Search Results (2,887)

Markerless video-based motion capture is a fast-developing, low-burden and versatile alternative to marker-based stereophotogrammetry, yet independent validation evidence for several commercial solutions is still scarce. This study validates the markerless software CapturyStudio (The Captury GmbH, Saarbrücken, Germany) for the reconstruction of upper- and lower-limb joint kinematics, comparing it with a validated Xsens (Movella, Henderson, NV, USA) inertial measurement unit system. Ten healthy subjects (five females and five males) performed two standardized clinical tasks, a Reach-To-Grasp gesture for the upper limb and a Timed-Up and Go test for the lower limb, recorded simultaneously with eight BTS SMART EVO-DX 2 (BTS Bioengineering S.p.A., Garbagnate Milanese, Italy) cameras operating in markerless mode and a 17-sensor Xsens system. Elbow, shoulder, knee and hip flexion–extension angles were reconstructed from three-dimensional anatomical keypoints provided by CapturyStudio and compared with the Xsens angles through root mean square error in absolute and percentage terms, range-of-motion accuracy, intraclass correlation coefficient (ICC), Spearman’s coefficient (ρ), Bland–Altman analysis and non-parametric Wilcoxon Rank-Sum tests. CapturyStudio reproduced the temporal pattern of all four angles faithfully (ICC ≥ 0.87; ρ ≥ 0.89), with median discrepancies of about 12° for the elbow and below 8° for shoulder, knee and hip and with the best agreement for the upper limb; the main weakness was a systematic overestimation of hip range of motion. Since both systems are indirect measurement techniques, these values represent the discrepancy between two methods and an upper bound on the error of the markerless system rather than its absolute accuracy. Their magnitude is comparable to the changes regarded as clinically meaningful in goniometric assessment, so the system is presently suited to the analysis of movement patterns rather than to the measurement of absolute joint angles. The study is to be read as a technical comparison of two measurement systems, delimiting the conditions under which future clinical, rehabilitation and sports applications may be pursued. Full article

To address Global Navigation Satellite System (GNSS) spoofing threats to Inertial Navigation System (INS)/GNSS integrated navigation systems, this paper analyzes the internal error propagation mechanisms and quantifies perturbation patterns within the Kalman filter (KF) architecture. Mathematical models for step-type, linear ramp, and nonlinear smooth ramp spoofing are established, and the Anomaly Signal-to-Noise Ratio (ASNR) is adopted to quantify disturbances across four core filtering dimensions based on real-world vehicular test data. The results demonstrate that filtering innovations at the forefront of information fusion respond most directly and sensitively (peaking at an ASNR of 341.4181) with a standard zero-mean Gaussian baseline, serving as the optimal metric for spoofing detection; in contrast, error states exhibit marked amplitude attenuation (maximum ASNR of 116.3291), while filter gains and state covariance show negligible variations (maximum ASNRs of 22.6023 and 19.3014, respectively). Further evaluation of Inertial Measurement Unit (IMU) accuracy constraints reveals that under step spoofing, position innovations remain robust (ASNR: 260–510), whereas velocity innovation ASNR drops by approximately 50% with IMU degradation; under linear ramp spoofing, velocity innovations dominate the response (ASNR: 41.16–70.46) while position innovations decay markedly; and under nonlinear smooth ramp spoofing, overall innovations are suppressed, and low-grade IMUs suffer severe noise masking (peak horizontal ASNRs dropping below 10), significantly enhancing attack stealthiness. The findings provide quantitative empirical evidence and theoretical guidance for anti-spoofing design in integrated navigation. Full article

Accurate localization and mapping are essential for autonomous mobile robots operating in unknown environments. This study investigates the impact of Extended Kalman Filter (EKF)-based sensor fusion on the performance of three widely used two-dimensional (2D) LiDAR Simultaneous Localization and Mapping (SLAM) algorithms: GMapping, Karto SLAM, and SLAM Toolbox. Wheel encoder longitudinal velocity and inertial measurement unit (IMU) yaw angular velocity were fused using an EKF and compared with raw wheel odometry using the MIT Stata Center dataset. Localization performance was evaluated both before and after SLAM using translational and rotational Absolute Pose Error (APE) across multiple trajectory segments. Five repeated executions were performed for each SLAM configuration to characterize run-to-run variability. Prior to SLAM, EKF-filtered odometry reduced translational APE root mean square error (RMSE) by approximately 61–75% and rotational APE RMSE by approximately 65–77% relative to raw odometry. After SLAM, translational differences between the two odometry sources were substantially smaller and varied according to the evaluated algorithm and trajectory, while rotational performance exhibited larger and less consistent changes. These results demonstrate that substantial improvements in upstream odometry accuracy do not necessarily produce proportional improvements in final SLAM localization and that the influence of sensor fusion varied across the evaluated SLAM algorithm and trajectory segments, providing practical guidance for selecting localization strategies in autonomous mobile robots. Full article

Stroke survivors with upper-limb impairments often have difficulty using conventional computer interfaces, which limits their ability to perform daily computer-related activities independently. This study developed a wearable multimodal assistive interface that enables computer interaction through a virtual cursor. A lightweight headband equipped with electrooculography (EOG), electroencephalography (EEG), and an inertial measurement unit (IMU) was used to acquire multimodal signals for interaction control. EOG signals were processed to detect voluntary blinks to generate clicks, head movements were mapped to cursor movements through IMU-based control, and frontal EEG signals were used to estimate attention as an auxiliary mechanism for command verification. A rapid user-specific calibration procedure was introduced to adapt blink-detection thresholds to individual EOG characteristics without requiring extensive training. Thirty stroke patients with upper-limb impairments participated in experiments involving common computer tasks, including news reading, video playback, and character spelling. The system achieved an average operation accuracy of 87.53 ± 4.92%, an average operation time of 3.49 ± 0.49 s, and an information transfer rate of 62.04 ± 15.93 bits/min in the spelling task. The mean NASA-TLX score was 32.1 ± 5.4, indicating a moderate subjective workload during system use. These results demonstrate the feasibility of the proposed wearable multimodal assistive interface for supporting computer interaction in stroke survivors with upper-limb impairments. Full article

Integrating wearable motion sensing with neuromodulation may improve understanding of how alterations in neural excitability influence running performance and biomechanics. This study investigated whether intermittent theta burst stimulation (iTBS) applied to the primary motor cortex (M1), dorsolateral prefrontal cortex (DLPFC), or both regions influences running performance and sensor-derived spatiotemporal parameters during a 3000 m time-trial run. Ten endurance-trained runners (7 males) completed four stimulation conditions (M1, DLPFC, M1 + DLPFC, and sham) in a randomized, sham-controlled, repeated-measures crossover design. Running performance and spatiotemporal gait parameters were continuously monitored using wearable inertial measurement units (IMUs), with analyses conducted across the initial, steady-state, and final acceleration phases of the run. The M1 + DLPFC condition resulted in the fastest mean completion time, averaging approximately three seconds faster than sham. However, these differences were not statistically significant. Sensor-derived biomechanical measures revealed significantly higher running speeds and alterations in stride time and step frequency during the initial phase following combined stimulation compared with the other conditions. Ratings of perceived exertion and spatiotemporal variability did not differ between stimulation conditions. These findings demonstrate the utility of wearable IMUs for detecting subtle phase-specific changes in running biomechanics and suggest that combined stimulation of motor and cognitive control regions may influence early-stage running performance, warranting further investigation in larger cohorts. As the complete sample consisted of only ten runners, these findings are preliminary and require confirmation in a larger sample size. Full article

Soccer requires rapid tactical decision-making, perceptual-cognitive processing, and coordinated physical execution, making it a relevant application domain for virtual reality (VR). VR systems integrate head-mounted displays, inertial measurement units, eye-tracking sensors, and electroencephalographic interfaces to support training, assessment, rehabilitation, and engagement. However, evidence remains fragmented across populations, study designs, sensing configurations, and research purposes, limiting conclusions about effectiveness and real-world application. Following PRISMA 2020, this systematic review synthesized 20 empirical studies published between January 2020 and 16 August 2026 involving school, academy, collegiate, and selected indirect adult soccer populations. Studies were classified by sensor modality, tracking configuration, evidence purpose, and outcome domain. Controlled intervention studies reported possible short-term improvements in selected sensorimotor, tactical, perceptual-cognitive, technical, and motivational outcomes. In contrast, cross-sectional and profiling studies showed that some VR tasks distinguished players by expertise, age, or competitive level; these findings support assessment or discriminative validity but do not demonstrate that VR training improves performance. Rehabilitation and injury-related evidence was limited and partly derived from adult or clinical populations, whereas engagement studies suggested potential benefits for motivation, attention, and participation. Six-degrees-of-freedom HMDs, 360° projection systems, eye tracking, and EEG generated different types of evidence, but no study directly compared hardware configurations within the same sample. The main contribution of this review is an integrated evidence-purpose and sensor-based synthesis that distinguishes training effectiveness from assessment validity across student-soccer applications. Overall, evidence remains promising but preliminary because of small and mixed populations, methodological heterogeneity, incomplete technical reporting, possible publication and language bias, short follow-up, and limited transfer to full-match performance. Standardized sensor reporting, controlled interventions, and longitudinal transfer assessments are required. Protocol registration: OSF. Full article

Positioning jumps are a primary cause of trajectory discontinuities in urban canyon environments, severely hindering the widespread adoption of autonomous vehicles. This paper proposes a CNN-GRU fusion-based method for correcting such positioning jumps. A complete 15-dimensional error-state extended Kalman filter (EKF) framework is established to analyze the jump generation mechanisms from three perspectives—pseudorange distortion, inertial drift, and filter gain divergence—thereby justifying the use of inertial measurement unit (IMU) time-series data for anomaly prediction. An end-to-end mapping model is further constructed, in which a one-dimensional convolutional neural network (CNN) extracts cross-channel spatial features from multi-axis inertial data, while a gated recurrent unit (GRU) captures long-term temporal error evolution. A hysteresis navigation quality factor and a piecewise Huber loss function are incorporated to enable hierarchical adaptive optimization. Experimental results demonstrate that the proposed method reduces the positioning root mean square error (RMSE) from 1.24 m to 0.70 m, achieves a jump suppression rate of 43.5%, and maintains a single-frame inference latency of 11.8 ms, meeting the real-time requirements for future autonomous driving localization. Full article

Terrain types significantly affect the dynamics and locomotion performance of hexapod robots during walking. Terrain classification is a key solution to modify gait patterns in different terrains and recognize hazardous conditions. Perceiving the terrain with proprioceptive sensing is a robust and reliable approach in extreme conditions. In this paper, an efficient terrain classification approach for a hexapod robot is proposed. The proposed method combines a deep classification framework including the long short-term memory (LSTM) network and an effective statistical feature extraction. Proprioceptive inertial measurement unit (IMU) data is only used as the sensing system for the robot–terrain interaction. In the feature extraction process, four meaningful characteristic features, namely, the mean, median, Lomb–Scargle periodogram power spectral density (LPSD), and Welch’s power spectral density (WPSD), are extracted from the body orientation data using a sliding-window method. These features are combined and fed into the network to perform the training and testing processes. In the experiments, the proposed method is evaluated with commonly used soft computing and deep learning models. The classification performance for the concrete, pebble, and waxed tile terrains reaches 100% with the proposed method. The overall accuracy, precision, sensitivity, specificity, F1-score, and Matthew correlation coefficient are recorded as 95.45%, 96.36%, 95.28%, 98.86%, 95.49%, and 94.61%, respectively. These results demonstrate that the proposed approach delivers reliable classification performance with a low-cost and easy-to-implement solution. Full article

Machine learning (ML) algorithms can be used to extract clinically meaningful information from movement data captured by inertial measurement units (IMUs), but many human activity recognition (HAR) pipelines are developed on large laboratory datasets that may not reflect small, heterogeneous, real-world samples. The purpose of this study is to systematically compare the accuracy of multiple ML models, feature sets (both simple and expanded), class balancing strategies, null and transition period handling techniques, and sensor configurations for recognizing a set of four everyday activities extracted from IMU time series data from an age-diverse population. Six ML classifiers were trained and tested: multilayer perceptron, random forest, k-nearest neighbors, logistic regressor, CatBoost, and gaussian naive bayes. These approaches were used in a pipeline with differing sampling techniques including the synthetic minority oversampling technique or random undersampling, and feature handling steps including principal component analysis or a Select-From-Model metatransformer. Additionally, two deep learning methods, DeepConvLSTM and ResGCNN, were trained and tested. Accuracy, precision, recall, and area under the receiver operating characteristic curve were compared to a dummy classifier as a benchmark approximation to chance performance. All pipelines performed better than the dummy classifier, with model accuracy ranging between 0.427 and 0.644. This study demonstrated the ability of several ML algorithms to properly recognize a set of functional activities using limited IMU data from both children and adults. Full article

Selecting a sensing architecture for knee osteoarthritis (OA) screening requires balancing biomechanical information, system complexity, and reproducibility. We audited a public Korean multimodal gait dataset and performed a leakage-resistant internal evaluation. The release contained 180 participants (90 normal, 90 knee OA) measured using a smart insole, instrumented gait mat, and inertial measurement units (IMUs); all 1080 JavaScript Object Notation (JSON) files were checked for structural, value, provenance, and duplication errors. The primary benchmark was a fixed class-balanced L2 logistic regression model using nine gait mat variables, evaluated with subject-level repeated stratified five-fold cross-validation and 10,000 outcome-stratified bootstrap resamples. The audit identified 14 source-path metadata errors and one opposing-label duplicate smart insole payload, but no parsing, schema, range, or cross-partition subject errors. The gait mat model achieved an area under the receiver operating characteristic curve (AUROC) of 0.924 (95% confidence interval [CI], 0.879–0.962), balanced accuracy 0.883 (0.833–0.928), sensitivity 0.856, specificity 0.911, and Brier score 0.102. Adding smart insole and/or IMU features did not improve AUROC. Provider-model reproduction was descriptive because the public Validation partition informed model selection. In this release, the compact gait mat feature set provided the most favorable observed balance of discrimination, interpretability, and sensing complexity; external prospective evaluation is required before clinical use. Full article

This study proposes a multi-source perceptual information fusion method to improve the accuracy and stability of dairy cow behavior monitoring. Existing machine vision approaches are often affected by lighting conditions, occlusion, and complex cowshed environments, while single wearable inertial measurement unit (IMU) devices may confuse similar behaviors such as eating, ruminating, standing, and lying. To address these limitations, a wireless collar was developed to synchronously collect nine-axis IMU data and ultra-wideband (UWB) ranging data in real time. Combined with manual behavioral observations, a dataset covering seven behaviors—eating, ruminating, standing, lying, drinking, sleeping, and lateral trunk contact—was constructed. By integrating neck-motion features extracted from the IMU data with spatial-distance features obtained from the UWB data, an IMU–UWB dual-branch fusion model was developed to automatically classify dairy cow behaviors. The results indicate that the proposed method can effectively reduce confusion among similar behaviors and improve the recognition of behaviors with limited samples. This approach enables more comprehensive assessment of dairy cows’ daily activities and health status, providing technical support for health monitoring, early disease warning, and intelligent dairy farm management. Full article

Pathological gait classification plays an important role in objective motor function assessment, early clinical screening, and rehabilitation evaluation. However, traditional clinical gait assessment methods are highly dependent on expert experience and may fail to detect subtle gait abnormalities. Moreover, existing inertial measurement unit (IMU)-based gait recognition methods often rely on single-sensor configurations or single-scale temporal models, limiting their ability to capture complex pathological gait patterns. In this study, a convolutional neural network–bidirectional long short-term memory–temporal convolutional network (CNN-BiLSTM-TCN) multi-branch feature fusion framework was proposed for pathological gait classification using a publicly available clinical multi-inertial measurement unit dataset containing 260 subjects. The proposed model employs three parallel branches to extract local instantaneous motion variations, continuous temporal dynamics, and relatively broader temporal dependencies within the 2 s input window, respectively, followed by feature-level fusion and end-to-end joint optimization. Experimental results show that the proposed model achieves a test accuracy of 0.9818 and an F1-score of 0.9700, outperforming conventional machine learning methods, single-branch models, voting-based fusion methods, and other temporal models, including Support Vector Machine (SVM), Temporal Convolutional Network (TCN), and Convolutional Neural Network-long short-term memory (CNN-LSTM). Five repeated experiments with stratified random splits demonstrate minimal performance variation, indicating good robustness and stability. The proposed framework provides a potential approach for pathological gait screening and quantitative rehabilitation assessment. Full article

Background/Objectives: Exercise medicine is gaining significant importance in adult oncology to improve physical activity and quality of life (QoL). However, few studies have investigated the effects of adapted physical activities in the pediatric population. The aim of this secondary analysis is to compare the movement quality of a hematological/oncological pediatric population before and after an individualized exercise program (IEP). Methods: Participants who met the inclusion criteria (aged 5–18 years, oncological/hematological diagnosis, consent) underwent an IEP delivered both in the hospital and via telemedicine at home. The subject’s movement quality was assessed before and after six months of the IEP using instrumented functional tests (i.e., 6 min walking test, Timed Up and Go, T25-FW, and turning test). To reduce the number of variables obtained, principal component analysis (PCA) was performed, and the resulting scores were then compared. Results: A total of 18 subjects (median age 12 years; eight females) were included in the analysis. Through the PCA, four dimensions were identified: Gait Efficiency, Gait Quality, Dynamic Balance, and Functional Abilities. The pre–post comparison showed significant improvements (p = 0.002) in Dynamic Balance and a trend (p = 0.05) in Gait Efficiency. Conclusions: The presented results indicate the crucial Principal Components (PCs) of movement in children treated for cancer. Moreover, in our setting, under the IEP we observed a significant improvement in Dynamic Balance. The results are consistent with those observed in previous studies. However, the limited number of subjects and the study design preclude definitive conclusions. Full article

To address the challenges of GNSS signal blockages and severe multipath effects in complex urban environments, this paper proposes a tightly coupled precise point positioning (PPP)/inertial navigation system (INS) integration method based on an adaptive robust Kalman filter (ARKF) for smartphones. The proposed method integrates a robust estimation module based on the IGG-III weight function and an adaptive factor derived from vehicle dynamic intensity and geometric precision indicators, to mitigate observation outliers and dynamic model errors. To evaluate the positioning performance of this algorithm, two typical vehicle experiments based on the GNSS and inertial measurement unit (IMU) chipsets of the Xiaomi Mi 8, as well as an external H30 IMU, were conducted. Experimental results show that in the urban expressway environment, the horizontal root mean square (RMS) error of the loosely coupled PPP/INS solution was reduced by 74.17% compared with the conventional PPP solution, while the maximum horizontal positioning error of the tightly coupled PPP/INS solution was reduced by 44.82% compared with the loosely coupled PPP/INS solution. In the complex urban road and tunnel environments, the proposed ARKF-based tightly coupled PPP/INS method achieved a 36.79% reduction in horizontal RMS error compared with the tightly coupled PPP/INS solution based on the standard extended Kalman filter (EKF) and demonstrated more robust positioning performance in the tunnel. Full article

In recent years, advances in exoskeleton technology have increased the demand for human motion classification in terms of both movement diversity and recognition accuracy, making the effective classification of more complex asymmetric movements increasingly important. This study integrated surface electromyography (sEMG) and inertial measurement unit (IMU) signals and employed mutual information (MI) and muscle symmetry features (MSF) to analyze the characteristic differences between symmetrical muscles in both legs during asymmetric movements, with the aim of improving the accuracy of asymmetric motion classification. sEMG and IMU signals were collected from six movements, including three asymmetric postures: asymmetrical stance, single-knee kneeled position, and crouching advance. The acquired signals were processed through energy envelope analysis, active segment extraction, empirical mode decomposition (EMD), feature extraction, MI extraction, and MSF extraction. The relevance based on weight feature selection (RWFS) combined with conditional mutual information (CMI) method was then applied to reduce feature dimensionality, prioritize features with significant fluctuations, and preserve key characteristics. Finally, the CNN-LSTM-Attention algorithm was used for classification. Experimental results showed that fusing sEMG and IMU signals achieved 96.30% accuracy in lower limb motion recognition. The proposed method improves asymmetric movement classification and may provide a potential basis for exoskeleton motion classification in special environments. Full article