Search Results (3,935)

In tennis, where performance is governed by complex kinetic chain interactions, objective skill classification is vital for coaching and talent identification. This study presents a hierarchical deep learning framework leveraging synchronized bilateral Inertial Measurement Unit (IMU) data from 39 participants (11 elite, 28 amateur). The proposed system successfully distinguishes expertise levels across a total of 4594 strokes, including augmented samples.. A hybrid Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) architecture was developed to autonomously extract spatiotemporal features from the raw kinematic signals of forehand, backhand, service, and volley strokes. The proposed model achieved an accuracy of 95.54%, significantly outperforming both traditional machine learning and state-of-the-art deep learning benchmarks. Qualitative t-distributed Stochastic Neighbor Embedding (t-SNE) analyses revealed that elite athletes form highly homogeneous clusters in the feature space. Furthermore, quantitative Asymmetry Index assessments confirmed that professionals exhibit superior bilateral coordination stability. These findings demonstrate that the proposed end-to-end system offers a robust, field-applicable solution for identifying technical excellence. It provides coaches with reliable digital biomarkers, thereby overcoming the limitations of subjective visual observation. Full article

Background/Objectives: Understanding the microstructure of ingestive behavior (IB) is critically important to the development and success of interventions to change eating rates and produce more optimal food energy intake outcomes. Detailed measurement of IB microstructure is needed to guide development of real-time sensing approaches that can support such interventions. This article summarizes novel measurement and inference strategies around both digital video and inertial motion sensors in a structured laboratory protocol. Methods: Digital video footage was annotated for chews and bites and analyzed with generalized additive models to assess differences in IB for each of four meal courses varying by food texture. Results: Significant differences were revealed in IB microstructure in the form of nonlinear patterns of annotated video footage and initial sensing tests, indicating an optimal sensor location over the jaw’s condyle bone. Conclusions: Findings of an intensive longitudinal multicourse full meal protocol reflect important differences in nonlinear trends of eating behavior for diverse texture foods. These differences inform further development of technology-aided measurement strategies, provide an experimental protocol for fieldwide IB inquiry, and reveal expected fundamental differences in ingestion rates. Further inquiry into the underlying causes of nonlinearities for high UPF foods, along with sensor measurements, is warranted. Full article

Tracking biomechanical changes associated with different training modalities remains a methodological challenge in applied sports science. This pilot longitudinal study examined stroke technique stability in seven junior rowers (aged 16.6 ± 0.5 years) across three measurement sessions (March, April, June), separated by two training mesocycles emphasising strength training and intensive rowing, respectively. Upper body angular velocity was recorded using a smartphone-based MEMS sensor fixed to the upper back during incremental ergometer exercise. Overall stroke duration and its standard deviation remained stable throughout the study period, whereas the durations of the two stroke phases corresponding to forward (drive) and backward (recovery) body motion changed systematically across mesocycles. Phase-specific changes were statistically significant in 10 of 12 paired comparisons (rank-sum test) and 7 of 12 within-subject comparisons (Wilcoxon signed-rank test) for phase durations, and in 9 and 5 of 12 comparisons for their standard deviations, respectively. These findings suggest that the internal structure of the rowing stroke is sensitive to training load specificity, even when overall stroke timing remains unchanged, and that smartphone-based angular velocity analysis provides a feasible tool for individualized biomechanical monitoring in young athletes. Full article

Wearable inertial measurement units are widely used for human motion analysis due to their portability; however, most IMU-based motion capture systems rely on dense sensor configurations that increase cost, complexity, and usability challenges in real-world applications. To address this limitation, this paper presents a sparse inertial human motion reconstruction framework that uses only five wearable sensors while maintaining real-time performance and biomechanical plausibility. The proposed framework integrates Movella Xsens DOT IMUs with a learning-based inverse kinematics pipeline and a real-time biomechanical digital twin for motion reconstruction and visualization. The evaluation was conducted in two phases: first, a real-time motion streaming system was established to validate sensor alignment, coordinate frame consistency, and end-to-end latency; second, a sparse inference framework was trained using the Virginia Tech Natural Motion Dataset combined with a custom dataset containing hard negative samples. Experimental results show that the system can accurately reconstruct full-body human motion, excluding head movement, with a local Mean Per-Joint Position Error of 5.96 cm using only five sensors. Comparative ablation studies demonstrate that Transformer-based temporal modeling achieves better geometric accuracy and temporal smoothness than recurrent and convolutional baselines, while physics-informed regularization and hard negative mining significantly improve biomechanical consistency and reduce motion jitter. Real-time experiments further demonstrate that the framework operates within interactive latency limits, highlighting its potential for biomechanical digital twin applications. Full article

Lower-limb amputation remains a significant clinical and socio-economic challenge, while the high cost of microprocessor-controlled prostheses (MPKs) limits their widespread accessibility. This paper presents the design and preliminary laboratory-scale evaluation of a low-cost microprocessor-controlled ankle prosthesis intended as a feasibility-oriented alternative platform for future active prosthetic system development. Building upon the previously developed V1 mechanical architecture, an updated CAD model was created in the SolidWorks 2024 environment, and the kinematic configuration was refined using a ball-screw transmission (SFU1204-300) driven by a NEMA 17 stepper motor. The electronic control system integrates an ESP32 microcontroller, an MPU9250 inertial measurement unit (IMU), a limit switch for initial-position detection, and a WiFi-based REST API interface for communication and control. Laboratory no-load experiments demonstrated controlled positional behavior, repeatable angular response, and successful operation of the homing procedure within a motion range of 0–4200 motor steps. The prototype actively generated dorsiflexion–plantar flexion motion in the sagittal plane, while a passive inversion–eversion mechanism was incorporated and intended to improve structural adaptability. IMU-based measurements enabled preliminary monitoring of angular displacement and positional behavior during the experiments. The presented prototype represents an initial engineering feasibility study of a low-cost active ankle actuation architecture and provides a foundation for future investigations involving load-bearing experiments, biomechanical gait analysis, and closed-loop control implementation. Full article

Team handball is an intermittent sport characterized by variable kinematic and neuromuscular demands, which require precise monitoring to optimize training design. The aim of the present study was to establish data-driven intensity thresholds for external load variables and to examine their distribution across training tasks in elite women’s handball. External load was monitored in 17 professional female handball players during five training sessions within a competitive microcycle using inertial measurement units. Kinematic variables (speed, acceleration, and deceleration) and a neuromuscular variable (jump impulse) were analyzed. A k-means clustering approach was applied to classify each variable into five intensity zones. Subsequently, the distribution of these zones across different training tasks was evaluated. The results showed a predominance of low-to-moderate intensity actions across all the variables, with a progressive reduction in the frequency of higher-intensity efforts. Acceleration values were consistently higher than deceleration across all the zones. Jump impulse also followed a similar distribution, reflecting the neuromuscular demands of training. A task-based analysis revealed clear differences in intensity profiles, with tasks involving opposition eliciting higher proportions of moderate-to-high-intensity actions, while tasks without opposition showed an absence of high-intensity zones. These findings provide objective reference values for external load in elite women’s handball and highlight the importance of task design in modulating physical and neuromuscular demands. The use of data-driven thresholds and ecologically valid training tasks may contribute to more effective and individualized load prescription. Full article

Background/Objectives: Children with Autism Spectrum Disorder (ASD, here on termed autistic children) exhibit motor difficulties in social and non-social contexts. Although previous studies have reported behavioral and neural characteristics, their relationship remains largely unexplored. The current study aimed to investigate the behavioral and neural mechanisms underlying interpersonal synchrony in autistic children using simultaneous kinematic and Functional Near-Infrared Spectroscopy (fNIRS) recordings. Methods: Fifty-eight autistic or non-autistic children participated (mean age = 10.1, standard error = 0.3). fNIRS and an inertial measurement unit were used simultaneously to record the neural activity over frontotemporal and parietal regions and arm movement kinematics during a reach-to-clean-up task across three conditions: Watch—the child observed the tester clean up the blocks; Do—the child cleaned up the blocks independently; and Together—the child and tester cleaned up the blocks synchronously. Results: Behaviorally, autistic children demonstrated longer movement displacement, higher average velocity and acceleration, and a greater number of movement units. In terms of cortical activation, autistic children showed hypoactivation in the bilateral precentral gyrus and right inferior parietal lobe, along with hyperactivation in the right middle frontal gyrus, left inferior frontal gyrus, and left inferior parietal lobule. Correlations between kinematic and neural measures suggest that autistic children rely more on online/feedback control to compensate for reduced feedforward control. Conclusions: This study reveals unique compensatory strategies in autistic children, highlighting the connections between neural and behavioral characteristics. These findings have strong potential to inform the development of ASD screening tools and to guide targeted intervention strategies. Full article

Neck pain is increasingly associated with exposure-dependent dysfunction linked to digitally mediated behaviors, prolonged near-work, sustained postures, and reduced movement variability, whereas cervical assessment remains dominated by static imaging and brief in-clinic examination. This narrative review evaluates why current diagnostic approaches remain poorly suited to the dynamic nature of many contemporary cervical disorders and examines segmental cervical motion as a clinically relevant but insufficiently observed functional target. Evidence from static imaging, dynamic radiographic methods, laboratory motion analysis, wearable inertial sensing, markerless video, and digital measure validation frameworks is synthesized to assess both current capabilities and translational limitations. Dynamic radiographic methods can characterize intervertebral motion with high anatomical specificity, but they are not suitable for scalable longitudinal monitoring. By contrast, wearable and video-based approaches are more compatible with real-world assessment, yet they capture external head–neck kinematics rather than vertebral-level kinematics directly and remain constrained by indirect observability, soft-tissue artifact, and inference uncertainty. On this basis, the review proposes a four-layer framework for continuous non-invasive cervical functional assessment based on sensing, representation, inference, and clinical interpretation, in which segmental cervical behavior is treated as a latent segment-informed functional construct inferred from multimodal external signals and periodically anchored to sparse reference-grade imaging anchors. Segmental motion signatures are consequently positioned as candidate digital measures for longitudinal cervical monitoring, provided that their development is supported by rigorous analytical and clinical validation, explicit uncertainty reporting, and demonstrated incremental clinical value. Full article

This paper presents a comprehensive UAV testbed that establishes quantitative baselines for hardware vulnerability diagnosis and cyber–physical security validation by leveraging comparative flight logs from PX4-based Software-In-The-Loop (SITL) simulations and multiple real-world quadrotor missions. The testbed utilizes a unified data pipeline centered on the uORB message bus and ULog format, enabling the extraction of high-resolution telemetry, including raw Inertial Measurement Unit (IMU) data, state-estimation, and actuator control signals. Evaluated across varying environmental conditions, side-by-side time-series and statistical analyses reveal critical sim-to-real discrepancies in sensor fidelity, GPS interference, and onboard resource behavior that are often overlooked in virtual environments. Real-world data exposes hardware-induced noise, mechanical vibrations, and electromagnetic disturbances that significantly impact flight stability and system reliability. By mathematically quantifying these discrepancies (e.g., via variance and probability distribution shifts), the proposed testbed establishes a rigorous baseline for distinguishing natural physical variability from anomalous or adversarial behavior. Ultimately, this work provides a foundational framework for developing robust anomaly detection models and validating the cyber–physical security of autonomous UAV systems in safety-critical environments. Full article

Postural stability is an essential component of biomedical assessment, particularly for fall prevention and functional monitoring in older adults. This pilot feasibility study explores whether a single inertial measurement unit (IMU) positioned at the lumbar level can provide preliminary, objective indicators of postural control under controlled testing conditions. Triaxial acceleration and angular data were collected using a low-cost IMU and processed through standard filtering, drift-compensation, and feature-extraction procedures to obtain commonly used sway parameters. Five young adults and one elderly participant were evaluated before and after a two-week balance-training period to examine the system’s sensitivity to training-related changes. The results suggest reductions in sway amplitude, variability, and angular fluctuations across most participants, consistent with expected physiological adaptations. While these findings are exploratory and limited by the small sample size, they indicate that a minimal single-sensor configuration may offer a practical and accessible approach for preliminary balance assessment in clinical and home-based settings. Further validation with larger cohorts and gold-standard reference systems is required. Full article

Gravity-assisted navigation is an important means for underwater vehicles to achieve autonomous, passive, and long-endurance navigation. Among its key procedures, correcting the inertial navigation system (INS) based on gravity matching positions is of critical significance. In this paper, using shipborne measured INS data and gravity data together with a gravity database inverted from satellite altimetry data, the entire process of gravity-assisted navigation was experimentally validated through the normal time-frequency transform (NTFT) and Kalman filtering. NTFT is mainly used for gravity error correction, while Kalman filtering is primarily applied to matching algorithms. The analysis of the results shows that after 68.8 h, gravity-assisted navigation technology (GANT) can maintain navigation accuracy within 2 n mile (1 n mile ≈ 1852 m). Through comparison of different calibration methods, it is concluded that open-loop calibration applied only in the longitude direction is feasible and achieves satisfactory navigation performance. This surface vessel-based gravity-assisted navigation experiment addresses aspects such as experimental conditions and algorithmic techniques, serving as an important foundation for further underwater navigation applications. Full article

Falls in older adults and individuals with balance impairments remain a major concern because they are closely associated with injury, reduced mobility, and loss of independence. This study presents a preclinical proof-of-concept for a cognitive smart walker architecture that combines user-compatible walking assistance with active safety intervention. The system integrates a 2D LiDAR sensor for contactless lower-limb monitoring, a six-degree-of-freedom (6-DOF) force/torque sensor to measure user–walker interaction, and an inertial measurement unit (IMU) for dynamic monitoring, with all data processed in real time on a Raspberry Pi/ROS-based platform. Normal walking assistance is provided through a command-level variable admittance-based controller that converts interaction forces into a smoothed signed duty-cycle command rather than a rigid speed-control signal. Safety decisions are managed by a Hierarchical State Machine (HSM). Early-risk conditions are handled through motor-based dynamic braking, whereas severe physical crises additionally deploy lateral support legs to enlarge the base of support. Within this framework, the system can detect and manage foot entanglement, grip loss, forward fall, vertical collapse, lateral fall, successive crises, and recovery-abort events. In experiments across multiple scenarios, the system correctly detected all 50 crisis cases and did not issue unnecessary interventions in 30 non-crisis cases. These findings show that the proposed architecture can preserve transparent walking assistance during normal gait while providing graded, context-sensitive active safety when risk emerges. Full article

Electronic systems are increasingly used to support pediatric gait assessment by enabling objective measurement of biomechanical parameters beyond traditional laboratory settings. However, although technological development has expanded in adult populations, the extent to which embedded technologies and human–machine interaction (HMI) modalities have been integrated into pediatric monitoring systems remains unclear. This systematic review synthesizes evidence published between 2015 and 2025 on electronic systems applied to pediatric gait biomechanics. The review followed PRISMA guidelines, was registered in PROSPERO (CRD420251230372), and adopted a descriptive synthesis approach. A total of 2619 records were identified, and after eligibility assessment and methodological quality appraisal using CASP, 34 studies were included in the final synthesis. The studies were examined according to system type, interaction characteristics, and biomechanical outcomes. The findings indicate a predominance of wearable architectures and inertial sensing technologies in the literature on electronic systems for pediatric gait monitoring. However, HMI modalities were rarely described, and most systems functioned primarily as passive data acquisition tools. Biomechanical outcomes focused mainly on motion-derived parameters, whereas region-specific plantar-load distribution was infrequently assessed, and no studies reported the use of force-sensitive resistors for zonal pressure monitoring. These findings suggest that future advances may depend on integrative approaches that combine multimodal sensing, interaction mechanisms, and functional load characterization. Full article

Wearable sensors are transformative tools for continuous gait assessment in daily life. Tripping, a leading cause of falls, is closely linked to inadequate foot clearance, making accurate foot height measurement critical for fall risk evaluation. Inertial measurement units offer a practical solution for foot trajectory reconstruction; however, conventional drift correction methods such as zero-velocity updates fail to adequately address cumulative height errors. Recent kinematic constraint-based approaches improve height accuracy but remain limited to offline processing and lack simultaneous activity classification. To address these gaps, we developed a real-time, single-IMU system for continuous foot height trajectory reconstruction with simultaneous classification of five locomotion activities deployed on a smartphone. Twenty healthy adults were recruited for model training and independent validation. Level walking maintained ground reference ($0.0$ cm, 95% CI: [$-1.8$, $1.8$] cm), cumulative height errors remained below 1.1 cm across ramp and stair negotiation with a mean absolute error of 0.42%, and obstacle clearance was quantified. The system achieved 96.08% overall classification accuracy with less than one gait cycle latency. Toe height was estimated through rigid-body transformation with comparable accuracy to the foot height. This framework provides a practical foundation for real-time gait intervention and fall prevention applications. Full article

As global population aging intensifies, fall-related injuries among the elderly have become a critical public health concern. Existing fall detection methods based on wearable IMUs all extract features in the sensor’s body frame, failing to exploit the information embedded in sensor signals. Some higher-performing methods incorporate magnetometer-fused Euler angles to enrich features, but their dependence on specific hardware and fusion algorithms makes exact replication during deployment difficult. In contrast, the proposed MadgwickFall-Net relies on acceleration and angular velocity, and, to the best of our knowledge, for the first time introduces the Madgwick algorithm into fall detection to transform inertial signals into a gravity-aligned global coordinate system. A four-branch parallel architecture processes signals from both coordinate frames, fully exploiting the complementarity between dual-frame signals. Cross-validation on the KFall dataset using 5-fold subject-independent stratification demonstrates an F1-Score of 0.9824 and accuracy of 98.36%, specifically, four main evaluation indicators outperform all comparison models. With only 59.7 KB parameters, the model is suitable for edge device deployment. Rolling inference experiments demonstrate a median pre-impact lead time of 390 ms. MadgwickFall-Net offers a practical and deployable solution for real-world wearable fall detection systems, demonstrating strong potential for protecting elderly individuals in daily life scenarios. Full article