Search Results (1,404)

Background/Objectives: Endometriosis is a chronic inflammatory condition that often requires laparoscopic examination for definitive diagnosis. Automated analysis of laparoscopic images using Deep Learning (DL) may support clinicians by improving diagnostic consistency and efficiency. This study aimed to develop and evaluate explainable DL models for the binary classification of endometriosis using laparoscopic images from the publicly available GLENDA (Gynecologic Laparoscopic ENdometriosis DAtaset). Methods: Four representative architectures—ResNet50, EfficientNet-B2, EdgeNeXt_Small, and Vision Transformer (ViT-Small/16)—were systematically compared under class-imbalanced conditions using five-fold cross-validation. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) and SHapley Additive exPlanations (SHAP) were applied for visual explanation, and their quantitative alignment with expert-annotated lesion masks was assessed using Intersection over Union (IoU), Dice coefficient, and Recall. Results: Among the evaluated models, EdgeNeXt_Small achieved the best trade-off between classification performance and computational efficiency. Grad-CAM produced spatially coherent visualizations that corresponded well with clinically relevant lesion regions. Conclusions: The study shows that lightweight convolutional neural network (CNN)–Transformer architectures, combined with quantitative explainability assessment, can identify endometriosis in laparoscopic images with reasonable accuracy and interpretability. These findings indicate that explainable AI methods may help improve diagnostic consistency by offering transparent visual cues that align with clinically relevant regions. Further validation in broader clinical settings is warranted to confirm their practical utility. Full article

Deep learning has transformed numerous areas of data science by achieving outstanding performance in tasks such as image recognition, speech processing, and natural language understanding. Recently, the challenges of financial forecasting—marked by nonlinear dynamics, volatility, and regime shifts—have attracted increasing attention from the deep learning community. Among these approaches, Convolutional Neural Networks (CNNs), originally developed for spatial data, have shown strong potential for modelling financial time series. This study presents an interpretable CNN-based framework for stock price forecasting using the S&P 500 index as a case study. The proposed approach integrates historical price data with technical indicators within a unified experimental design and compares performance against traditional statistical (ARIMA) and sequential deep learning (LSTM) baselines. Empirical results demonstrate that the CNN model achieves superior predictive Accuracy while maintaining computational efficiency and interpretability through SHAP and Grad-CAM analyses. The findings suggest that lightweight CNN architectures can serve as effective, transparent tools for short-horizon financial forecasting, and future research may extend this framework to multimodal settings incorporating sentiment or news-based data. Full article

George Town, the capital of Penang, Malaysia, was inscribed as a UNESCO World Heritage Site in 2008 and is renowned for its multicultural architectural surfaces. However, these historic façades face significant deterioration challenges, particularly biodeterioration caused by weed growth on wall surfaces under hot and humid equatorial conditions. Root penetration is a critical surface defect, accelerating mortar decay and threatening structural integrity. To address this issue, this study proposes YOLOv11-SWDS (Surface Weed Detection System), a lightweight and interpretable deep learning framework tailored for surface defect detection in the form of weed intrusion on heritage buildings. The backbone network was redesigned to enhance the extraction of fine-grained features from visually cluttered surfaces, while attention modules improved discrimination between weed patterns and complex textures such as shadows, stains, and decorative reliefs. For practical deployment, the model was optimized through quantization and knowledge distillation, significantly reducing computational cost while preserving detection accuracy. Experimental results show that YOLOv11-SWDS achieved an F1 score of 86.0% and a mAP@50 of 89.7%, surpassing baseline models while maintaining inference latency below 200 ms on edge devices. These findings demonstrate the potential of deep learning-based non-destructive detection for monitoring surface defects in heritage conservation, offering both a reliable tool for sustaining George Town’s cultural assets and a transferable solution for other UNESCO heritage sites. Full article

UAV object detection is still difficult to achieve due to large-scale variation, dense small objects, a complicated background, and resource constraints from onboard computing. To solve these problems, we develop a diffusion-enhanced detection network, DL-DEIM, tailored for aerial images. The proposed scheme generalizes the DEIM baseline across three orthogonal axes. First, we propose a lightweight backbone network called DCFNet, which utilizes a DRFD module and a FasterC3k2 module to maintain spatial information and reduce computational complexity. Second, we propose a LFDPN module, which can conduct bidirectional multi-scale fusion via frequency-spatial self-attention and deep feature refinement and largely enhance cross-scale contextual propagation for small objects. Third, we propose LAWDown, an adaptive-content-aware downsampling to preserve the discriminative representation with higher accuracy at lower resolutions, which can effectively capture the spatially-variant weights and group channel interactions. On the VisDrone2019 dataset, DL-DEIM achieves a mAP@0.5 of 34.9% and a mAP@0.5:0.95 of 20.0%, outperforming the DEIM baseline by +4.6% and +2.9%, respectively. The model maintains real-time inference speed (356 FPS) with only 4.64 M parameters and 11.73 GFLOPs. Ablation studies validate the fact that DCFNet, LFDPN, and LAWDown collaboratively contribute to the accuracy and efficiency. Visualizations also display clustered and better localized activation in crowded scenes. These results show that DL-DEIM achieves a good tradeoff between detection probability and computation burden and it can be used in practice on resource-limited UAV systems. Full article

Crack segmentation in cluttered scenes with slender and irregular patterns remains difficult, and practical systems must balance accuracy and efficiency. We present CONTI-CrackNet, which is a lightweight visual state-space network that integrates a Multi-Directional Selective Scanning Strategy (MD3S). MD3S performs bidirectional scanning along the horizontal, vertical, and diagonal directions, and it fuses the complementary paths with a Bidirectional Gated Fusion (BiGF) module to strengthen global continuity. To preserve fine details while completing global texture, we propose a Dual-Branch Pixel-Level Global–Local Fusion (DBPGL) module that incorporates a Pixel-Adaptive Pooling (PAP) mechanism to dynamically weight max-pooled responses and average-pooled responses. Evaluated on two public benchmarks, the proposed method achieves an F1 score (F1) of 0.8332 and a mean Intersection over Union (mIoU) of 0.8436 on the TUT dataset, and it achieves an mIoU of 0.7760 on the CRACK500 dataset, surpassing competitive Convolutional Neural Network (CNN), Transformer, and Mamba baselines. With 512 × 512 input, the model requires 24.22 G floating point operations (GFLOPs), 6.01 M parameters (Params), and operates at 42 frames per second (FPS) on an RTX 3090 GPU, delivering a favorable accuracy–efficiency balance. These results show that CONTI-CrackNet improves continuity and edge recovery for thin cracks while keeping computational cost low, and it is lightweight in terms of parameter count and computational cost. Full article

Pneumonia remains a major global health concern, particularly among pediatric populations in low-resource settings where radiological expertise is limited. This study investigates the enhancement of deep convolutional neural networks (CNNs) for automated pneumonia diagnosis from chest X-ray images through the integration of a novel module combining Inception blocks, Mish activation, and Batch Normalization (IncMB). Four state-of-the-art transfer learning models—InceptionV3, InceptionResNetV2, MobileNetV2, and DenseNet201—were evaluated in their base form and with the proposed IncMB extension. Comparative analysis based on standardized classification metrics reveals consistent performance improvements across all models with the addition of the IncMB module. The most notable improvement was observed in InceptionResNetV2, where the IncMB-enhanced model achieved the highest accuracy of 0.9812, F1-score of 0.9761, precision of 0.9781, recall of 0.9742, and strong specificity of 0.9590. Other models also demonstrated similar trends, confirming that the IncMB module contributes to better generalization and discriminative capability. These enhancements were achieved while reducing the total number of parameters, indicating improved computational efficiency. In conclusion, the integration of IncMB significantly boosts the performance of CNN-based pneumonia classifiers, offering a promising direction for the development of lightweight, high-performing diagnostic tools suitable for real-world clinical application, particularly in underserved healthcare environments. Full article

The Vehicular Internet of Things (V-IoT) has emerged as a cornerstone of next-generation intelligent transportation systems (ITSs), enabling applications ranging from safety-critical collision avoidance and cooperative awareness to infotainment and fleet management. These heterogeneous services impose stringent quality-of-service (QoS) demands for latency, reliability, and fairness while competing for limited and dynamically varying spectrum resources. Conventional schedulers, such as round-robin or static priority queues, lack adaptability, whereas deep reinforcement learning (DRL) solutions, though powerful, remain computationally intensive and unsuitable for real-time roadside unit (RSU) deployment. This paper proposes a lightweight and interpretable reinforcement learning (RL)-based spectrum management framework for Vehicular Internet of Things (V-IoT) networks. Two enhanced Q-Learning variants are introduced: a Value-Prioritized Action Double Q-Learning with Constraints (VPADQ-C) algorithm that enforces reliability and blocking constraints through a Constrained Markov Decision Process (CMDP) with online primal–dual optimization, and a contextual Q-Learning with Upper Confidence Bound (Q-UCB) method that integrates uncertainty-aware exploration and a Success-Rate Prior (SRP) to accelerate convergence. A Risk-Aware Heuristic baseline is also designed as a transparent, low-complexity benchmark to illustrate the interpretability–performance trade-off between rule-based and learning-driven approaches. A comprehensive simulation framework incorporating heterogeneous traffic classes, physical-layer fading, and energy-consumption dynamics is developed to evaluate throughput, delay, blocking probability, fairness, and energy efficiency. The results demonstrate that the proposed methods consistently outperform conventional Q-Learning and Double Q-Learning methods. VPADQ-C achieves the highest energy efficiency (≈$8.425\times {10}^7$ bits/J) and reduces interruption probability by over $60\%$, while Q-UCB achieves the fastest convergence (within ≈190 episodes), lowest blocking probability (≈0.0135), and lowest mean delay (≈0.351 ms). Both schemes maintain fairness near $0.364$, preserve throughput around 28 Mbps, and exhibit sublinear training-time scaling with $\mathcal{O}\left(1\right)$ per-update complexity and $\mathcal{O}\left(N^2\right)$ overall runtime growth. Scalability analysis confirms that the proposed frameworks sustain URLLC-grade latency (<0.2 ms) and reliability under dense vehicular loads, validating their suitability for real-time, large-scale V-IoT deployments. Full article

Coal block image segmentation is of great significance for obtaining the particle size distribution and specific gravity information of ores. However, the existing methods are limited by harsh environments, such as dust, complex shapes, and the uneven distribution of light, color and texture. To address these challenges, based on the backbone of the U-Net encoder and decoder, and combining the characteristics of dilated convolution and inverted residual structures, we propose a lightweight deep convolutional network (DIRU-Net) for coal block image segmentation. We have also constructed a high-quality dataset of conveyor belt coal block images, solving the problem that there are currently no publicly available datasets. We comprehensively evaluated DIRU-Net in the coal block dataset and compared it with other state-of-the-art coal block segmentation methods. DIRU-Net outperforms all methods in terms of segmentation performance and lightweight. Among them, the segmentation accuracy rate reaches 94.8%, and the parameter size is only 0.77 MB. Full article

Hyperspectral imagers on satellites obtain the fine spectral signatures that are essential in distinguishing one material from another but at the expense of a limited spatial resolution. Enhancing the latter is thus a desirable preprocessing step in order to further improve the detection capabilities offered by hyperspectral images for downstream tasks. At the same time, there is growing interest in deploying inference methods directly onboard satellites, which calls for lightweight image super-resolution methods that can be run on the payload in real time. In this paper, we present a novel neural network design, called Deep Pushbroom Super-Resolution (DPSR), which matches the pushbroom acquisition of hyperspectral sensors by processing an image line by line in the along-track direction with a causal memory mechanism to exploit previously acquired lines. This design greatly limits the memory requirements and computational complexity, achieving onboard real-time performance, i.e., the ability to super-resolve a line in the time that it takes to acquire the next one, on low-power hardware. Experiments show that the quality of the super-resolved images is competitive with or even surpasses that of state-of-the-art methods that are significantly more complex. Full article

As global agriculture shifts to intelligence and precision, crop attribute detection has become foundational for intelligent systems (harvesters, UAVs, sorters). It enables real-time monitoring of key indicators (maturity, moisture, disease) to optimize operations—reducing crop losses by 10–15% via precise cutting height adjustment—and boosts resource-use efficiency. This review targets harvesting-stage and in-field monitoring for grains, fruits, and vegetables, highlighting practical technologies: near-infrared/Raman spectroscopy (non-destructive internal attribute detection), 3D vision/LiDAR (high-precision plant height/density/fruit location measurement), and deep learning (YOLO for counting, U-Net for disease segmentation). It addresses universal field challenges (lighting variation, target occlusion, real-time demands) and actionable fixes (illumination compensation, sensor fusion, lightweight AI) to enhance stability across scenarios. Future trends prioritize real-world deployment: multi-sensor fusion (e.g., RGB + thermal imaging) for comprehensive perception, edge computing (inference delay < 100 ms) to solve rural network latency, and low-cost solutions (mobile/embedded device compatibility) to lower smallholder barriers—directly supporting scalable precision agriculture and global sustainable food production. Full article

Background: Renal Cell Carcinoma (RCC) is the most common type of kidney cancer and requires accurate histopathological grading for effective prognosis and treatment planning. However, manual grading is time-consuming, subjective, and susceptible to inter-observer variability. Objective: This study proposes EAT-Net (Efficient Attention Transformer Network), a dual-stream deep learning model designed to automate and enhance RCC grade classification from histopathological images. Method: EAT-Net integrates EfficientNetB0 for local feature extraction and a Vision Transformer (ViT) stream for capturing global contextual dependencies. The architecture incorporates Squeeze-and-Excitation (SE) modules to recalibrate feature maps, improving focus on informative regions. The model was trained and evaluated on two publicly available datasets, KMC-RENAL and RCCG-Net. Standard preprocessing was applied, and the model’s performance was assessed using accuracy, precision, recall, and F1-score. Results: EAT-Net achieved superior results compared to state-of-the-art models, with an accuracy of 92.25%, precision of 92.15%, recall of 92.12%, and F1-score of 92.25%. Ablation studies demonstrated the complementary value of the EfficientNet and ViT streams. Additionally, Grad-CAM visualizations confirmed that the model focuses on diagnostically relevant areas, supporting its interpretability and clinical relevance. Conclusion: EAT-Net offers an accurate, and explainable framework for RCC grading. Its lightweight architecture and high performance make it well-suited for clinical deployment in digital pathology workflows. Full article

Rice, a dietary staple for over half of the global population, is highly susceptible to bacterial and fungal diseases such as bacterial blight, brown spot, and leaf smut, which can severely reduce yields. Traditional manual detection is labor-intensive and often results in delayed intervention and excessive chemical use. Although deep learning models like convolutional neural networks (CNNs) achieve high accuracy, their computational demands hinder deployment in resource-limited agricultural settings. We propose MCP-X, an ultra-compact CNN with only 0.21 million parameters for real-time, on-device rice disease classification. MCP-X integrates a shallow encoder, multi-branch expert routing, a bi-level recurrent simulation encoder–decoder (BRSE), an efficient channel attention (ECA) module, and a lightweight classifier. Trained from scratch, MCP-X achieves 98.93% accuracy on PlantVillage and 96.59% on the Rice Disease Detection Dataset, without external pretraining. Mechanistically, expert routing diversifies feature branches, ECA enhances channel-wise signal relevance, and BRSE captures lesion-scale and texture cues—yielding complementary, stage-wise gains confirmed through ablation studies. Despite slightly higher FLOPs than MobileNetV2, MCP-X prioritizes a minimal memory footprint (~1.01 MB) and deployability over raw speed, running at 53.83 FPS (2.42 GFLOPs) on an RTX A5000. It achieves 16.7×, 287×, 420×, and 659× fewer parameters than MobileNetV2, ResNet152V2, ViT-Base, and VGG-16, respectively. When integrated into a multi-resolution ensemble, MCP-X attains 99.85% accuracy, demonstrating exceptional robustness across controlled and field datasets while maintaining efficiency for real-world agricultural applications. Full article

Memory forensics is an essential cybersecurity tool that comprehensively examines volatile memory to detect the malicious activity of fileless malware that can bypass disk analysis. Image-based detection techniques provide a promising solution by visualizing memory data into images to be used and analyzed by image processing tools and machine learning methods. However, the effectiveness of image-based data for detection and classification requires high computational efforts. This paper investigates the efficacy of texture-based methods in detecting and classifying memory-resident or fileless malware using different image resolutions, identifying the best feature descriptors, classifiers, and resolutions that accurately classify malware into specific families and differentiate them from benign software. Moreover, this paper uses both local and global descriptors, where local descriptors include Oriented FAST and Rotated BRIEF (ORB), Scale-Invariant Feature Transform (SIFT), and Histogram of Oriented Gradients (HOG) and global descriptors include Discrete Wavelet Transform (DWT), GIST, and Gray Level Co-occurrence Matrix (GLCM). The results indicate that as image resolution increases, most feature descriptors yield more discriminative features but require higher computational efforts in terms of time and processing resources. To address this challenge, this paper proposes a novel approach that integrates Local Interpretable Model-agnostic Explanations (LIME) with deep learning models to automatically identify and crop the most important regions of memory images. The LIME’s ROI was extracted based on ResNet50 and MobileNet models’ predictions separately, the images were resized to 128 × 128, and the sampling process was performed dynamically to speed up LIME computation. The ROIs of the images are cropped to new images with sizes of (100 × 100) in two stages: the coarse stage and the fine stage. The two generated LIME-based cropped images using ResNet50 and MobileNet are fed to the lightweight neural network to evaluate the effectiveness of the LIME-based identified regions. The results demonstrate that the LIME-based MobileNet model’s prediction improves the efficiency of the model by preserving important features with a classification accuracy of 85% on multi-class classification. Full article

The application of efficient optical-electrical sorting technology for the automatic separation of copper mine waste rocks not only enables the recovery of valuable copper metals and promotes the resource utilization of non-ferrous mine waste, but also conserves large areas of land otherwise used for waste disposal and alleviates associated environmental issues. However, the process is challenged by the low copper content, fine dissemination of copper-bearing minerals, and complex mineral composition and associated relationships. To address these challenges, this study leverages dual-energy X-ray imaging and multimodal learning, proposing a lightweight twin-tower convolutional neural network (CNN) designed to fuse high- and low-energy spectral information for the automated sorting of copper mine waste rocks. Additionally, the study integrates an emerging Kolmogorov-Arnold network as a classifier to enhance the sorting performance. To validate the efficacy of our approach, a dataset comprising 31,057 pairs of copper mine waste rock images with corresponding high- and low-energy spectra was meticulously compiled. The experimental results demonstrate that the proposed lightweight method achieves competitive, if not superior, performance compared to contemporary mainstream deep learning networks, yet it requires merely 1.32 million parameters (only 6.2% of ResNet-34), thereby indicating extensive potential for practical deployment. Full article

Dermoscopy, a non-invasive imaging technique, has transformed dermatology by enabling early detection and differentiation of skin conditions. Integrating deep learning with dermoscopic images enhances diagnostic potential but raises computational challenges. This study introduces APNet, an attention-based architecture designed for melanoma detection, offering fewer parameters than conventional convolutional neural networks. Two baseline models are considered: HU-Net, a trimmed U-Net that uses only the encoding path for classification, and Pocket-Net, a lightweight U-Net variant that reduces parameters through fewer feature maps and efficient convolutions. While Pocket-Net is highly resource-efficient, its simplification can reduce performance. APNet extends Pocket-Net by incorporating squeeze-and-excitation (SE) attention blocks into the encoding path. These blocks adaptively highlight the most relevant dermoscopic features, such as subtle melanoma patterns, improving classification accuracy. The study evaluates APNet against Pocket-Net and HU-Net using four large, annotated dermoscopy datasets (ISIC 2017–2020), covering melanoma, benign nevi, and other lesions. Results show that APNet achieves faster processing than HU-Net while overcoming the performance loss observed in Pocket-Net. By reducing parameters without sacrificing accuracy, APNet provides a practical solution for computationally demanding dermoscopy, offering efficient and accurate melanoma detection where medical imaging resources are limited. Full article