Search Results (314)

Sign language is a visual language articulated through body movements. Existing approaches predominantly leverage RGB inputs, incurring substantial computational overhead and remaining susceptible to interference from foreground and background noise. A second fundamental challenge lies in accurately modeling the nonlinear temporal dynamics and inherent asynchrony across body parts that characterize sign language sequences. To address these challenges, we propose a novel part-wise graph Fourier learning method for skeleton-based continuous sign language recognition (PGF-SLR), which uniformly models the spatiotemporal relations of multiple body parts in a globally ordered yet locally unordered manner. Specifically, different parts within different time steps are treated as nodes, while the frequency domain attention between parts is treated as edges to construct a part-level Fourier fully connected graph. This enables the graph Fourier learning module to jointly capture spatiotemporal dependencies in the frequency domain, while our adaptive frequency enhancement method further amplifies discriminative action features in a lightweight and robust fashion. Finally, a dual-branch action learning module featuring an auxiliary action prediction branch to assist the recognition branch is designed to enhance the understanding of sign language. Our experimental results show that the proposed PGF-SLR achieved relative improvements of 3.31%/3.70% and 2.81%/7.33% compared to SOTA methods on the dev/test sets of the PHOENIX14 and PHOENIX14-T datasets. It also demonstrated highly competitive recognition performance on the CSL-Daily dataset, showcasing strong generalization while reducing computational costs in both offline and online settings. Full article

Urine pH serves as an indicator of systemic acid–base balance and helps detect early-stage urinary and renal disorders. However, conventional monitoring methods rely on instruments or manual procedures, limiting their use among vulnerable groups such as infants and bedridden elderly individuals. In this study, a pH-responsive smart hydrogel was developed and integrated into diapers to enable real-time, equipment-free, and visually interpretable urine pH monitoring. An optimised degumming process enabled one-step preparation of a silk fibroin–sericin aqueous solution. We employed a visible light-induced photo-crosslinking strategy to fabricate a dual-network hydrogel with enhanced strength and stability. Increasing sericin content accelerated gelation (≤15 min) and improved performance, achieving a maximum stress of 54 kPa, strain of 168%, and water absorption of 566%. We incorporated natural anthocyanins and fine-tuned them to produce four distinct colour changes in response to urine pH, with significantly improved colour differentiation (ΔE). Upon contact with urine, the hydrogel displays green within the normal pH range, indicating a healthy state. At the same time, a reddish-purple or blue colour serves as a visual warning of abnormal acidity or alkalinity. This intelligent hydrogel system combines rapid gelation, excellent mechanical properties, and a sensitive visual response, offering a promising platform for body fluid monitoring. Full article

Background: Stair ambulation is a complex motor task that presents a substantial fall risk for people with Parkinson’s disease (PwPD) who often have postural instability and gait difficulty (PIGD) and experience unpredictable freezing of gait (FOG) episodes. While dual-task (DT) interference during level walking is well-documented, its impact on stair ambulation, an everyday, high-risk activity, remains poorly understood. Objective: The aim of this study was to quantify the impact of dual tasking on patterns of motor control during stair ambulation using kinetic data from The Stair Ambulation and Functional Evaluation of Gait (Safe-Gait) system. Methods: Seventeen individuals with Parkinson’s disease (PD) completed three single-task (ST) and three dual-task (DT) trials on the Safe-Gait system, which sampled kinetic data via embedded force plates during stair ascent and descent. The force plate data were used to quantify step time, braking and propulsive impulses, and center of pressure (CoP) displacement and sway speed to assess DT effects on stair ambulation kinetics. Results: Dual-task conditions led to significant increases in step time (p < 0.001), braking impulse (p < 0.01), anteroposterior center of pressure (CoP) range (p < 0.05), and a decrease in mediolateral CoP speed (p < 0.01). Conclusions: Dual tasking during stair ambulation altered gait kinetics in PwPD, evidenced by slower, less stable movement patterns. These findings highlight the impact of cognitive motor DT interference on functional mobility and support the use of instrumented stair assessments to guide therapeutic care and fall risk interventions. Full article

This study introduces a novel deep learning architecture for vessel trajectory prediction based on Automatic Identification System (AIS) data. The motivation stems from the increasing importance of maritime transport and the need for intelligent solutions to enhance safety and efficiency in congested waterways—particularly with respect to collision avoidance and real-time traffic management. Special emphasis is placed on river navigation scenarios that limit maneuverability with the demand of higher forecasting precision than open-sea navigation. To address these challenges, we propose a Principal Component Analysis (PCA)-driven layered attention mechanism integrated within an encoder–decoder model to reduce redundancy and enhance the representation of spatiotemporal features, allowing the layered attention modules to focus more effectively on salient positional and movement patterns across multiple time steps. This dual-level integration offers a deeper contextual understanding of vessel dynamics. A carefully designed evaluation framework with statistical hypothesis testing demonstrates the superiority of the proposed approach. The model achieved a mean positional error of 0.0171 nautical miles (SD: 0.0035), with a minimum error of 0.0006 nautical miles, outperforming existing benchmarks. These results confirm that our PCA-enhanced attention mechanism significantly reduces prediction errors, offering a promising pathway toward safer and smarter maritime navigation, particularly in traffic-critical riverine systems. While the current evaluation focuses on short-term horizons in a single river section, the methodology can be extended to complex environments such as congested ports or multi-ship interactions and to medium-term or long-term forecasting to further enhance operational applicability and generalizability. Full article

We present a dual biosensing strategy integrating Quartz Crystal Microbalance (QCM) and Surface-Enhanced Raman Spectroscopy (SERS) for the quantitative and molecular-specific detection of FKBP12. Silver nanodendritic arrays were electrodeposited onto QCM sensors, optimized for SERS enhancement using Rhodamine 6G, and functionalized with a custom-designed receptor to selectively capture FKBP12. QCM measurements revealed a two-step Langmuir adsorption behavior, enabling sensitive mass quantification with a low limit of detection. Concurrently, in situ SERS analysis on the same sensor provided vibrational fingerprints of FKBP12, resolved through comparative studies of the free protein, surface-bound receptor, and surface-bound receptor–protein complex. Ethanol-induced denaturation confirmed protein-specific peaks, while shifts in receptor vibrational modes—linked to FKBP12 binding—demonstrated dynamic molecular interactions. A ratiometric parameter, derived from key peak intensities, served as a robust, concentration-dependent signature of complex formation. This platform bridges quantitative (QCM) and structural (SERS) biosensing, offering real-time mass tracking and conformational insights. The nanodendritic substrate’s dual functionality, combined with the receptor’s selectivity, advances label-free protein detection for applications in drug diagnostics, with potential adaptability to other target analytes. Full article

This paper proposes a novel dual-functional radar-communication (DFRC) framework that integrates unmanned aerial vehicle (UAV) communications into an integrated sensing and communication (ISAC) system, termed the ISAC-UAV architecture. In this system, the UAV’s mobility is leveraged to simultaneously serve multiple single-antenna uplink users (UEs) and perform radar-based sensing tasks. A key challenge stems from the target position uncertainty due to movement, which impairs matched filtering and beamforming, thereby degrading both uplink reception and sensing performance. Moreover, UAV energy consumption associated with mobility must be considered to ensure energy-efficient operation. We aim to jointly maximize radar sensing accuracy and minimize UAV movement energy over multiple time steps, while maintaining reliable uplink communications. To address this multi-objective optimization, we propose a deep reinforcement learning (DRL) framework based on a long short-term memory (LSTM)-enhanced deep deterministic policy gradient (DDPG) network. By leveraging historical target trajectory data, the model improves prediction of target positions, enhancing sensing accuracy. The proposed DRL-based approach enables joint optimization of UAV trajectory and uplink power control over time. Extensive simulations validate that our method significantly improves communication quality and sensing performance, while ensuring energy-efficient UAV operation. Comparative results further confirm the model’s adaptability and robustness in dynamic environments, outperforming existing UAV trajectory planning and resource allocation benchmarks. Full article

Inspection, maintenance, and repair (IMR) operations on underwater infrastructure remain costly and time-intensive because fully teleoperated remote operated vehicle s(ROVs) lack the range and dexterity necessary for precise cooperative underwater manipulation, and the alternative of using professional divers is ruled out due to the risk involved. This work presents and experimentally validates an autonomous, dual-I-AUV (Intervention–Autonomous Underwater Vehicle) system capable of assembling rigid pipeline segments through coordinated actions in a confined underwater workspace. The first I-AUV is a Girona 500 (4-DoF vehicle motion, pitch and roll stable) fitted with multiple payload cameras and a 6-DoF Reach Bravo 7 arm, giving the vehicle 10 total DoF. The second I-AUV is a BlueROV2 Heavy equipped with a Reach Alpha 5 arm, likewise yielding 10 DoF. The workflow comprises (i) detection and grasping of a coupler pipe section, (ii) synchronized teleoperation to an assembly start pose, and (iii) assembly using a kinematic controller that exploits the Girona 500’s full 10 DoF, while the BlueROV2 holds position and orientation to stabilize the workspace. Validation took place in a 12 m × 8 m × 5 m water tank. Results show that the paired I-AUVs can autonomously perform precision pipeline assembly in real water conditions, representing a significant step toward fully automated subsea construction and maintenance. Full article

Rapid screening of foodborne pathogens is critical for food safety, yet current detection techniques often suffer from low efficiency and complexity. In this study, we developed a sliding microfluidic colorimetric biosensor for the fast, sensitive, and multiplex detection of Salmonella. First, the target bacteria were specifically captured by antibody-functionalized magnetic nanoparticles in the microfluidic chip, forming magnetic bead–bacteria complexes. Then, through motor-assisted sliding of the chip, manganese dioxide (MnO₂) nanoflowers conjugated with secondary antibodies were introduced to bind the captured bacteria, generating a dual-antibody sandwich structure. Finally, a second sliding step brought the complexes into contact with a chromogenic substrate, where the MnO₂ nanoflowers catalyzed a colorimetric reaction, and the resulting signal was used to quantify the Salmonella concentration. Under optimized conditions, the biosensor achieved a detection limit of 10 CFU/mL within 20 min. In spiked pork samples, the average recovery rate of Salmonella ranged from 94.9% to 125.4%, with a coefficient of variation between 4.0% and 6.8%. By integrating mixing, separation, washing, catalysis, and detection into a single chip, this microfluidic biosensor offers a user-friendly, time-efficient, and highly sensitive platform, showing great potential for the on-site detection of foodborne pathogens. Full article

High penetration of photovoltaic (PV) generation presents new challenges for voltage regulation in distribution networks (DNs), primarily due to output intermittency and constrained reactive power capabilities. This paper introduces a distributed voltage control method leveraging reactive power compensation from PV inverters. Instead of relying on centralized computation, the proposed method allows each inverter to make local decisions using real-time voltage measurements and delayed communication with neighboring PV nodes. To account for practical asynchronous communication and feedback delay, a Distributed Online Primal–Dual Push–Sum (DOPP) algorithm that integrates a fixed-step delay model into the push–sum coordination framework is developed. Through extensive case studies on a modified IEEE 123-bus system, it has been demonstrated that the proposed method maintains robust performance under both static and dynamic scenarios, even in the presence of fixed feedback delays. Specifically, in static scenarios, the proposed strategy rapidly eliminates voltage violations within 50–100 iterations, effectively regulating all nodal voltages into the acceptable range of [0.95, 1.05] p.u. even under feedback delays with a delay step of 10. In dynamic scenarios, the proposed strategy ensures 100% voltage compliance across all nodes, demonstrating superior voltage regulation and reactive power coordination performance over conventional droop and incremental control approaches. Full article

Decision making is challenging in autonomous driving (AD) under highway scenarios because of the unpredictable behaviors of neighbor vehicles, leading to the necessity of accurately modelling interactions between vehicles. Though ego-attention, a variant of self-attention, provides a way for object interaction extraction, its feature expression still needs to improve. This paper improves the original ego-attention by reweighting the encoding vehicle features, forcing them to pay more attention to significant features. Moreover, we designed a rule-based driver assistance module (DAM) to alleviate mis-decisions by constraining action space. Finally, we constructed our final AD decision-making model by integrating the proposed reweighting ego-attention and the DAM into the dual-input decision-making framework trained by enhanced deep reinforcement learning (DRL). We evaluated our decision-making model on highway scenarios. The results show that our model achieves better performance in success step (39.95 steps/episode), speed (29.15 m/s), lane-changing times (5.64 times/episode), and task completion rate (98%) than existing models, including DRL-GAT-SA, AE-D3QN-DA, and ego-attention-based ones, implying the competitive driving accuracy, safety, and comfort of our model. Full article

The spread of COVID-19 is influenced by multiple factors, including control policies, virus characteristics, individual behaviors, and environmental conditions, exhibiting highly complex nonlinear dynamic features. The time series of new confirmed cases shows significant nonlinearity and non-stationarity. Traditional prediction methods that rely solely on one-dimensional case data struggle to capture the multi-dimensional features of the data and are limited in handling nonlinear and non-stationary characteristics. Their prediction accuracy and generalization capabilities remain insufficient, and most existing studies focus on single-step forecasting, with limited attention to multi-step prediction. To address these challenges, this paper proposes a multi-module fusion prediction model—TSMixer-BiKSA network—that integrates multi-feature inputs, Variational Mode Decomposition (VMD), and a dual-branch parallel architecture for 1- to 3-day-ahead multi-step forecasting of new COVID-19 cases. First, variables highly correlated with the target sequence are selected through correlation analysis to construct a feature matrix, which serves as one input branch. Simultaneously, the case sequence is decomposed using VMD to extract low-complexity, highly regular multi-scale modal components as the other input branch, enhancing the model’s ability to perceive and represent multi-source information. The two input branches are then processed in parallel by the TSMixer-BiKSA network model. Specifically, the TSMixer module employs a multilayer perceptron (MLP) structure to alternately model along the temporal and feature dimensions, capturing cross-time and cross-variable dependencies. The BiGRU module extracts bidirectional dynamic features of the sequence, improving long-term dependency modeling. The KAN module introduces hierarchical nonlinear transformations to enhance high-order feature interactions. Finally, the SA attention mechanism enables the adaptive weighted fusion of multi-source information, reinforcing inter-module synergy and enhancing the overall feature extraction and representation capability. Experimental results based on COVID-19 case data from Italy and the United States demonstrate that the proposed model significantly outperforms existing mainstream methods across various error metrics, achieving higher prediction accuracy and robustness. Full article

Path planning for picking safflowers is a key component in ensuring the efficient operation of robotic safflower-picking systems. However, existing single-arm picking devices have become a bottleneck due to their limited operating range, and a breakthrough in multi-arm cooperative picking is urgently needed. To address the issue of inadequate adaptability in current path planning strategies for dual-arm systems, this paper proposes a novel path planning method for dual-arm picking (LTSACO). The technique centers on a dynamic-weight heuristic strategy and achieves optimization through the following steps: first, the K-means clustering algorithm divides the target area; second, the heuristic mechanism of the Ant Colony Optimization (ACO) algorithm is improved by dynamically adjusting the weight factor of the state transition probability, thereby enhancing the diversity of path selection; third, a 2-OPT local search strategy eliminates path crossings through neighborhood search; finally, a cubic Bézier curve heuristically smooths and optimizes the picking trajectory, ensuring the continuity of the trajectory’s curvature. Experimental results show that the length of the parallelogram trajectory, after smoothing with the Bézier curve, is reduced by 20.52% compared to the gantry trajectory. In terms of average picking time, the LTSACO algorithm reduces the time by 2.00%, 2.60%, and 5.60% compared to DCACO, IACO, and the traditional ACO algorithm, respectively. In conclusion, the LTSACO algorithm demonstrates high efficiency and strong robustness, providing an effective optimization solution for multi-arm cooperative picking and significantly contributing to the advancement of multi-arm robotic picking systems. Full article

Chirped radio-frequency signals are essential waveforms in radar systems. To enhance resolution and improve the signal-to-noise ratio through higher energy transmission, chirps with high time–bandwidth products are highly desirable. Photonic technologies, with their ability to handle broad electrical bandwidths, have been widely employed in the generation, filtering, processing, and detection of broadband electrical waveforms. In this work, we propose a photonics-based large-TBWP RF chirp generator utilizing dual optical frequency combs with a small difference in the repetition rate. By employing dispersion modules for frequency-to-time mapping, we convert the spectral interferometric patterns into a temporal RF sinusoidal carrier signal whose frequency is swept through the optical shot-to-shot delay. We derive analytical expressions to quantify the system’s performance under various design parameters, including the comb repetition rate and its offset, the second-order dispersion, the transform-limited optical pulse width, and the photodetector’s bandwidth limitations. We benchmark the expected system performance in terms of RF bandwidth, chirp duration, chirp rate, frequency step size, and TBWP. Using realistic dual-comb source parameters, we demonstrate the feasibility of generating RF chirps with a duration of 284.44 $\mathsf{\mu }$s and a bandwidth of 234.05 GHz, corresponding to a TBWP of $3.3\times {10}^7$. Full article

This study investigates the integration of advanced optimization algorithms within energy-intensive infrastructures and industrial plants. In fact, the authors focus on the dynamic interplay between computational intelligence and operational efficiency in wastewater treatment plants (WWTPs). In this context, energy optimization is thought of as a hybrid process that emerges at the intersection of engineered systems, environmental dynamics, and operational constraints. Despite the known energy-intensive nature of WWTPs, where pumps and blowers consume over 60% of total power, current methods lack systematic, real-time adaptability under variable conditions. To address this gap, the study proposes a computational framework that combines hydraulic simulation, manufacturer-based performance mapping, and a Memetic Algorithm (MA) capable of real-time optimization. The methodology synthesizes dynamic flow allocation, auto-tuning mutation, and step-by-step improvement search into a cohesive simulation environment, applied to a representative parallel-pump system. The MA’s dual capacity to explore global configurations and refine local adjustments reflects both static and kinetic aspects of optimization: the former grounded in physical system constraints, the latter shaped by fluctuating operational demands. Experimental results across several stochastic scenarios demonstrate consistent power savings (12.13%) over conventional control strategies. By bridging simulation modeling with optimization under uncertainty, this study contributes to sustainable operations management, offering a replicable, data-driven tool for advancing energy efficiency in infrastructure systems. Full article

To address challenges of background interference and limited multi-scale feature extraction in infrared small target detection, this paper proposes a YOLO-HVS detection algorithm inspired by the human visual system. Based on YOLOv8, we design a multi-scale spatially enhanced attention module (MultiSEAM) using multi-branch depth-separable convolution to suppress background noise and enhance occluded targets, integrating local details and global context. Meanwhile, the C2f_DWR (dilation-wise residual) module with regional-semantic dual residual structure is designed to significantly improve the efficiency of capturing multi-scale contextual information by expanding convolution and two-step feature extraction mechanism. We construct the DroneRoadVehicles dataset containing 1028 infrared images captured at 70–300 m, covering complex occlusion and multi-scale targets. Experiments show that YOLO-HVS achieves mAP50 of 83.4% and 97.8% on the public dataset DroneVehicle and the self-built dataset, respectively, which is an improvement of 1.1% and 0.7% over the baseline YOLOv8, and the number of model parameters only increases by 2.3 M, and the increase of GFLOPs is controlled at 0.1 G. The experimental results demonstrate that the proposed approach exhibits enhanced robustness in detecting targets under severe occlusion and low SNR conditions, while enabling efficient real-time infrared small target detection. Full article