Search Results (3,265)

Improvements in exoskeletons and robotic systems are gaining increasing attention because of their potential to improve neuromuscular rehabilitation and assist people in their daily activities, significantly improving their quality of life. However, the high cost and complexity of current devices limit their accessibility to many patients and rehabilitation centers. This work presents the design and development of a low-cost walking exoskeleton, conceived to offer an affordable and simple alternative. The system uses a compact eight-bar mechanism with only one degree of freedom per leg, drastically simplifying motorization and control. The exoskeleton is customized for each patient using a synthesis process based on evolutionary algorithms to replicate a predefined gait. Despite the reduced number of degrees of freedom, the resulting mechanism perfectly matches the desired ankle and knee trajectories. The device is designed to be lightweight and affordable, with components fabricated using 3D printing, standard aluminum bars, and one actuator per leg. A working prototype was fabricated, and its functionality and gait accuracy were confirmed. Although limited to a predefined gait pattern and requiring crutches for balance and steering, this exoskeleton represents a promising solution for rehabilitation centers with limited resources, offering accessible and effective gait assistance to a wider population. Full article

UAV accident investigation is essential for safeguarding the fast-growing low-altitude airspace. While near-daily incidents are reported, they were rarely analyzed in depth as current inquiries remain expert-dependent and time-consuming. Because most jurisdictions mandate formal reporting only for serious injury or substantial property damage, a large proportion of minor occurrences receive no systematic investigation, resulting in persistent data gaps and hindering proactive risk management. This study explores the potential of using large language models (LLMs) to expedite UAV accident investigations by extracting human-factor insights from unstructured narrative incident reports. Despite their promise, the off-the-shelf LLMs still struggle with domain-specific reasoning in the UAV context. To address this, we developed a human factors analysis and classification system (HFACS)-guided analytical framework, which blends structured prompting with lightweight post-processing. This framework systematically guides the model through a two-stage procedure to infer operators’ unsafe acts, their latent preconditions, and the associated organizational influences and regulatory risk factors. A HFACS-labelled UAV accident corpus comprising 200 abnormal event reports with 3600 coded instances has been compiled to support evaluation. Across seven LLMs and 18 HFACS categories, macro-F1 ranged 0.58–0.76; our best configuration achieved macro-F1 0.76 (precision 0.71, recall 0.82), with representative category accuracies > 93%. Comparative assessments indicate that the prompted LLM can match, and in certain tasks surpass, human experts. The findings highlight the promise of automated human factor analysis for conducting rapid and systematic UAV accident investigations. Full article

Timely identification and accurate delineation of ultra-early ischemic stroke lesions in non-contrast computed tomography (CT) scans of the human brain are of paramount importance for prompt medical intervention and improved patient outcomes. In this study, we propose a deep learning-driven methodology specifically designed for segmenting ultra-early ischemic regions, with a particular emphasis on both the ischemic core and the surrounding penumbra during the initial stages of stroke progression. We introduce a lightweight preprocessing model based on convolutional filtering techniques, which enhances image clarity while preserving the structural integrity of medical scans, a critical factor when detecting subtle signs of ultra-early ischemic strokes. Unlike conventional preprocessing methods that directly modify the image and may introduce artifacts or distortions, our approach ensures the absence of neural network-induced artifacts, which is especially crucial for accurate diagnosis and segmentation of ultra-early ischemic lesions. The model employs predefined differentiable filters with trainable parameters, allowing for artifact-free and precision-enhanced image refinement tailored to the challenges of ultra-early stroke detection. In addition, we incorporated into the combined preprocessing pipeline a newly proposed trainable linear combination of pretrained image filters, a concept first introduced in this study. For model training and evaluation, we utilize a publicly available dataset of acute ischemic stroke cases, focusing on the subset relevant to ultra-early stroke manifestations, which contains annotated non-contrast CT brain scans from 112 patients. The proposed model demonstrates high segmentation accuracy for ultra-early ischemic regions, surpassing existing methodologies across key performance metrics. The results have been rigorously validated on test subsets from the dataset, confirming the effectiveness of our approach in supporting the early-stage diagnosis and treatment planning for ultra-early ischemic strokes. Full article

Pultrusion is a manufacturing process used to produce fiber-reinforced polymer composites with excellent mechanical, thermal, and chemical properties. The resulting materials are lightweight, durable, and corrosion-resistant, making them valuable in aerospace, automotive, construction, and energy sectors. However, conventional thermoset composites remain difficult to recycle due to their infusible and insoluble cross-linked structure. This review explores integrating vitrimer technology a novel class of recyclable thermosets with dynamic covalent adaptive networks into the pultrusion process. As only limited studies have directly reported vitrimer pultrusion to date, this review provides a forward-looking perspective, highlighting fundamental principles, challenges, and opportunities that can guide future development of recyclable high-performance composites. Vitrimers combine the mechanical strength (tensile strength and modulus) of thermosets with the reprocessability and reshaping of thermoplastics through dynamic bond exchange mechanisms. These polymers offer high-temperature reprocessability, self-healing, and closed-loop recyclability, where recycling efficiency can be evaluated by the recovery yield retention of mechanical properties and reuse cycles meeting the demand for sustainable manufacturing. Key aspects discussed include resin formulation, fiber impregnation, curing cycles, and die design for vitrimer systems. The temperature-dependent bond exchange reactions present challenges in achieving optimal curing and strong fiber–matrix adhesion. Recent studies indicate that vitrimer-based composites can maintain structural integrity while enabling recycling and repair, with mechanical performance such as flexural and tensile strength comparable to conventional composites. Incorporating vitrimer materials into pultrusion could enable high-performance, lightweight products for a circular economy. The remaining challenges include optimizing curing kinetics, improving interfacial adhesion, and scaling production for widespread industrial adoption. Full article

Facing the diversity of the market, the industry has to move towards Industry 4.0, and smart manufacturing based on cyber-physical systems is the only way to move towards Industry 4.0. However, there are two key concepts in Industry 4.0: cyber-physical systems (CPSs) and digital twins (DTs). In the paper, we propose a smart manufacturing system suitable for stamping press processes based on the CPS concept and use DT to establish a manufacturing-end robot guidance generation model. In the smart manufacturing system of stamping press processes, fog nodes are used to connect three major architectures, including device health diagnosis, manufacturing device, and material traceability. In addition, a special hook end point is designed, and its lightweight visual guidance generation model is established to improve the production efficiency of the manufacturing end in product manufacturing. Full article

Micro-arc oxidation (MAO) technology demonstrates remarkable advantages in fabricating ceramic coatings on lightweight alloys. For aluminum alloys, MAO rapidly forms dense, pore-free ceramic layers within minutes, significantly enhancing corrosion and wear resistance at low processing costs. In magnesium alloys, optimized electrolyte compositions and process parameters enable composite coatings with a combination of high hardness and self-lubrication properties, while post-treatments like laser melting or corrosion inhibitors extend salt spray corrosion resistance. Titanium alloys benefit from MAO coatings with exceptional interfacial bonding strength and mechanical performance, making them ideal for biomedical implants and aerospace components. Notably, dense ceramic oxide films grown in situ via MAO on high-entropy alloys (HEAs) triple surface hardness and enhance wear/corrosion resistance. However, MAO applications on steel require pretreatments like aluminizing, thermal spraying, or ion plating. Current challenges include coating uniformity control, efficiency for complex geometries, and long-term stability. Future research focuses on multifunctional coatings (self-healing, antibacterial) and eco-friendly electrolyte systems to expand engineering applications. Full article

Structured-light 3D reconstruction is an active measurement technique that extracts spatial geometric information of objects by projecting fringe patterns and analyzing their distortions. It has been widely applied in industrial inspection, cultural heritage digitization, virtual reality, and other related fields. This review presents a comprehensive analysis of mainstream fringe-based reconstruction methods, including Fringe Projection Profilometry (FPP) for diffuse surfaces and Phase Measuring Deflectometry (PMD) for specular surfaces. While existing reviews typically focus on individual techniques or specific applications, they often lack a systematic comparison between these two major approaches. In particular, the influence of different projection schemes such as Digital Light Processing (DLP) and MEMS scanning mirror–based laser scanning on system performance has not yet been fully clarified. To fill this gap, the review analyzes and compares FPP and PMD with respect to measurement principles, system implementation, calibration and modeling strategies, error control mechanisms, and integration with deep learning methods. Special focus is placed on the potential of MEMS projection technology in achieving lightweight and high-dynamic-range measurement scenarios, as well as the emerging role of deep learning in enhancing phase retrieval and 3D reconstruction accuracy. This review concludes by identifying key technical challenges and offering insights into future research directions in system modeling, intelligent reconstruction, and comprehensive performance evaluation. Full article

Magnesium alloys, characterized by high specific strength and low density, have high potential for applications in transportation and aerospace. Nevertheless, ensuring the reliable joining of thin-walled components remains a major technical challenge. This study examines how rotational speed affects the microstructure and mechanical properties of friction stir welded AZ61 magnesium alloy hollow profiles (3 mm thick), with particular focus on the underlying mechanisms. The results show that higher rotational speed during friction stir welding promotes dynamic recrystallization and weakens the basal texture. It also affects microstructural homogeneity, where an optimal rotational speed produces a relatively uniform hybrid microstructure consisting of refined recrystallized and un-recrystallized regions. This balance enhances both texture strengthening and microstructural optimization. The weld joint fabricated at a rotational speed of 1500 rpm showed the best overall mechanical properties, with ultimate tensile strength, yield strength, and elongation reaching peak values of 286.7 MPa, 154.7 MPa, and 9.7%, respectively. At this speed, the average grain size in the weld nugget zone was 4.92 μm, and the volume fraction of second-phase particles was 0.67%. This study establishes a critical process foundation for the reliable joining of thin-walled magnesium alloy structures. The optimized parameters serve as valuable guidelines for engineering applications in lightweight transportation equipment and aerospace manufacturing. Full article

Based on the problem of incomplete mining of Additive Manufacturing (AM) potential caused by the limitations of current Design for Additive Manufacturing (DFAM) methods, this paper proposes to integrate Additive Manufacturing and axiomatic design to obtain the global conceptual design method of products to be manufactured with AM. In response to the lower process dependence of AM technology compared to traditional processes, two integration measures of “influence region division” and “process domain forward” are proposed, and finally, the axiomatic design process for AM is obtained. Taking the assembly-free integrated design of mechanical fingers imitating dexterous hands as an example, the conceptual design method studied was validated. The application of innovative features such as flexible finger joints and lattice-filled finger joints shows that the design method proposed in this paper can deeply tap into the manufacturing potential of AM, achieve lightweight and integrated molding of products, which provides useful references for designers. Full article

In this paper, we propose a novel Dynamic Cipher Composition (DCC) based on multi-algorithm approach using the Library of Image Encryption Methods (LIEM). Unlike conventional static encryption schemes, the proposed DCC randomly selects and applies different encryption algorithms to spatially segmented regions of an image during each execution. To manage this process efficiently, the system employs two lightweight registers: one for configuration management and another for region-specific modality assignment, both indexed for streamlined storage and retrieval. Experimental evaluations conducted on standard test images demonstrate that the DCC achieves a near-optimal Shannon entropy, high values of Net Pixel Change Rate (NPCR) and Unified Average Changing Intensity (UACI), and negligible pixel correlation coefficients. These results confirm the scheme’s strong resistance to statistical, differential, and structural attacks, while preserving computational efficiency suitable for real-time applications such as telemedicine, cloud storage, and video surveillance systems. Full article

In recent years, with continuous technological advances, BIM technology has gradually expanded from the traditional construction industry into the field of hydraulic engineering. Since BIM models, which span the entire project lifecycle, contain substantial amounts of data and the operation and maintenance phase accounts for the majority of this lifecycle, higher computational demands are imposed. Consequently, the lightweighting of BIM models has become imperative. In this study, an improved Quadric Error Metric (QEM) algorithm was applied to simplify the geometric data of the constructed BIM model. The research investigates whether the lightweight model can reduce the computational requirements during its application in the operation and management of hydraulic engineering, thereby enhancing its general applicability. Furthermore, a fuzzy comprehensive evaluation model was established to assess the effectiveness of the lightweighting process. The experimental results indicate that the optimized model occupies significantly less memory space. Additionally, model loading time and rendering CPU usage were substantially improved. The lightweight effect was evaluated as excellent based on the fuzzy comprehensive evaluation. Full article

The integration of SLAM with Gaussian splatting presents a significant challenge: achieving compatibility between real-time performance and high-quality rendering. This paper introduces a novel SLAM system named SFGS-SLAM (SuperFeats Gaussian Splatting SLAM), restructured from tracking to mapping, to address this issue. A new keypoint detection network is designed and characterized by fewer parameters than existing networks such as SuperFeats, resulting in faster processing speeds. This keypoint detection network is augmented with a global factor graph incorporating the GICP (Generalized Iterative Closest Point) odometry, reprojection-error factors and loop-closure constraints to minimize drift. It is integrated with the Gaussian splatting as the mapping part. By leveraging the reprojection error, the proposed system further reduces odometry error and improves rendering quality without compromising speed. It is worth noting that SFGS-SLAM is primarily designed for static indoor environments and does not explicitly model or suppress dynamic disturbances. Comprehensive experiments were conducted on various datasets to evaluate the performance of our system. Extensive experiments on indoor and synthetic datasets show that SFGS-SLAM achieves accuracy comparable to state-of-the-art SLAM while running in real time. SuperFeats reduces matching latency by over 50%, and joint optimization significantly improves global consistency. Our results demonstrate the practicality of combining lightweight feature matching with dense Gaussian mapping, highlighting trade-offs between speed and accuracy. Full article

This paper outlines the process of developing a low-cost system for home appliance control via real-time hand gesture classification using Computer Vision and a custom lightweight machine learning model. This system strives to enable those with speech or hearing disabilities to interface with smart home devices in real time using hand gestures, such as is possible with voice-activated ‘smart assistants’ currently available. The system runs on a Raspberry Pi 5 to enable future IoT integration and reduce costs. The system also uses the official camera module v2 and 7-inch touchscreen. Frame preprocessing uses MediaPipe to assign hand coordinates, and NumPy tools to normalise them. A machine learning model then predicts the gesture. The model, a feed-forward network consisting of five fully connected layers, was built using Keras 3 and compiled with TensorFlow Lite. Training data utilised the HaGRIDv2 dataset, modified to consist of 15 one-handed gestures from its original of 23 one- and two-handed gestures. When used to train the model, validation metrics of 0.90 accuracy and 0.31 loss were returned. The system can control both analogue and digital hardware via GPIO pins and, when recognising a gesture, averages 20.4 frames per second with no observable delay. Full article

Micro-expression recognition (MER) aims to detect brief and subtle facial movements that reveal suppressed emotions, discerning authentic emotional responses in scenarios such as visitor experience analysis in museum settings. However, it remains a highly challenging task due to the fleeting duration, low intensity, and limited availability of annotated data. Most existing approaches rely solely on either appearance or motion cues, thereby restricting their ability to capture expressive information fully. To overcome these limitations, we propose a lightweight multi-modal fusion network, termed M³ENet, which integrates both motion and appearance cues through early-stage feature fusion. Specifically, our model extracts horizontal, vertical, and strain-based optical flow between the onset and apex frames, alongside RGB images from the onset, apex, and offset frames. These inputs are processed by two modality-specific subnetworks, whose features are fused to exploit complementary information for robust classification. To improve generalization in low data regimes, we employ targeted data augmentation and adopt focal loss to mitigate class imbalance. Extensive experiments on five benchmark datasets, including CASME I, CASME II, CAS(ME)², SAMM, and MMEW, demonstrate that M³ENet achieves state-of-the-art performance with high efficiency. Ablation studies and Grad-CAM visualizations further confirm the effectiveness and interpretability of the proposed architecture. Full article

A multilayered coating process, based on cement and silica fume, was applied to the surface of expanded vermiculite aggregate (EVA) using a cold bonding method. This investigation represents the first systematic study of this multilayered coating method, with the objective of evaluating the effectiveness of coating thickness in the production of high-performance lightweight mortar. In the experimental phase of this study, a range of aggregate replacement levels was examined, and a series of tests were conducted to assess parameters such as dry density, porosity, thermal conductivity, water absorption, sorptivity, compressive strength, flexural strength, and shear strength. The obtained Mohr–Coulomb (MC) constitutive model parameters and shear strength properties were verified numerically. The verification process facilitated the simulation of the three-dimensional (3D) combined behavior of the produced mortar with cement paste, cement–silica fume liner, and EVA. The simulation was conducted using a micro-scale finite element (FE) model based on the Computer Tomography (CT) data. The Pareto-efficient utilization boundaries of coated-EVA in the production of high-strength lightweight mortar are then specified using Response Surface optimization analyses. The present study demonstrates that the cold bonding multilayered coating process is a highly effective aggregate-strengthening method. This study revealed that the Pareto-efficient replacement range of coated-EVA is 24–58%, corresponding to a coating thickness of 0.9–2.6 mm. It is evident that the effective utilization of the replaced aggregate in the mortar production is subject to a limit, which can be determined through Pareto-efficiency analysis, and it is contingent upon the performance requirements of the resulting mortar. Full article