Search Results (3,106)

The rising global demand for prosthetic limbs, driven by approximately 185,000 amputations annually in the United States, underscores the need for innovative and cost-efficient solutions. This study explores the integration of hybrid materials, advanced 3D printing techniques, and smart sensing technologies to enhance prosthetic finger production. A Taguchi-based design of experiments (DoE) approach using an L09 orthogonal array was employed to systematically evaluate the effects of infill density, infill pattern, and print speed on the tensile behavior of FDM-printed PLA components. Findings reveal that higher infill densities (90%) and hexagonal patterns significantly enhance yield strength, ultimate tensile strength, and stiffness. Additionally, the rheological properties of polydimethylsiloxane (PDMS) were optimized at various temperatures (30–70 °C), characterizing its viscosity, shear-thinning factors, and stress behaviors for 3D bioprinting of flexible sensors. Barium titanate (BaTiO₃) was incorporated into PDMS to fabricate a flexible tactile sensor, achieving reliable open-circuit voltage readings under applied forces. Structural and functional components of the finger prosthesis were fabricated using FDM, stereolithography (SLA), and extrusion-based bioprinting (EBP) and assembled into a functional prototype. This research demonstrates the feasibility of integrating hybrid materials and advanced printing methodologies to create cost-effective, high-performance prosthetic components with enhanced mechanical properties and embedded sensing capabilities. Full article

The ultrasonic guided wave method is successfully used for structural health monitoring (SHM) of aircraft structures utilizing PZT (Pb-Zr-Ti based piezoceramic material) sensors for guided wave generation and detection. To increase the mechanical durability of the sensors in operational conditions, this paper demonstrates the feasibility of the integration of PZTs into the Glass fiber/Polymethyl methacrylate (G/PMMA) composite plate and evaluates the possibility of impact damage detection using generated guided waves. Two types of PZT sensors were embedded into different layers during the manufacturing process. Generally, radial mode disc sensors are used for Lamb wave generation, and thickness-shear square-shaped sensors are used for both Lamb and shear wave generation. First, the wave propagation was analyzed considering the sensor type and sensor placement within the layup. The main objective was to propose the optimal sensor network with embedded sensors for successful impact damage detection. Lamb wave frequency tuning of disk sensors and unique vibrational characteristics of integrated shear sensors were exploited to selectively actuate only one guided wave mode. Finally, the Reconstruction Algorithm for the Probabilistic Inspection of Damage (RAPID) was utilized for damage localization and visualization. Full article

In this work, we tested the use of Convolutional Neural Networks (CNNs) to classify booming noise inside vehicles. Instead of relying only on long experimental campaigns, we generated a synthetic dataset from Sound Quality Equivalent (SQE) models that were originally built from real acoustic measurements collected with sensors. By applying smoothing functions and Hann windows, we were able to vary the intensity of the booming effect across different mission profiles. The CNNs were trained on spectrograms derived from these signals, with labels informed by psychoacoustic evaluations. The best model reached about 95.5% accuracy in the binary task (booming vs. no booming) and around 93.3% when using three classes (severe, mild, none). Tests with data from three different car models showed that the method can generalize across platforms. These results suggest that CNNs may become a practical tool for NVH analysis, offering a simpler and cheaper complement to traditional end-of-line testing, and one that could be adapted for real-time embedded systems. Full article

Upper-limb motor impairment is a major consequence of stroke and neuromuscular disorders, imposing a sustained clinical and socioeconomic burden worldwide. Quantitative assessment of limb positioning and motion accuracy is fundamental to rehabilitation, guiding therapy evaluation and robotic assistance. The evolution of upper-limb positioning systems has progressed from optical motion capture to wearable inertial measurement units (IMUs) and, more recently, to data-driven estimators integrated with rehabilitation robots. Each generation has aimed to balance spatial accuracy, portability, latency, and metrological reliability under ecological conditions. This review presents a systematic synthesis of the state of measurement uncertainty, calibration, and traceability in upper-limb rehabilitation robotics. Studies are categorised across four layers, i.e., sensing, fusion, cognitive, and metrological, according to their role in data acquisition, estimation, adaptation, and verification. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol was followed to ensure transparent identification, screening, and inclusion of relevant works. Comparative evaluation highlights how modern sensor-fusion and learning-based pipelines achieve near-optical angular accuracy while maintaining clinical usability. Persistent challenges include non-standard calibration procedures, magnetometer vulnerability, limited uncertainty propagation, and absence of unified traceability frameworks. The synthesis indicates a gradual transition toward cognitive and uncertainty-aware rehabilitation robotics in which metrology, artificial intelligence, and control co-evolve. Traceable measurement chains, explainable estimators, and energy-efficient embedded deployment emerge as essential prerequisites for regulatory and clinical translation. The review concludes that future upper-limb systems must integrate calibration transparency, quantified uncertainty, and interpretable learning to enable reproducible, patient-centred rehabilitation by 2030. Full article

Fault-tolerant control in safety-critical industrial systems demands adaptive responses to equipment degradation, parameter drift, and sensor failures while maintaining strict operational constraints. Traditional model-based controllers struggle under these conditions, requiring extensive retuning and dense instrumentation. Recent safe multi-agent reinforcement learning (MARL) frameworks with control barrier functions (CBFs) achieve real-time constraint satisfaction in robotics and power systems, yet assume comprehensive state observability—incompatible with sensor-hostile industrial environments where instrumentation degradation and contamination risks dominate design constraints. This work presents a safety-aware multi-agent deep reinforcement learning framework for adaptive fault-tolerant control in sensor-lean industrial environments, achieving formal safety through learned implicit barriers under partial observability. The framework integrates four synergistic mechanisms: (1) multi-layer safety architecture combining constrained action projection, prioritized experience replay, conservative training margins, and curriculum-embedded verification achieving zero constraint violations; (2) multi-agent coordination via decentralized execution with learned complementary policies. Additional components include (3) curriculum-driven sim-to-real transfer through progressive four-stage learning achieving 85–92% performance retention without fine-tuning; (4) offline extended Kalman filter validation enabling 70% instrumentation reduction (91–96% reconstruction accuracy) for regulatory auditing without real-time estimation dependencies. Validated through sustained deployment in commercial beverage manufacturing clean-in-place (CIP) systems—a representative safety-critical testbed with hard flow constraints (≥1.5 L/s), harsh chemical environments, and zero-tolerance contamination requirements—the framework demonstrates superior control precision (coefficient of variation: 2.9–5.3% versus 10% industrial standard) across three hydraulic configurations spanning complexity range 2.1–8.2/10. Comprehensive validation comprising 37+ controlled stress-test campaigns and hundreds of production cycles (accumulated over 6 months) confirms zero safety violations, high reproducibility (CV variation < 0.3% across replicates), predictable complexity–performance scaling ($R^2=0.89$), and zero-retuning cross-topology transferability. The system has operated autonomously in active production for over 6 months, establishing reproducible methodology for safe MARL deployment in partially-observable, sensor-hostile manufacturing environments where analytical CBF approaches are structurally infeasible. Full article

Scene depth information is a key component of any robotic mobile application. Range sensors, such as LiDAR, sonar, or radar, capture depth data of a scene. However, the data captured by these sensors frequently presents missing regions or information with a low confidence level. These missing regions in the depth data could be large areas without information, making it difficult to make decisions, for instance, for an autonomous vehicle. Recovering depth data has become a primary activity for computer vision applications. This work proposes and evaluates an interpolation model to infer dense depth maps from a Lab color space reference picture and an incomplete-depth image embedded in a completion pipeline. The complete proposal pipeline comprises convolutional layers and a convex combination of the infinity Laplacian and non-local means model. The proposed model infers dense depth maps by considering depth data and utilizing clues from a color picture of the scene, along with a metric for computing differences between two pixels. The work contributes (i) the convex combination of the two models to interpolate the data, and (ii) the proposal of a class of function suitable for balancing between different models. The obtained results show that the model outperforms similar models in the KITTI dataset and outperforms our previous implementation in the NYU_v2 dataset, dropping the MSE by 34.86%, 3.35%, and 34.42% for 4×, 8×, 16× upsampling tasks, respectively. Full article

This paper introduces a streamlined three-step synthesis method for crafting porous Fe₂O₃/ZnO nanofibers (NFs). Initially, Fe₂O₃ nanoparticles (NPs) were synthesized using the hydrothermal method. Subsequently, PVP NFs laden with Fe₂O₃ NPs and zinc salt were synthesized via an electrospinning method. Finally, porous Fe₂O₃/ZnO NFs were fabricated through calcination, resulting in an average diameter of approximately 100 nm. Gas-sensing experiments illuminate that the porous Fe₂O₃/ZnO NFs exhibit outstanding sensitivity, selectivity, and robust long-term stability. Although the response magnitude decreased under high relative humidity (RH) due to competitive adsorption, the sensor maintained distinct detectable responses towards NO₂ vapor at an optimum temperature of 225 °C. Particularly noteworthy is the substantial enhancement in NO₂ sensing properties observed in the Fe₂O₃/ZnO composite compared to pure ZnO NFs. This enhancement can be ascribed to the distinctive microstructure and heterojunction formed between Fe₂O₃ and ZnO. Full article

High-rise building areas (HRBs) play a crucial role in providing social and environmental services during the process of modern urbanization. Their large-scale, long-term spatial distribution characteristics have significant implications for fields such as urban planning and regional climate analysis. However, existing studies are largely limited to local regions and fixed-time-phase images. These studies are also influenced by differences in remote sensing image acquisition, such as regional architectural styles, lighting conditions, seasons, and sensor variations. This makes it challenging to achieve robust extraction across time and regions. To address these challenges, we propose an improved method for extracting HRBs that uses a Prior-Embedded Dual-Branch Neural Network (PEDNet). The dual-path design balances global features with local details. More importantly, we employ a window attention mechanism to introduce diverse prior information as embedded features. By integrating these features, our method becomes more robust against HRB image feature variations. We conducted extensive experiments using Sentinel-2 data from four typical cities. The results demonstrate that our method outperforms traditional models, such as FCN and U-Net, as well as more recent high-performance segmentation models, including DeepLabV3+ and BuildFormer. It effectively captures HRB features in remote sensing images, adapts to complex conditions, and provides a reliable tool for wide geographic span, cross-timestamp urban monitoring. It has practical applications for optimizing urban planning and improving the efficiency of resource management. Full article

This study presents a systematic review of ontology–AI integration for construction image understanding, aiming to clarify how ontologies enhance semantic consistency, interpretability, and reasoning in AI-based visual analysis. Construction sites involve highly dynamic and unstructured conditions, making image-based hazard detection and situation assessment both essential and challenging. Ontology-based frameworks offer a structured semantic layer that can complement deep learning models; however, most existing studies adopt ontologies only as post-processing mechanisms rather than embedding them within model training or inference workflows. Following PRISMA 2020 guidelines, a comprehensive search of the Web of Science Core Collection (2014–2025) identified 587 publications, of which 152 met the eligibility criteria, and 16 explicitly addressed construction image data. Topic modeling revealed five functional objectives—regulatory compliance, hazard reasoning, decision support, knowledge reuse, and sustainability—and four primary data modalities: BIM, text, image, and sensor data. Two dominant integration patterns were observed: training-stage and output-stage enhancement. While quantitative performance improvements were modest, qualitative gains were consistent across studies, including reduced false positives, improved interpretability, and enhanced situational understanding. Persistent gaps were identified in standardization, scalability, and real-world validation. This review provides the first structured synthesis of ontology–AI research for construction image understanding and offers an evidence-based research agenda that links observed limitations to actionable directions for semantic AI in construction. Full article

Early diagnosis of Parkinson’s disease (PD) is crucial for slowing its progression. Gait analysis is increasingly used to detect early symptoms, with smart insoles emerging as a cost-effective and convenient tool for daily monitoring. However, smart insoles have practical limitations, including durability concerns, limited battery life, and difficulties in minimizing the number of sensors. In this study, we designed a novel deep convolutional neural network model for accurately detecting abnormal gaits in patients with PD using a reduced number of sensors embedded in smart insoles. The proposed convolutional neural network (CNN) model was trained on a gait dataset collected from a total of 29 participants, including 13 healthy individuals, 9 elderly individuals, and 7 patients with Parkinson’s disease (PD). Instead of combining plantar pressure data from both feet, the model processes each foot independently through sequential layers to better capture gait asymmetries. The proposed CNN model achieved a classification accuracy of 90.35% using only 8 of the 32 plantar pressure sensors in the smart insole, outperforming a conventional CNN model by approximately 10%. The experimental results demonstrate the potential of our CNN model for effectively detecting abnormal gait patterns in patients with PD while minimizing sensor requirements, enhancing the practicality and efficiency of smart insoles for real-world use. Full article

Multimodal forecasting is increasingly needed to maintain energy levels, storage capacity, and compute efficiency in off-grid, renewable-powered cloud environments. Variable sensor quality, uncertain interactions with renewable energy, and rapidly changing weather patterns make real-time forecasting difficult. Current transformer, GNN, and CNN systems suffer from sensor noise instability, multimodal temporal–spectral correlation issues, and challenges in the interpretability of operational decision-making. In this research, Q-RCANeX, a quantum-guided residual convolutional attention network for off-grid cloud infrastructures, estimates battery state of charge, renewable energy sources, and microgrid efficiency to overcome these restrictions. The system uses a Hybrid Quantum–Bayesian Evolutionary Optimizer, quantum feature embedding, temporal–spectral attention, residual convolutional encoding, and signal decomposition preprocessing. These parameters reinforce features, reduce noise, and align forecasting behavior with microgrid dynamics. Q-RCANeX obtains 98.6% accuracy, 0.992 AUC, and 0.986 R³ values for REAF, WGF, SOC-F, and EEIF forecasting tasks, according to a statistical study. Additionally, it determines inference latency to 4.9 ms and model size to 18.5 MB. Even with 20% of sensor data missing or noisy, the model outperforms 12 state-of-the-art baselines and maintains 96.8% accuracy using ANOVA, Wilcoxon, Nemenyi, and Holm tests. The findings indicate that the forecasting framework has high accuracy, clarity, and resilience to failures. This makes it useful for real-time, off-grid management of renewable cloud microgrids. Full article

The Sparse Subgraph Finding (SGF) problem addresses the challenge of identifying sub–graphs with weak social interactions and sparse connections within a graph, which can be effectively modeled as discovering sparse subsystems in intelligent sensor networks. Traditional methods often rely on manually designed heuristics, which are computationally expensive and lack scalability, especially when dealing with complex sensor network systems. In this paper, we propose RL-SGF, a novel framework that integrates deep reinforcement learning and graph embedding through joint optimization to overcome these limitations. By simultaneously optimizing subsystem sparsity and representation learning within a unified framework, RL-SGF enhances both the effectiveness and robustness of the model in sensor network applications. Experimental results on synthetic and real-world datasets, including social networks, citation networks, and sensor network simulations, demonstrate that RL-SGF outperforms existing algorithms in terms of efficiency and solution quality, making it highly applicable to real-world sparse subsystem discovery scenarios in intelligent sensor networks. Full article

(1) Background: This study presents an adaptive, contactless, and privacy-preserving respiratory-rate monitoring system based on thermal imaging, designed for real-time operation on embedded edge hardware. The system continuously processes temperature data from a compact thermal camera without external computation, enabling practical deployment for home or clinical vital-sign monitoring. (2) Methods: Thermal frames are captured using a $256\times 192$ TOPDON TC001 camera and processed entirely on an NVIDIA Jetson Orin Nano. A YOLO-based detector localizes the nostril region in every even frame (stride = 2) to reduce the computation load, while a Kalman filter predicts the ROI position on skipped frames to maintain spatial continuity and suppress motion jitter. From the stabilized ROI, a temperature-based breathing signal is extracted and analyzed through an adaptive median–MAD hysteresis algorithm that dynamically adjusts to signal amplitude and noise variations for breathing phase detection. Respiratory rate ($RR$) is computed from inter-breath intervals (IBI) validated within physiological constraints. (3) Results: Ten healthy subjects participated in six experimental conditions including resting, paced breathing, speech, off-axis yaw, posture (supine), and distance variations up to 2.0 m. Across these conditions, the system attained a MAE of $0.57\pm 0.36$ BPM and an RMSE of $0.64\pm 0.42$ BPM, demonstrating stable accuracy under motion and thermal drift. Compared with peak-based and FFT spectral baselines, the proposed method reduced errors by a large margin across all conditions. (4) Conclusions: The findings confirm that accurate and robust respiratory-rate estimation can be achieved using a low-resolution thermal sensor running entirely on an embedded edge device. The combination of YOLO-based nostril detector, Kalman ROI prediction, and adaptive MAD–hysteresis phase that self-adjusts to signal variability provides a compact, efficient, and privacy-preserving solution for non-invasive vital-sign monitoring in real-world environments. Full article

The hydraulic performance of woven geotextiles is frequently overlooked in roadway design, despite their extensive use for reinforcement applications. Woven geotextiles are typically manufactured from hydrophobic polymers such as polypropylene or polyester and can act as capillary barriers under unsaturated conditions. This results in moisture accumulation at the soil–geotextile interface, adversely impacting long-term pavement performance. Such problems can be effectively mitigated using geotextiles with enhanced lateral drainage (ELD) capabilities, which are engineered with hydrophilic fibers to facilitate capillary-driven lateral water movement under unsaturated conditions. This functionality facilitates the redistribution of moisture away from the interface, mitigating moisture retention and enhancing drainage performance. The hydraulic performance of geotextiles with enhanced lateral drainage capabilities under unsaturated conditions remains insufficiently understood, particularly in terms of their influence zone and drainage efficiency. For this reason, the present study evaluates the lateral drainage behavior of an ELD geotextile using a soil column test, compared against a control setup without a geotextile and with a non-woven geotextile. Two moisture migration scenarios, namely capillary rise and vertical infiltration, were simulated, with the water table varied at multiple depths. Moisture sensors were embedded along the column depth to monitor real-time water content variations. Results show that the ELD geotextile facilitated efficient lateral drainage, with a consistent influence zone extending up to 2 inches below the fabric. Under infiltration, the ELD geotextile reduced moisture accumulation by 30% around the geotextile, highlighting its superior drainage behavior. These findings encourage practicing engineers to adopt rational, performance-based designs that leverage ELD geotextiles to enhance subgrade drainage and moisture control in pavement and geotechnical applications. Full article

This article presents the design, fabrication, and experimental validation of a centimeter-scale autonomous robot that achieves bidirectional locomotion and trajectory control through 3D-printed resonators actuated by piezoelectricity and integrated with miniature legs. Building on previous works that employed piezoelectric bimorphs, the proposed system replaces them with custom-designed 3D-printed resonant plates that exploit the excitation of standing waves (SW) to generate motion. Each resonator is equipped with strategically positioned passive legs that convert vibratory energy into effective thrust, enabling both linear and rotational movement. A differential drive configuration, implemented through two independently actuated resonators, allows precise guidance and the execution of complex trajectories. The robot integrates onboard control electronics consisting of a microcontroller and inertial sensors, which enable closed-loop trajectory correction via a PD controller and allow autonomous navigation. The experimental results demonstrate high-precision motion control, achieving linear displacement speeds of 8.87 mm/s and a maximum angular velocity of 37.88°/s, while maintaining low power consumption and a compact form factor. Furthermore, the evaluation using the mean absolute error (MAE) yielded a value of 0.83° in trajectory tracking. This work advances the field of robotics and automatic control at the insect scale by integrating efficient piezoelectric actuation, additive manufacturing, and embedded sensing into a single autonomous platform capable of agile and programmable locomotion. Full article