Search Results (3,581)

Driving behavior recognition plays a crucial role in intelligent driving systems and road traffic safety. Due to insufficient driving experience and limited ability to allocate visual attention, novice drivers are considered a high-risk group for traffic accidents. Existing approaches primarily focus on experienced drivers and rely on single-modal eye-tracking data, making it difficult to model spatial attention distributions and long-term temporal dependencies simultaneously. Moreover, these methods are often affected by modality asynchrony during multimodal fusion, further limiting performance gains. To address these challenges, this study proposes a novice driver behavior recognition method based on bimodal eye-tracking features and a gated cross-modal attention fusion (GCMAF) mechanism. The model adopts a spatial–temporal dual-branch architecture. The spatial branch employs ResNet34 to extract eye-tracking heatmap features to represent the visual attention distribution. In contrast, the temporal branch integrates a 1D-CNN with the Mamba model to capture local dynamic patterns and long-range temporal dependencies. In the fusion stage, the GCMAF module is introduced to enhance cross-modal interactions, and a gating mechanism is further used to adaptively adjust modality weights, thereby mitigating the adverse effects of modality asynchrony. To validate the effectiveness and generalization ability of the proposed method, repeated experiments and five-fold cross-validation are conducted. The results demonstrate that the model achieves an average classification accuracy of 93.86% across four driving behavior categories, with standard deviations below 0.3%. Compared with baseline methods, paired t-test results show that the performance improvement is statistically significant (p < 0.01). Ablation studies further confirm the independent contribution of each component. Overall, the proposed method outperforms existing approaches in terms of accuracy and stability, providing effective support for driving behavior assessment and proactive safety warning systems. Full article

This paper investigates the feasibility of 3D self-localization and tracking using chipless radio frequency identification (RFID) tags operating in the terahertz (THz) frequency band. The primary objective is to achieve sub-millimeter (sub-mm) localization and tracking accuracy while minimizing reliance on external infrastructure. To this end, a hybrid localization framework is proposed that jointly exploits round-trip time-of-flight (RToF) and angle-of-arrival (AoA) measurements to enhance localization performance. Although near-field propagation effects are inherently significant in the considered THz operating regime, a simplified far-field approximation is adopted to facilitate tractable system modeling and analytical development. The proposed framework is further extended to dynamic scenarios through an extended Kalman filter (EKF)-based tracking algorithm, which incorporates temporal state evolution to improve estimation robustness under noisy measurements. Furthermore, the Cramér–Rao lower bound (CRLB) for the hybrid RToF-AoA system is derived to establish the fundamental limits of localization accuracy under varying system configurations and measurement conditions. Simulation results demonstrate that the proposed approach is capable of achieving sub-mm localization and tracking accuracy with a highly constrained anchor infrastructure, including operation with a single anchor in the considered scenario. These findings highlight the potential of THz chipless RFID technology as a promising enabling solution for next-generation high-accuracy localization and tracking applications. Full article

Background: Left ventricular (LV) dysfunction remains the leading cause of mortality in transfusion-dependent beta-thalassemia (TDßT), yet conventional echocardiography often fails to detect early myocardial impairment. This study aimed to comprehensively evaluate LV function in children with TDßT using three-dimensional echocardiography (3DE) and speckle-tracking strain analysis, comparing diagnostic performance with conventional two-dimensional (2D) parameters. Results: 50 TDßT patients were compared to 50 matched controls and exhibited preserved conventional LV ejection fraction (EF) on 2D (65.31 ± 7.12% vs. 69.21 ± 3.87%, p = 0.001), but 3DE revealed significant ventricular dilation with higher end-diastolic volume index (75.50 ± 17.99 vs. 65.63 ± 11.86 mL/m², p = 0.002) and end-systolic volume index (22.28 ± 7.85 vs. 18.21 ± 5.14 mL/m², p = 0.003). Despite preserved 3D EF (70.79 ± 5.98% vs. 72.07 ± 5.76%, p = 0.276), global longitudinal strain (GLS) was significantly impaired (−18.56 ± 2.37% vs. −21.47 ± 1.86%, p < 0.001). 3D volumetric parameters demonstrated superior diagnostic performance (AUC for LVEDVI Z-score = 0.874) compared to conventional indices. Transfusion duration correlated strongly with ventricular volumes (r = 0.569 for EDV, p < 0.001), while serum ferritin showed no significant correlation with cardiac parameters. Conclusions: Children with TDßT develop early subclinical LV dysfunction detectable by 3DE and strain analysis despite preserved conventional systolic indices. 3D volumetry and GLS should be integrated into routine cardiac surveillance protocols to enable timely therapeutic intervention. Full article

Conventional transient stability assessment in multi-machine power systems relies predominantly on fixed thresholds, which exhibit limited adaptability to varying operating conditions and fail to provide a unified analytical framework for rotor angle and voltage stability. To address these challenges, this paper proposes an adaptive threshold warning method based on geometric algebra. A multi-dimensional unified state vector incorporating generator rotor angles, speeds, electromagnetic powers and bus voltage magnitudes and phases is constructed to map system dynamics onto a high-dimensional geometric trajectory. The second- and third-order wedge products of this trajectory are computed to quantify disturbance severity and volumetric expansion preceding instability. An adaptive threshold mechanism is established utilizing sliding window robust statistics (Median Absolute Deviation) to track the trajectory’s instantaneous dimension in real time. Validation on the IEEE 39-bus system demonstrates that the proposed method issues a warning at t = 4.90 s, achieving a detection advance of 0.30 s relative to the conventional 30° rotor angle separation threshold. The method exhibits strong noise robustness with only 40 ms warning delay under 20 dB SNR conditions, and effectively captures rotor angle–voltage coupling characteristics. The geometric algebra framework offers a unified assessment tool with distinct advantages in computational speed, adaptivity, and interpretability. Full article

Determining the 3D position of a vehicle from a 2D image plays a key role in video surveillance, autonomous driving, and spatial localization. However, localization accuracy can significantly degrade in conditions of incomplete or synthetic measurement noise and keypoint jitter. In this paper, we propose a new iterative 3D position estimation algorithm (KGA). This algorithm includes geometric correction and calibration steps for converting from 2D to 3D coordinates; trajectory prediction and correction using a Kalman filter; and adaptive tuning of the filter parameters using the Goldschmidt algorithm. Experiments confirm that KGA outperforms the standard (FK) and modified (MFK) Kalman filters in accuracy and convergence speed, demonstrating robustness to various camera angles and noise levels. The novelty of this approach lies in the integration of the Goldschmidt algorithm into the Kalman filter to create an adaptation mechanism that dynamically adjusts the measurement noise covariance based on instantaneous innovation magnitude. Unlike end-to-end deep learning trackers or nonlinear filters (EKF/UKF), KGA is designed as a lightweight post-processing stage that can be seamlessly integrated into existing detection pipelines while maintaining the low computational footprint required for UAV-based edge deployment. The algorithm is of practical value for computer vision systems requiring accurate and robust tracking under varying observational conditions, with current implementation suitable for offline or buffered processing, and clear pathways to real-time deployment through code optimization. The algorithm is of practical value for computer vision systems requiring accurate and robust tracking under varying observational conditions. Full article

This study introduces the design process and fabrication method of a soft pneumatic silicone-based exosuit intended to assist human elbow extension and flexion movement for rehabilitation. First of all, an integrated fabrication method is developed to replace the step-by-step casting and cloth fiber layer, using a 3D-printed PVA mold in silicone casting to ensure the airtightness of the silicone actuator, and a carbon fiber woven mesh is used as the base plate of the actuator to improve its bending performance. Then, the finite element analysis is used to optimize the geometric parameters, hardness, and the number of air chambers for the exosuit structure. The experimental evaluation confirms that the exosuit achieves a bending angle of 112 degrees without any load and 71 degrees with a load of 2 kg. Combining with the PI angular controller, the system limits the maximum absolute tracking error to 4.29 degrees. These results also suggest the proposed exosuit is a promising candidate for practical rehabilitation tasks. Full article

Water damage under the coupled effects of traffic load and pore water pressure (PWP) is a primary cause of early failure in asphalt pavements. Although dense-graded pavements generally have low void ratios, excess PWP poses a severe threat to durability under extreme conditions. These conditions include heavy rainfall, water accumulation in wheel tracks, and upward capillary water rise. In this study, a mesoscopic model considering fluid–solid coupling effects was established using the Particle Flow Code in the 2 Dimensions (PFC2D) platform, which is based on the discrete element method (DEM). A parallel-bonded stress corrosion model was introduced to describe damage evolution. The results show that the maximum positive PWP increased monotonically with load, reaching a distinct peak value at a critical loading frequency under specific load amplitudes. At this critical frequency, the fatigue life was significantly shortened compared to lower-frequency conditions. The PWP response exhibited a clear phase lag relative to the applied load, with the lag angle increasing alongside frequency. Furthermore, the absolute value of the minimum PWP continued to increase with fatigue damage accumulation. This indicates that regions with a vacuum suction effect were continuously expanding, which is a key reason for asphalt film stripping from the aggregate surface. These findings provide a theoretical basis for understanding mesoscopic water damage mechanisms in asphalt pavements and offer a reference for durability design. Full article

Multi-agent perceptual map construction and long-term maintenance constitute an important paradigm for improving adaptability and real-world applicability. With the outstanding capability of 3D Gaussian Splatting in preserving fine-grained texture details, a number of 3DGS-based real-time mapping approaches have recently emerged. However, these methods often struggle to cope with complex dynamics in real-world environments and lack the generalization needed to scale to multi-agent systems. Existing solutions typically rely on direct parameter concatenation or locally confined optimization, which are unable to explicitly model cross-agent observation reliability under temporal asynchrony and dynamic inconsistency, and therefore tend to amplify conflicting updates rather than resolve them. To address these limitations, we propose DGOMapping, an online system for multi-agent dynamic perceptual mapping. DGOMapping leverages an uncertainty-coupled 4DGS scene representation and a collaborative interaction mechanism via Gaussian perception-score exchange, enabling both real-time 4DGS construction and long-term map memory adjustment. Experiments on multiple real-world datasets demonstrate that DGOMapping effectively suppresses dynamic interference and exploits multi-agent collaboration, achieving state-of-the-art performance in both tracking and reconstruction. The proposed system therefore provides a practical sensing-oriented solution for collaborative perception and real-time dynamic environment mapping. Full article

Adaptive Sidelobe Cancellation (ASLC) is a core technology for modern radar systems to suppress active sidelobe jamming. From the perspective of disrupting the ASLC system’s ability to stably track the jamming direction, this paper proposes a distributed jamming method based on random phase perturbation. The method employs two spatially separated jamming sources that simultaneously transmit coherent signals. By actively applying controllable random jumps to the relative phase between the two sources, the equivalent wavefront direction of the synthesized signal at the radar receiver changes rapidly, forming a non-stationary jamming that destroys the null-tracking capability of ASLC. An analytical model of the ASLC cancellation ratio (CR) under random phase perturbation is established, with a focus on analyzing the effects of time synchronization accuracy and phase synchronization accuracy on jamming performance. Monte Carlo simulation results show that the proposed method can reduce the average ASLC CR from 26.80 dB to 20.29 dB (a decrease of 6.51 dB). Under identical conditions, this performance is comparable to asynchronous blinking jamming while requiring no precise timing matching, and outperforms multi-source saturation jamming in resource efficiency (two vs. four jammers). This study provides promising simulation-level evidence for the effectiveness of the proposed jamming method. The quantitative results and sensitivity analyses offer a simulation-level theoretical reference for parameter design of distributed cooperative jamming. Further validation in semi-physical simulations or field trials is necessary before claiming engineering readiness. Full article

Autonomous driving necessitates a robust 3D perception system that includes accurate object detection, tracking, and segmentation. While recent low-cost camera-based methods have demonstrated promising results, these systems are prone to performance degradation under poor lighting conditions or adverse weather, resulting in considerable localization errors. In this paper, we present a novel approach called Frequency-aware Depth Association Radar-Camera (FDARC) Fusion. This method aims to generate semantically rich and spatially accurate Bird’s-Eye-View (BEV) feature maps by integrating data from both camera and radar sensors. Initially, the image features are enhanced using frequency-aware techniques. Subsequently, these features are transformed into BEV representation with the assistance of depth information estimated from both sensor modalities and radar measurements. This process, known as Depth Association (DA), facilitates more precise BEV representations. Following this, a Temporal and Deformable Cross-Fusion (TDCF) layer is utilized to encode multi-modal feature maps into a unified space-time dimension representation. Extensive experiments conducted on the nuScenes dataset show that FDARC achieves state-of-the-art performance in 3D detection tasks, markedly outperforming baseline models on the nuScenes val set using a ResNet-50 backbone, which attains 53.5% nuScenes Detection Score (NDS) and 44.7% mean Average Precision (mAP). Full article

Introduction: Biological invasions are a major driver of biodiversity loss, particularly in freshwater ecosystems. The Iberian Peninsula, a hotspot of endemic diversity, is increasingly threatened by invasive predatory fish, which may exert higher predatory rates under warmer environmental conditions, disrupting/endangering native fish communities. One such species is the European catfish (Silurus glanis), a large and voracious apex predator. Despite growing research, most telemetry studies have focused on lentic systems, limiting our understanding of its behaviour in lotic environments. Moreover, high-resolution biologging approaches remain largely unexplored. Objective: This study aims to characterize the habitat use and activity patterns of European catfish in a non-native lotic section of the lower Tagus River, and to identify key environmental drivers shaping its predatory behaviour. Methodology: Adult individuals were tagged with radio telemetry transmitters equipped with temperature, pressure (depth), and 3D-accelerometer archival sensors. A preliminary controlled experiment established activity thresholds to classify behaviours. Ten adult fish were then actively tracked over one year, combining spatial data with high-resolution biologging. Habitat use and activity patterns were analyzed across seasonal and circadian scales. Generalized Additive Models (GAMs) were used to assess the effects of environmental variables on activity levels and depth use, while Hurdle models were applied to identify the environmental drivers influencing the occurrence and frequency of burst activity events (predatory behaviour proxies). Results: Fish displayed strong site fidelity, frequently using structured habitats near riverbanks. European catfish also showed clear seasonal and circadian patterns in habitat use and activity, occupying deeper habitats in winter and shallower areas in warmer seasons. Activity occurred year-round, increasing in spring and summer and peaking at dusk, being influenced by temperature, river flow, season, and time of day. Burst activity occurred more often in spring and at dusk. Conclusions: This study unveils insights on European catfish behaviour in invaded lotic systems, highlighting consistent patterns linked to environmental conditions. These findings can support more targeted and effective management strategies for controlling this invasive species. Full article

The accuracy of shallow-water multibeam bathymetry is critically dependent on precise heave correction. However, sensor limitations often lead to incomplete correction, leaving periodic along-track stripe noises (heave residuals) that distort seabed morphology. Traditional filtering methods suppress this noise at the expense of genuine topographic detail. This paper proposes an innovative Data Feedback Correction (DFC) method that corrects the error at its source. DFC establishes a closed-loop framework: it diagnoses the residual’s dominant frequency from central beam data, extracts the residual signal via targeted filtering, and feeds it back as a compensation term into the original sensor heave sequence. This drives a recomputation of the geometric positioning, achieving source-level correction. In a field case, DFC demonstrated targeted, high-fidelity performance. Across all 34 survey lines, DFC achieved an average spectral attenuation of 1.85 dB (range: 1.0–3.7 dB) in the dominant residual band and reduced the RMSE of overlap discrepancies from 0.0923 m to 0.0773 m (a 16.25% improvement). Independent validation using 94,999 control line intersections further demonstrates a 14.31% RMSE improvement relative to an uncorrected control line reference, confirming that the correction improves both internal consistency and external accuracy, significantly enhancing internal consistency. Compared to moving average and wavelet denoising, DFC achieved comparable quantitative improvement while effectively suppressing visual stripes and features that are consistent with the original data, avoiding the over-smoothing or residual noise of traditional methods. This study confirms that closed-loop feedback of data residuals can fundamentally address spectrally aliased stripe noise, shifting the paradigm from “masking noise” to “correcting the source.” The method enhances data consistency in the tested scenario without sacrificing topographic authenticity, providing a promising new tool that warrants further validation across diverse survey conditions. Full article

The squat is a critical component of numerous rehabilitation and functional assessment protocols, playing a significant role in enhancing athletic performance and activities of daily living. Although some of the characteristics gathered during the squat need additional confirmation, Kinovea provides a free two-dimensional squat motion analysis tool that is simple to use in clinical practice. This analytical, cross-sectional reliability study aimed to evaluate the intra-rater and test–retest reliability (with a 20 min interval between performances) of loaded squat kinematics in a sample of women using Kinovea. Twenty women performed a loaded back squat; intra-rater reliability was assessed by re-analyzing the same video one week apart, and test–retest reliability was assessed across two performances separated by 20 min. The results showed good to excellent intra-rater reliability (ICC: 0.75–0.99; SEM: 0.16 cm to 5.14°; MDC: 0.44 cm to 14.24°), and moderate to excellent test–retest reliability (ICC: 0.64–0.98; SEM: 0.36 cm to 14.29°; MDC: 0.99 cm to 39.61°). Variables tracked in the sagittal plane showed high precision. Conversely, the head angle and knee angle in the frontal plane exhibited greater variability, reflected by higher SEM and MDC values. In conclusion, Kinovea is a reliable and accessible tool for clinical kinematic assessment of the squat, particularly in the sagittal plane parameters. However, due to the elevated measurement error observed in head angles and frontal-plane knee dynamics, the integration of 3D motion capture is recommended over 2D digital protocols for these variables. Full article

Head-mounted eye-tracking systems play a critical role in virtual reality, human–computer interaction, and clinical applications, yet achieving both high angular accuracy and precise 3D gaze position estimation with low-cost hardware remains challenging. This paper proposes a lightweight, training-free geometric 3D gaze tracking framework for binocular 3D gaze tracking using consumer-grade hardware, which leverages stereo geometric triangulation and a simplified physiological eye model to achieve robust 3D gaze estimation, requiring only standard infrared cameras and dichroic mirrors without additional specialized hardware. The method was evaluated in controlled indoor conditions with 30 participants, where it achieved an angular error ranging from 1.1° to 2.82° and a 3D gaze position error below 13.24 mm. Compared to two state-of-the-art academic non-deep-learning methods, the proposed framework delivers competitive angular accuracy while significantly reducing 3D position error, outperforming the baselines by 34% to 56% in depth estimation precision. These results demonstrates that the proposed geometric framework is a practical and effective solution for high-precision 3D gaze tracking on low-cost hardware, suitable for both research and consumer applications. Full article

Split-type robots are increasingly deployed in unstructured confined environments such as underground coal mines, where autonomous navigation and cooperative tracking control remain critical challenges. This paper presents a visual target-assisted tracking control scheme for a split-type drilling robot, adopting an active leader–passive follower architecture. The leader robot performs autonomous mobility and obstacle avoidance using 3D LiDAR-based offline path generation and online optimal search. The follower robot uses AprilTag visual fiducial markers to estimate the six-degree-of-freedom relative pose via the Perspective-N-Point algorithm, and it tracks the leader using a two-dimensional fuzzy PID controller that adaptively tunes PID parameters. Extensive experiments are conducted in simulation, simulated tunnels, a large-scale robot platform, and a real drilling robot prototype. Results demonstrate that the leader achieves an average navigation error below 0.175 m, while the follower maintains an average relative tracking error within 0.06 m. The proposed method enables stable, comparable accuracy with smoother, less oscillatory response, and high-precision cooperative navigation for heavy-duty split-type robots, offering a practical solution for intelligent drilling operations in underground confined spaces. Full article