Search Results (1,500)

Stroke often leads to severe motor impairment, especially in the upper limbs, greatly reducing a patient’s ability to perform daily tasks. Effective rehabilitation is essential to restore function and improve quality of life. Traditional therapies, while useful, may lack engagement, leading to low motivation and poor adherence. Gamification—using game-like elements in non-game contexts—offers a promising way to make rehabilitation more engaging. The authors explore a gamified rehabilitation system designed in Unity 3D using a Kinect V2 camera. The game includes key features such as adjustable difficulty, real-time and predominantly positive feedback, user friendliness, and data tracking for progress. The evaluations were conducted with 18 healthy participants, most of whom had prior virtual reality experience. About 77% found the application highly motivating. While the gameplay was well received, the visual design was noted as lacking engagement. Importantly, all users agreed that the game offers a broad range of difficulty levels, making it accessible to various users. The results suggest that the system has strong potential to improve rehabilitation outcomes and encourage long-term use through enhanced motivation and interactivity. Full article

Alzheimer’s disease (AD) involves the accumulation of amyloid-β (Aβ) plaques, whose quantification plays a central role in understanding disease progression. Automated segmentation of Aβ deposits in histopathological micrographs enables large-scale analyses but is hindered by the high cost of detailed pixel-level annotations. Weakly supervised learning offers a promising alternative by leveraging coarse or indirect labels to reduce the annotation burden. We evaluated a weakly supervised approach to segment and analyze thioflavin-S-positive parenchymal amyloid pathology in AD and age-matched brains. Our pipeline integrates three key components, each designed to operate under weak supervision. First, robust preprocessing (including retrospective multi-image illumination correction and gradient-based background estimation) was applied to enhance image fidelity and support training, as models rely more on image features. Second, class activation maps (CAMs), generated by a compact deep classifier SqueezeNet, were used to identify, and coarsely localize amyloid-rich parenchymal regions from patch-wise image labels, serving as spatial priors for subsequent refinement without requiring dense pixel-level annotations. Third, a patch-based convolutional neural network, U-Net, was trained on synthetic data generated from micrographs based on CAM-derived pseudo-labels via an extensive object-level augmentation strategy, enabling refined whole-image semantic segmentation and generalization across diverse spatial configurations. To ensure robustness and unbiased evaluation, we assessed the segmentation performance of the entire framework using patient-wise group k-fold cross-validation, explicitly modeling generalization across unseen individuals, critical in clinical scenarios. Despite relying on weak labels, the integrated pipeline achieved strong segmentation performance with an average Dice similarity coefficient (≈0.763) and Jaccard index (≈0.639), widely accepted metrics for assessing segmentation quality in medical image analysis. The resulting segmentations were also visually coherent, demonstrating that weakly supervised segmentation is a viable alternative in histopathology, where acquiring dense annotations is prohibitively labor-intensive and time-consuming. Subsequent morphometric analyses on automatically segmented Aβ deposits revealed size-, structural complexity-, and global geometry-related differences across brain regions and cognitive status. These findings confirm that deposit architecture exhibits region-specific patterns and reflects underlying neurodegenerative processes, thereby highlighting the biological relevance and practical applicability of the proposed image-processing pipeline for morphometric analysis. Full article

Purpose: To assess the performance of 2D T2-weighted (w) Turbo Spin Echo (TSE) MRI reconstructed with a deep learning (DL)-powered super resolution reconstruction (SRR) algorithm combining compressed sensing (CS) denoising and resolution upscaling for high-resolution hippocampal imaging in patients with (epileptic) seizures and suspected hippocampal pathology. Methods: A 2D T2w TSE coronal hippocampal sequence with compressed sense (CS) factor 1 (scan time 270 s) and a CS-accelerated sequence with a CS factor of 3 (scan time 103 s) were acquired in 28 patients. Reconstructions using the SRR algorithm (CS 1-SSR-s and CS 3-SSR-s) were additionally obtained in real time. Two readers graded the images twice, based on several metrics (image quality; artifacts; visualization of anatomical details of the internal hippocampal architecture (HIA); visibility of dentate gyrus/pes hippocampi/fornix/mammillary bodies; delineation of gray and white matter). Results: Inter-readout agreement was almost perfect (Krippendorff’s alpha coefficient = 0.933). Compared to the CS 1 sequence, the CS 3 sequence significantly underperformed in all 11 metrics (p < 0.001-p = 0.04), while the CS 1-SRR-s sequence outperformed in terms of overall image quality and visualization of the left HIA and right pes hippocampi (p < 0.001-p < 0.04) but underperformed in terms of presence of artifacts (p < 0.01). Lastly, relative to the CS 1 sequence, the CS 3-SRR-s sequence was graded worse in terms of presence of artifacts (p < 0.003) but with improved visualization of the right pes hippocampi (p = 0.02). Conclusion: DL-powered SSR demonstrates its capacity to enhance imaging performance by introducing flexibility in T2w hippocampal imaging; it either improves image quality for non-accelerated imaging or preserves acceptable quality in accelerated imaging, with the additional benefit of a reduced scan time. Full article

Crop disease identification is a pivotal research area in smart agriculture, forming the foundation for disease mapping and targeted prevention strategies. Among the most prevalent global wheat diseases, powdery mildew—caused by fungal infection—poses a significant threat to crop yield and quality, making early and accurate detection crucial for effective management. In this study, we present QY-SE-MResNet34, a deep learning-based classification model that builds upon ResNet34 to perform multi-class classification of wheat leaf images and assess powdery mildew severity at the single-leaf level. The proposed methodology begins with dataset construction following the GBT 17980.22-2000 national standard for powdery mildew severity grading, resulting in a curated collection of 4248 wheat leaf images at the grain-filling stage across six severity levels. To enhance model performance, we integrated transfer learning with ResNet34, leveraging pretrained weights to improve feature extraction and accelerate convergence. Further refinements included embedding a Squeeze-and-Excitation (SE) block to strengthen feature representation while maintaining computational efficiency. The model architecture was also optimized by modifying the first convolutional layer (conv1)—replacing the original 7 × 7 kernel with a 3 × 3 kernel, adjusting the stride to 1, and setting padding to 1—to better capture fine-grained leaf textures and edge features. Subsequently, the optimal training strategy was determined through hyperparameter tuning experiments, and GrabCut-based background processing along with data augmentation were introduced to enhance model robustness. In addition, interpretability techniques such as channel masking and Grad-CAM were employed to visualize the model’s decision-making process. Experimental validation demonstrated that QY-SE-MResNet34 achieved an 89% classification accuracy, outperforming established models such as ResNet50, VGG16, and MobileNetV2 and surpassing the original ResNet34 by 11%. This study delivers a high-performance solution for single-leaf wheat powdery mildew severity assessment, offering practical value for intelligent disease monitoring and early warning systems in precision agriculture. Full article

Background/Objectives: Total knee arthroplasty (TKA) is an effective surgical intervention for end stage knee osteoarthritis in elderly patients, with emerging robotically assisted techniques aiming to enhance surgical precision and patient outcomes. This study aimed to compare medium-term balance and functional outcomes between robotically assisted and conventional manual TKA in community-dwelling elderly patients. Methods: This cross-sectional study included 50 elderly patients undergoing TKA, who were divided into robotically assisted (n = 25) and conventional manual (n = 25) groups. Demographic and clinical data, balance performance, and functional outcomes were compared at nearly 1.5 years postoperatively. Outcome measures included balance performance assessed by the Berg Balance Scale (BBS), pain via the Visual Analog Scale (VAS), knee function as measured by the Lysholm Knee Scoring Scale, quality of life using the Short Form-12 (SF-12), joint awareness as evaluated by the Forgotten Joint Score-12 (FJS-12), and surgical satisfaction. Results: The groups had similar demographic and clinical data regarding age, gender, follow-up duration, surgical time, and anesthesia type (p > 0.05). The robotically assisted group demonstrated better balance performance on the BBS (p = 0.043) and had a statistically shorter length of hospital stay (1.22 vs. 1.42 days; p = 0.005). However, no statistically significant differences were observed in VAS activity pain (p = 0.053), Lysholm Knee Scoring Scale (p = 0.117), SF-12 physical and mental scores (p = 0.174 and p = 0.879), FJS-12 (p = 0.760), and surgical satisfaction (p = 0.218). Conclusions: Robotically assisted TKA is associated with advantageous postoperative recovery, particularly in terms of balance performance, showing no clinical difference in other functional outcomes compared to the conventional manual technique. From a physical therapy perspective, these findings emphasize the importance of developing tailored and effective rehabilitation strategies in the medium term for functional recovery in the elderly population. Full article

Single-image super-resolution (SISR) plays a critical role in enhancing visual quality for real-world applications, including industrial inspection and embedded vision systems. While deep learning-based approaches have made significant progress in SR, existing lightweight SR models often fail to accurately reconstruct high-frequency textures, especially under complex degradation scenarios, resulting in blurry edges and structural artifacts. To address this challenge, we propose a Dense Residual Fused Attention Network (DRFAN), a novel lightweight hybrid architecture designed to enhance high-frequency texture recovery in challenging degradation conditions. Moreover, by coupling convolutional layers and attention mechanisms through gated interaction modules, the DRFAN enhances local details and global dependencies with linear computational complexity, enabling the efficient utilization of multi-level spatial information while effectively alleviating the loss of high-frequency texture details. To evaluate its effectiveness, we conducted ×4 super-resolution experiments on five public benchmarks. The DRFAN achieves the best performance among all compared lightweight models. Visual comparisons show that the DRFAN restores more accurate geometric structures, with up to +1.2 dB/+0.0281 SSIM gain over SwinIR-S on Urban100 samples. Additionally, on a domain-specific rice grain dataset, the DRFAN outperforms SwinIR-S by +0.19 dB in PSNR and +0.0015 in SSIM, restoring clearer textures and grain boundaries essential for industrial quality inspection. The proposed method provides a compelling balance between model complexity and image reconstruction fidelity, making it well-suited for deployment in resource-constrained visual systems and industrial applications. Full article

Accurate geospatial data are essential for intelligent transportation systems and automated reporting applications, as location precision directly impacts safety analysis and decision-making. GPS devices are now routinely employed by law enforcement officers when filing vehicle crash reports, yet our investigation reveals that significant data quality issues persist. The high apparent precision of GPS coordinates belies their actual accuracy as we find that approximately 20% of crash sites need correction—results consistent with existing research. To address this challenge, we present a novel credibility scoring and correction algorithm that leverages a state-of-the-art multimodal large language model (LLM) capable of integrated visual and textual reasoning. Our framework synthesizes information from structured coordinates, crash diagrams, and narrative text, employing advanced artificial intelligence techniques for comprehensive geospatial validation. In addition to the LLM, our system incorporates open geospatial data from Overture Maps, an emerging collaborative mapping initiative, to enhance the spatial accuracy and robustness of the validation process. This solution was developed as part of research leading to a patent for autonomous vehicle routing systems that require high-precision crash location data. Applied to a dataset of 5000 crash reports, our approach systematically identifies records with location discrepancies requiring correction. By uniting the latest developments in multimodal AI and open geospatial data, our solution establishes a foundation for intelligent data validation in electronic reporting systems, with broad implications for automated infrastructure management and autonomous vehicle applications. Full article

A high intake of saturated fats and cholesterol from processed meats is associated with increased cardiovascular disease risk. This study aimed to develop a nutritionally enhanced Bologna-type sausage by partially replacing the beef content with a structured emulsion gel (EG) formulated from pine nut oil, inulin, carrageenan, and whey protein concentrate. The objective was to improve its lipid quality and functional performance while maintaining product integrity and consumer acceptability. Three sausage formulations were prepared: a control and two variants with 7% and 10% EG, which substituted for the beef content. The emulsion gel was characterized regarding its physical and thermal stability. Sausages were evaluated for their proximate composition, fatty acid profile, cholesterol content, pH, cooking yield, water-holding capacity, emulsion stability, instrumental texture, microstructure (via SEM), oxidative stability (TBARSs), and sensory attributes. Data were analyzed using a one-way and two-way ANOVA with Duncan’s test (p < 0.05). The EG’s inclusion significantly reduced the total and saturated fat and cholesterol, while increasing protein and unsaturated fatty acids. The 10% EG sample achieved a PUFA/SFA ratio of 1.00 and an over 80% reduction in atherogenic and thrombogenic indices. Functional improvements were observed in emulsion stability, cooking yield, and water retention. Textural and visual characteristics remained within acceptable sensory thresholds. SEM images showed more homogenous matrix structures in the EG samples. TBARS values increased slightly over 18 days of refrigeration but remained below rancidity thresholds. This period was considered a pilot-scale evaluation of oxidative trends. Sensory testing confirmed that product acceptability was not negatively affected. The partial substitution of beef content with pine nut oil-based emulsion gel offers a clean-label strategy to enhance the nutritional quality of Bologna-type sausages while preserving functional and sensory performance. This approach may support the development of health-conscious processed meat products aligned with consumer and regulatory demands. Full article

The study focuses on optimizing the Fused Deposition Modeling (FDM) process by implementing a cost-efficient support structure strategy. The main objective is to develop a systematic approach for analyzing structural and technological parameters considering print time, material consumption, and surface quality. The study focus is on manually designed support structures as an alternative to automatic generation, allowing for precise control over print settings. The methodology includes comparative analysis of various support strategies using a Prusa MK3S+ printer under standardized conditions. Statistical and visual evaluations confirm that the designed support structures reduce print time by up to 59 min while maintaining comparable material use and superior surface finish. The findings offer a practical framework for optimizing 3D printing processes, reducing waste, and enhancing efficiency in prototyping and small-batch production. Full article

Packaging equipment plays a crucial role in the semiconductor industry by enhancing product quality and reducing labor costs through automation. Research was conducted on IGBT module packaging equipment (an automatic pin insertion machine) during the pin assembly process of insulated gate bipolar transistor (IGBT) modules to improve productivity and product quality. First, the manual pin assembly process was divided into four stages: feeding, stabilizing, clamping, and inserting. Each stage was completed by separate cams, and corresponding step timing diagrams are drawn. The profiles of the four cams were designed and verified through theoretical calculations and kinematic simulations using a seventh-degree polynomial curve fitting method. Then, image algorithms were developed to detect pin tilt defects, pin tip defects, and to provide visual guidance for pin insertion. Finally, a pin insertion machine and its human–machine interaction interface were constructed. On-machine results show that the pin cutting pass rate reached 97%, the average insertion time for one pin was 2.84 s, the pass rate for pin insertion reached 99.75%, and the pin image guidance accuracy was 0.02 mm. Therefore, the designed pin assembly machine can reliably and consistently perform the pin insertion task, providing theoretical and experimental insights for the automated production of IGBT modules. Full article

This paper examines how artificial intelligence (AI) can be strategically deployed to enhance urban planning and environmental livability in Riyadh by generating data-driven, people-centric design interventions. Unlike previous studies that concentrate primarily on visualization, this research proposes an integrative appraisal framework that combines AI-generated design with site-specific environmental data and native vegetation typologies. This study was conducted across key jurisdictional areas including the Northern Ring Road, King Abdullah Road, Al Rabwa, Al-Malaz, Al-Suwaidi, Al-Batha, and King Fahd Road. Using AI tools, urban scenarios were developed to incorporate expanded pedestrian pathways (up to 3.5 m), dedicated bicycle lanes (up to 3.0 m), and ecologically adaptive green buffer zones featuring native drought-resistant species such as Date Palm, Acacia, and Sidr. The quantitative analysis of post-intervention outcomes revealed surface temperature reductions of 3.2–4.5 °C and significant improvements in urban esthetics, walkability, and perceived safety—measured on a five-point Likert scale with 80–100% increases in user satisfaction. Species selection was validated for ecological adaptability, minimal maintenance needs, and compatibility with Riyadh’s sandy soils. This study directly supports the Kingdom of Saudi Arabia’s Vision 2030 by demonstrating how emerging technologies like AI can drive smart, sustainable urban transformation. It aligns with Vision 2030’s urban development goals under the Quality-of-Life Program and environmental sustainability pillar, promoting healthier, more connected cities with elevated livability standards. The research not only delivers practical design recommendations for planners seeking to embed sustainability and digital innovation in Saudi urbanism but also addresses real-world constraints such as budgetary limitations and infrastructure integration. Full article

Smart home technology enhances the quality of life, particularly with respect to in-home care and health monitoring. While video-based methods provide accurate behavior analysis, privacy concerns drive interest in non-visual alternatives. This study proposes a Bluetooth Low Energy (BLE)-enabled indoor positioning and behavior recognition system, integrating machine learning techniques to support sustainable and privacy-preserving health monitoring. Key optimizations include: (1) a vertically mounted Data Collection Unit (DCU) for improved height positioning, (2) synchronized data collection to reduce discrepancies, (3) Kalman filtering to smooth RSSI signals, and (4) AI-based RSSI analysis for enhanced behavior recognition. Experiments in a real home environment used a smart wristband to assess BLE signal variations across different activities (standing, sitting, lying down). The results show that the proposed system reliably tracks user locations and identifies behavior patterns. This research supports elderly care, remote health monitoring, and non-invasive behavior analysis, providing a privacy-preserving solution for smart healthcare applications. Full article

With the increase in the penetration rate of distributed sources and loads, the sensor monitoring data is increasing dramatically. Power grid maintenance services require a rapid response in power quality data analysis. To achieve a rapid response and highly accurate classification of power quality disturbances (PQDs), this paper proposes an efficient classification algorithm for PQDs based on Lissajous trajectory (LT) and a lightweight DenseNet, which utilizes the concept of Lissajous curves to construct an ideal reference signal and combines it with the original PQD signal to synthesize a feature trajectory with a distinctive shape. Meanwhile, to enhance the ability and efficiency of capturing trajectory features, a lightweight L-DenseNet skeleton model is designed, and its feature extraction capability is further improved by integrating an attention mechanism with L-DenseNet. Finally, the LT image is input into the fusion model for training, and PQD classification is achieved using the optimally trained model. The experimental results demonstrate that, compared with current mainstream PQD classification methods, the proposed algorithm not only achieves superior disturbance classification accuracy and noise robustness but also significantly improves response speed in PQD classification tasks through its concise visualization conversion process and lightweight model design. Full article

When faced with diverse types of image tampering and image quality degradation in real-world scenarios, traditional image tampering localization methods often struggle to balance boundary accuracy and robustness. To address these issues, this paper proposes a symmetric guided dual-branch image tampering localization network—FENet (Fusion-Enhanced Network)—that integrates adaptive feature fusion and edge attention mechanisms. This method is based on a structurally symmetric dual-branch architecture, which extracts RGB semantic features and SRM noise residual information to comprehensively capture the fine-grained differences in tampered regions at the visual and statistical levels. To effectively fuse different features, this paper designs a self-calibrating fusion module (SCF), which introduces a content-aware dynamic weighting mechanism to adaptively adjust the importance of different feature branches, thereby enhancing the discriminative power and expressiveness of the fused features. Furthermore, considering that image tampering often involves abnormal changes in edge structures, we further propose an edge-aware coordinate attention mechanism (ECAM). By jointly modeling spatial position information and edge-guided information, the model is guided to focus more precisely on potential tampering boundaries, thereby enhancing its boundary detection and localization capabilities. Experiments on public datasets such as Columbia, CASIA, and NIST16 demonstrate that FENet achieves significantly better results than existing methods. We also analyze the model’s performance under various image quality conditions, such as JPEG compression and Gaussian blur, demonstrating its robustness in real-world scenarios. Experiments in Facebook, Weibo, and WeChat scenarios show that our method achieves average F1 scores that are 2.8%, 3%, and 5.6% higher than those of existing state-of-the-art methods, respectively. Full article

Duck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visually. In current practice, human inspectors use standard white light for crack detection, and many researchers have focused primarily on improving detection algorithms without addressing lighting limitations. Therefore, this paper presents duck egg crack detection using an adaptive convolutional neural network (CNN) model ensemble with multi-light channels. We began by developing a portable crack detection system capable of controlling various light sources to determine the optimal lighting conditions for crack visibility. A total of 23,904 images were collected and evenly distributed across four lighting channels (red, green, blue, and white), with 1494 images per channel. The dataset was then split into 836 images for training, 209 images for validation, and 449 images for testing per lighting condition. To enhance image quality prior to model training, several image pre-processing techniques were applied, including normalization, histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE). The Adaptive MobileNetV2 was employed to evaluate the performance of crack detection under different lighting and pre-processing conditions. The results indicated that, under red lighting, the model achieved 100.00% accuracy, precision, recall, and F1-score across almost all pre-processing methods. Under green lighting, the highest accuracy of 99.80% was achieved using the image normalization method. For blue lighting, the model reached 100.00% accuracy with the HE method. Under white lighting, the highest accuracy of 99.83% was achieved using both the original and HE methods. Full article