capacity teacher model to a lightweight student model. However, conventional evaluation metrics such as accuracy, mAP, IoU, or RMSE focus mainly on task performance and overlook how effectively the student internalizes the teacher’s knowledge. Methods: This study introduces the Knowledge Retention Score (KRS), a composite metric that integrates intermediate feature similarity and output agreement into a single interpretable score to quantify knowledge retention. KRS was primarily validated in computer vision (CV) through 36 experiments covering image classification, object detection, and semantic segmentation using diverse datasets and eight representative KD methods. Supplementary experiments were conducted in natural language processing (NLP) using transformer-based models on SST-2, and in time series regression with convolutional teacher–student pairs. Results: Across all domains, KRS correlated strongly with standard performance metrics while revealing internal retention dynamics that conventional evaluations often overlook. By reporting feature similarity and output agreement separately alongside the composite score, KRS provides transparent and interpretable insights into knowledge transfer. Conclusions: KRS offers a stable diagnostic tool and a complementary evaluation metric for KD research. Its generality across domains demonstrates its potential as a standardized framework for assessing knowledge retention beyond task-specific performance measures. Full article

To address circularity and resource recovery in modern structural applications, industry is seeking materials that are sustainable and lightweight. Although natural fiber-reinforced composites offer sustainability advantages, their mechanical properties remain inferior to those of synthetic fiber systems, limiting practical deployment. Flax fibers were selected as reinforcement due to their high specific stiffness, biodegradability, and wide availability. This study implements a three-level strategy to enhance the flexural performance of flax fiber-reinforced composites: at the process level, curing under distinct heating rates to promote a more uniform polymer network; at the material level, incorporation of a carbonaceous additive derived from fuel–oil furnace waste to strengthen interfacial adhesion; and at the structural level, adoption of a sandwich configuration with a recycled PET core to increase section bending inertia. Specimens were fabricated via vacuum-assisted resin transfer molding (VARTM) and tested using a three-point bending method. Mechanical testing shows clear improvements in flexural performance, with the sandwich architecture yielding the highest values and increasing flexural strength by up to 4.52 × relative to the other conditions. For the curing series, FTIR indicates greater reaction extent, evidenced by lower intensities of the epoxide ring at 915 cm⁻¹ and glycidyl/oxirane band near 972 cm⁻¹, together with a more pronounced C–O–C stretching region, consistent with the higher flexural response. While SEM observations revealed interfacial debonding at 5% FCB, a hybrid mechanism with crack deflection appeared at 10%. This transition created tortuous crack paths, consistent with the higher flexural strength and modulus at 10% FCB. A distinctive feature of this work is the integration of three reinforcement strategies—controlled curing, waste-derived carbon additive, and recycled PET sandwich design. This integration not only enhances the performance of natural fiber composites but also emphasizes sustainability by valorizing recycled and waste-derived resources, thereby supporting the development of greener composite materials. Full article