Search Results (2,914)

The spread of unmanned aerial vehicles in daily operations makes the early and reliable diagnosis of propeller faults necessary. However, the performance values reported for such systems are usually obtained with sample level splits, and it is not known which feature representation should be matched with which learner. In this study, a leakage-free feature–model matching framework is presented for propeller fault classification. Microphone and six-axis inertial measurement unit data have been collected on a test bench with 980 kV and 1400 kV motors for one healthy and eight faulty propeller conditions at 16 throttle levels, and 8490 windows of 1 s have been extracted from 1735 measurement files. Four scalar feature sets and three time-frequency representations have been matched with seven ensemble learners and three compact convolutional networks under a file atomic split, and the permutation ranking of the best model has been returned to the feature selection stage. The highest macro-F1 value of 0.8027 and an accuracy of 0.8816 have been obtained with the stacked ensemble trained on the 52 input subset ranked by explainability. It is seen that the time domain statistics and the accelerometer axes are dominant, that three inertial axes reach a macro-F1 of 0.7661, and that cepstral and envelope features stay below the Welch-based features at the sampling rate of 90.9 Hz. The cross-motor experiments have shown that the models depend strongly on the motor class, and the McNemar test has confirmed that the difference between the ensemble branch and the compact convolutional branch is not accidental. In this way, the framework can be used as an evaluation protocol for low-cost multisensor setups on low-level devices. Full article

Exercise recognition and movement quality assessment remain challenging in supervised exercise training, particularly under viewpoint changes and self-occlusion. Vision-based methods provide spatial posture information but are susceptible to keypoint loss, whereas inertial sensing is less affected by occlusion but provides limited information about global posture geometry. This study presents a dual-stream prototype that combines a nine-axis inertial measurement unit (IMU) with vision-based pose estimation. A 1DCNN-LSTM branch models inertial dynamics, a custom keypoint temporal branch models normalized pose sequences, and a confidence-gated rule adjusts their contributions according to visual keypoint reliability. Owing to the absence of a public synchronized multi-view IMU–vision exercise dataset with the required protocol, we constructed IMV-Exercise, comprising 10 participants, three exercises, and 900 repetition-level samples with side-, front-, and posterior-view recordings. The system achieved 96.0% exercise recognition accuracy under leave-one-subject-out cross-validation. In a separate viewpoint-specific evaluation, the fused output achieved 91.2% action-window accuracy under posterior viewing. Across 50 online trials, the reported recognition accuracy was 96.0%, the mean end-to-end latency was 195 ms, and the recorded maximum was below 210 ms. These results establish feasibility within the studied cohort and exercises; broader generalization and feedback effectiveness require larger, independently controlled evaluations. Full article

Future industrial human activity recognition (HAR) may require discrimination among many operational elements, including movements with partially overlapping kinematics. This controlled pilot study characterized recognition across 22 upper-body movement classes with varying structural similarity and examined classifier, signal scaling, and temporal window length. Sixteen adults performed the movements with an XSENS motion-capture system; eight upper-limb inertial measurement units provided 80 synchronous time-series channels. Thirteen participants were used for model development, and three whose observed execution patterns differed comparatively from the remainder were deliberately reserved as a challenge-oriented holdout. Support vector classifier (SVC), random forest (RF), Gaussian naive Bayes (NB), and long short-term memory (LSTM) models were evaluated with min–max or maximum-absolute scaling and 62-, 93-, or 124-frame windows. RF with maximum-absolute scaling and a 124-frame window achieved the best aggregate holdout performance (accuracy = 0.950; F1 = 0.939). Importantly, this performance was obtained on three entirely unseen participants who were deliberately reserved because their observed execution patterns and fluency differed from those of the model-development participants, providing a controlled, challenge-oriented test of transfer across inter-individual execution variability. Nevertheless, strong aggregate performance did not translate into uniform class-level reliability, and prominent errors remained concentrated in specific movement pairs. These findings provide empirical evidence for both the participant-independent transfer capability and the class-specific limitations of motion-only recognition, supporting its role as a methodological precursor to future AI-assisted work study and human–robot collaboration rather than as evidence of end-to-end industrial HAR. Full article

In static acrobatic gymnastics pyramids, maintaining stability in a multi-person system is critical, yet unconstrained floor baselines and base-to-top pairing mechanics remain poorly quantified. This study evaluated postural stability in shoulder-stand pyramids, examining the interplay of two specific top-athlete variations (lighter Pyramid T1 vs. heavier Pyramid T2) and base-athlete stances (parallel vs. tandem). Five elite base-athletes were monitored while supporting two top-athlete variations, a lighter (Pyramid T1) and a heavier (Pyramid T2) during a standard static shoulder-stand pyramid across parallel and tandem foot placement configurations (three trials in each Pyramid variation). Unconstrained free floor-standing baselines were also recorded for base-athletes and for tops prior to and following pyramid trials. The root mean square (RMS) of the resultant 3D free acceleration (Xsens MTw Awinda inertial sensors sampling at 100 Hz, Xsens MT Manager version 4.6.5 software) positioned at the bases’ and the tops’ shanks (right and left) was used to assess postural stability. A five-point median filter followed by a zero-phase, 2nd-order forward and reverse Butterworth low-pass filter (yielding an effective 4th-order response at 5 Hz and 10 Hz cutoffs) was applied to all signals (MATLAB R2025b). Stance-envelope dimensions were calculated from rectangular boundaries fitted to the base’s foot outlines. Non-parametric Spearman rank correlations ($\rho$) and parametric correlations ($r,R^2$) were used to test the interbase-consistency and base-to-top coupling. Two-way repeated measures ANOVAs (pyramid x stance configurations) were applied with primary analytical emphasis placed on descriptive effect sizes alongside exact $p$-values (SPSS v30, p < 0.05). The acrobatic tandem stance expanded the parallel stance-envelope area by $148.3\%$ and its width by $24.7\%$. When base-athletes transitioned from free standing to pyramids there was a substantial acceleration RMS increase (Pyramid T1: +24.3% to 83.6%, Pyramid T2: 47.2% to 166.2%). Supporting the heavier top-athlete (Pyramid T2) significantly increased the bases’ resultant acceleration RMS by $+37\%$ to $+48\%$ across both filter cutoff thresholds ($p<0.05$). Furthermore, top athletes exhibited differential behaviors: while Top 2 displayed lower acceleration RMS than Top 1, she experienced a greater acceleration surge when in Pyramid ($+238.4\% \mathrm{to} +266.2\%$). The bases’ and the tops’ acceleration profiles did not exhibit parallel responses, indicating decoupled rather than mirrored stability adjustments. Furthermore, when the acceleration RMS was normalized to stance-envelope dimensions, significant pyramid x stance interaction ($p<0.05$) was observed in the anteroposterior but not the mediolateral acceleration. Base-athlete stability varies significantly across top-athlete variations and stance geometries. Evaluating unconstrained floor baselines alongside spatial stance boundaries is essential for capturing structural loading dynamics in multi-person athletic tasks. Full article

This study used a cognitive screening instrument rather than a clinical diagnosis to define screening-defined mild cognitive impairment (screening-defined MCI) in community-dwelling older adults. Smartphone-based instrumented Timed Up and Go (iTUG) assessment using inertial measurement unit (IMU) sensors enables quantitative assessment of individual movement components. This cross-sectional study investigated the association between Turn 1 time and screening-defined MCI in 318 community-dwelling older adults aged ≥65 years. Cognitive function was assessed using the Japanese version of the Montreal Cognitive Assessment (MoCA-J); 177 participants with scores ≤ 25 were classified as having screening-defined MCI, and 141 with scores ≥ 26 as without screening-defined MCI. Turn 1 time was significantly longer in participants with screening-defined MCI than in those without screening-defined MCI (median [IQR], 1.40 [1.20–1.50] vs. 1.20 [1.10–1.30] s; p < 0.001). Receiver operating characteristic analysis yielded an AUC of 0.694 (95% CI, 0.637–0.751), and the preliminary, data-derived cutoff maximizing the Youden index was 1.35 s (sensitivity, 0.525; specificity, 0.780). After adjustment for age and sex, each 0.1 s increase in Turn 1 time was associated with higher odds of screening-defined MCI (OR, 1.322; 95% CI, 1.176–1.487; p < 0.001), while a Turn 1 time ≥ 1.35 s was associated with approximately threefold higher odds of screening-defined MCI (OR, 3.108; 95% CI, 1.832–5.271; p < 0.001). The association remained significant after additional adjustment for maximum walking speed and psychological distress (OR per 0.1 s increase, 1.286; 95% CI, 1.135–1.457; p < 0.001). Smartphone-based iTUG assessment of turning may provide complementary mobility-related information alongside established cognitive screening measures as part of a broader assessment of community-dwelling older adults. The 1.35 s cutoff should be considered a preliminary, data-derived threshold from an exploratory analysis, should not be used for clinical decision-making, and requires validation in an independent sample before any clinical application can be considered. Full article

This paper presents an observer-based strategy for controlling the horizontal trajectories of a hummingbird robot from on-board inertial measurements (MEMS). The centrifugal acceleration resulting from sharp turns is responsible for the dynamic coupling between the roll axis and the pitch and yaw axes. This coupling cannot be accounted for with independent control loops for the three axes; the problem can be solved with a modified state observer (MSO) introduced on the roll axis. Numerical simulations are presented to confirm the idea. The limited additional computational burden allows for real-time implementation. The MSO allows the robot to mimic the behavior of birds that lean towards the inside when turning. Under steady-state conditions (uniform longitudinal velocity and constant yaw rate), the pitch angle is such that the longitudinal component of the gravity vector balances the longitudinal drag force and the roll angle is such that the lateral component of the gravity vector balances the centrifugal acceleration. Full article

The ring laser gyroscope (RLG), a representative type of optical gyroscope, exhibits a lock-in region in which very small angular velocity inputs cannot be measured due to backscattering from the mirrors. Generally, this lock-in effect is mitigated by applying a high-amplitude sinusoidal vibration to the gyro body. The mechanical device used to induce this sinusoidal vibration is referred to as a dither. Dithers vary in configuration depending on the size of the gyro; while single-axis dithers are applied to gyros with relatively large optical paths, a cluster dither—which simultaneously applies sinusoidal vibrations to three-axis gyroscopes—is used for those with smaller optical paths. Unlike in the single-axis dither, the gyro body is mounted on the cluster dither at a specific angle. Furthermore, while the dither fixing hole in a single-axis dither is located at the center of the gyro body, it is positioned on the periphery in a cluster dither. Consequently, the center of rotation for a cluster dither is located at the center of the dither itself, rather than coinciding with the center of the gyro body. To increase the natural frequency of the cluster dither with such a configuration, this paper proposes a design employing a partially tapered non-uniform and heterogeneous cantilever beam, rather than the uniform and homogeneous cantilever beam used in conventional single-axis dither spokes, and presents a corresponding natural frequency analysis method. The accuracy of the proposed natural frequency analysis method is validated through modeling and simulation (M&S) and through experimental testing of fabricated prototypes. Full article

Background/Objectives: Change-of-direction (COD) movements represent a fundamental component of performance in multidirectional sports and constitute one of the primary mechanisms of knee injury. The biomechanical assessment of such movements has traditionally relied on optoelectronic systems and force platforms, tools characterized by high accuracy but limited applicability in field settings. Inertial measurement units (IMUs) represent a promising alternative; however, operational doubts and uncertainties frequently persist. Therefore, the purpose of this systematic review was to critically evaluate the concurrent validity and practical utility of IMU sensors for detecting the biomechanical characteristics of COD maneuvers in sport. Methods: The bibliographic search was conducted in March 2024 across the PubMed MEDLINE, Scopus, and Web of Science databases, using Boolean combinations of the following keywords: IMU, “inertial measurement unit”, CoD, “change of direction”, “cutting maneuvers”, sport, and soccer. Study selection and analysis were performed, and methodological quality was assessed using the QUADAS-2 tool. Results: In the original search (March 2024), ten studies were included, involving 208 participants; a formal update of the search (through August 2026), conducted with the same protocol, identified two additional candidate studies (14 and 30 participants), bringing the total to twelve studies and 252 participants; both supplementary studies underwent the same four-reviewer independent screening, full-text data extraction and QUADAS-2 appraisal applied to the original ten studies. The findings indicate that IMUs demonstrate good concurrent validity for kinematic variables in the sagittal plane, particularly at the hip and knee joints, with ICC values up to 0.99 and a mean RMSE below 2°. Performance decreases substantially in the frontal and transverse planes. Regarding ground reaction forces, IMUs provide acceptable estimates of mean values, but not of instantaneous forces. For temporal variables, IMUs proved comparable to timing gates in the assessment of explosive actions. Conclusions: Based on a limited and heterogeneous evidence base of twelve studies, IMUs appear to be a promising and accessible technology for specific field-based applications, particularly for the assessment of CODs at 0°, 45°, and 90° in the sagittal plane, for monitoring right-left asymmetries, and for counting explosive actions. Given the small number of included studies and their methodological heterogeneity, these findings should be interpreted with caution. IMUs cannot yet be recommended as a complete replacement for gold-standard systems in applications requiring high precision or detailed analysis of instantaneous forces. Full article

Reliable localization without GPS is a prerequisite for autonomous unmanned aerial vehicles (UAVs) operating inside warehouses, where a lightweight monocular camera paired with an inertial measurement unit (IMU) and onboard computer are the minimal sensing and processing an onboard platform can carry. This paper presents a tightly coupled monocular point-feature visual-inertial odometry (VIO) system for that setting, realized on a GTSAM fixed-lag factor graph with inverse-depth landmarks, on-manifold IMU preintegration, and an online loop-closure pose graph. The system is developed as the initial estimation stage of an autonomous stock-management UAV under development for indoor logistics warehouses. The decisive design element is the bootstrap: the metric, gravity-aligned initialization of a monocular estimator is well conditioned only under a translation-rich trajectory, a condition the near-zero-baseline pickup and takeoff transient that opens every indoor flight violates. Building on the visual-inertial alignment of VINS-Mono, we harden this step with a pre-bundle-adjust conditioning gate and a continuous-window initialization that refines the whole bootstrap window inside the smoother instead of freezing a single seed. On all eleven EuRoC MAV sequences, indoor flight tests recorded onboard a micro air vehicle in an industrial hall and two instrumented rooms, one fixed configuration per operating environment converges on every sequence, including three that otherwise diverge by tens to thousands of meters, and, driven by the same feature stream as locally run VINS-Mono and PL-VINS baselines, attains the better pure-odometry accuracy on nine of the eleven, with ATE RMSE of 0.12–0.37 m on the Machine Hall, a margin a paired signed-rank test confirms against VINS-Mono and leaves unconfirmed against PL-VINS at this sample size. We identify the stock fixed-lag marginalization as the principal consistency limitation and outline First-Estimates-Jacobian marginalization as the route to a more consistent estimator, establishing a characterized point-only baseline on one public benchmark as the starting point for subsequent on-platform work. Full article

Home-based physiotherapy is performed without supervision, which leads to incorrect execution and motivates systems that assess movement automatically from inertial measurement units (IMUs). Such systems assign each repetition to a category, yet a relevant share of repetitions fall near a class boundary, where even trained raters disagree. Classifiers trained with one-hot labels collapse these borderline repetitions onto a single class and discard this ambiguity. To address this, we build on label distribution learning, which represents each repetition as a distribution over classes instead of a single label. We introduce a way to construct such distributions without a large rater pool by perturbing the thresholds of a rule-based evaluation procedure to simulate rater disagreement. We train a network to reproduce these distributions with a Kullback–Leibler objective, which we call the ambiguity approach, and compare it against a one-hot cross-entropy baseline on four IMU exercise datasets. From the predicted distribution we then determine whether a repetition is ambiguous and which classes are relevant to it. The ambiguity approach matched or exceeded the baseline classification on all four datasets and detected ambiguity and the relevant classes more reliably. Representing the label distribution in the training target therefore adds information about ambiguity at no cost to classification. Full article

Self-Supervised Learning (SSL) has emerged as an effective paradigm for reducing the dependence of Human Activity Recognition (HAR) models on labeled data. To address the inadequate exploitation of IMU spatio-temporal correlations during pre-training and the limited generalization caused by simplistic fine-tuning strategies, a novel SSL framework for IMU-based HAR is proposed. The framework employs the Transformer and Depthwise Separable Convolution (DSC) to jointly capture global temporal dependencies and local spatial features, which are adaptively fused into discriminative spatio-temporal representations. These representations are subsequently enhanced through spatio-temporal feature extraction and multi-dimensional feature aggregation for downstream HAR. Furthermore, an IMU-based data acquisition platform was developed to construct the CQXY dataset. The proposed method was validated through comprehensive evaluations on four public datasets (UCI, Motion, HHAR, and Shoaib) and one self-collected dataset (CQXY). Experimental results show that, on the public datasets, the proposed method improves classification accuracy, F1-score, and Cohen’s kappa coefficient by an average of 13.11%, 14.24%, and 16.70%, respectively, compared with the baseline models. Similarly, on the self-collected dataset, the corresponding improvements reach 8.87%, 11.07%, and 10.81%. These results confirm the generalization of the proposed approach across datasets of different scales and domain. Full article

Human motion monitoring plays an important role in biomechanics and rehabilitation, where accurate measurement of limb movement is required. This study presents the design and experimental validation of a wearable system for ankle motion monitoring based on an inertial measurement unit (IMU). The proposed system integrates an IMU sensor, an Arduino Nano microcontroller, a microSD data logging module, and a battery-powered supply within a compact wearable device. Experimental tests were conducted to analyze three oснoвных movements of the ankle joint, including dorsiflexion–plantarflexion, inversion–eversion, and abduction–adduction. The IMU sensor was used to record angular velocity, linear acceleration, and orientation data in real time. The results demonstrate that the system is capable of capturing characteristic motion patterns and distinguishing between different types of ankle movements. The measured orientation angles (Roll, Pitch, and Yaw) correspond well to the expected kinematic behavior of the ankle joint. The obtained ranges are consistent with typical physiological values, confirming the reliability of the proposed approach. Overall, the developed wearable system provides an effective and practical solution for motion monitoring. It can be applied in rehabilitation and biomechanical analysis, while future work will focus on integrating additional sensors to enable a full multisensor platform. Full article

Reliable wearable motion tracking depends not only on nominal sensor precision but on whether calibration remains valid after re-donning, anatomical misalignment, magnetic disturbance, temperature change, and prolonged operation. This structured critical review treats calibration as a system-level engineering decision spanning intrinsic inertial measurement unit (IMU) correction, sensor-to-segment alignment, flexible-sensor calibration, drift management, and complementary or external references. A reproducible Scopus core search conducted in May 2026 identified 807 records. Three co-authors screened titles, abstracts, and keywords using explicit eligibility criteria, with full-text inspection when required; the final 110-source reference corpus combines eligible core records with supplementary and contextual sources identified through coverage checks in IEEE Xplore, Web of Science, ScienceDirect, and the MDPI database. Unlike prior reviews that mainly treat individual calibration layers or inertial-error mechanisms, this review jointly compares sensor-level, anatomical, multimodal, adaptive, and external-reference routes within a common deployment-oriented framework. Evidence is coded by failure mechanism, calibration route, sensing modality, application context, validation context, and deployment constraint. No universally superior route is supported: static and functional alignment differ in burden and anatomical sensitivity; magnetometer use depends on field reliability; vision and ultra-wideband (UWB) references can restore absolute observability but add infrastructure dependence; and direct IMU–flex calibration remains comparatively sparse. The resulting decision framework prioritizes reproducibility, robustness, calibration stability, and fitness for real-world deployment over isolated best-case accuracy. Full article

Attitude estimation has increasingly relied on MEMS inertial measurement units (IMUs) owing to the low cost and miniature size, but the inherent high random noise and error accumulation limit long-term measurement accuracy. This article proposes an integrated attitude estimation algorithm based on data fusion from a MIMU inertial array and magnetometer to address this challenge. First, a redundant inertial array is constructed using homogeneous gyroscopes, and a Kalman filter (KF) is designed to fuse output signals from multiple gyroscopes to estimate true angular rate. Second, an integrated error state Kalman filter (ESKF) for the MIMU/magnetometer system is developed. Using the attitude quaternion calculated by the strapdown inertial solution as the nominal state and combining it with measurements from the accelerometer and magnetometer as observations, the attitude error is estimated and corrected. Both simulations and field experiments were conducted to validate the effectiveness of the proposed algorithm. The experimental results show that the ESKF algorithm performs best in estimation accuracy and addresses the issue of error accumulation and fluctuation. In particular, the Root Mean Square Error (RMSE) of the ESKF algorithm was significantly reduced, with the roll angle reduced by 55.34%, the pitch angle by 30.25%, and the yaw angle by 55.71%. Full article

Reliable short-term position forecasting may provide anticipatory state information for collision-risk assessment, communication management, and prediction-assisted control in Internet of Things (IoT)-enabled unmanned aerial vehicles (UAVs); these downstream functions are not evaluated directly here. This study reformulates UAV position prediction as a flight-wise, multi-horizon, three-dimensional forecasting problem and tests whether position, velocity, gravity-resolved acceleration, and quaternion-orientation histories improve predictive accuracy while measuring model-level edge-inference cost rather than end-to-end system latency. The dataset contains 3100 AirSim flights with high-rate kinematic, inertial, attitude, pressure, and magnetic-field measurements under variable horizontal wind. The reported generalization is flight-disjoint within one AirSim domain; route/scenario disjointness and transfer to physical UAVs are not established. Signals are converted to a common navigation frame, gravity-resolved, low-pass filtered, resampled to 50 Hz, and partitioned by flight identifier before normalization and window construction. Each learned model receives 2 s of history and predicts the complete next 1 s trajectory, with errors evaluated at 0.1, 0.5, and 1.0 s. The sensor-enriched LSTM (LSTM-PVAQ) is compared under matched conditions with persistence, constant-velocity, constant-acceleration, extended Kalman filter, reduced-feature LSTM, GRU, temporal convolutional network (TCN), and compact Transformer baselines. LSTM-PVAQ achieved 3D RMSE values of 0.043, 0.168, and 0.371 m at 0.1, 0.5, and 1.0 s, respectively. At 1 s, its RMSE was 21.7% lower than LSTM-PV, 13.1% lower than GRU-PVAQ, 9.3% lower than TCN-PVAQ, and 16.8% lower than Transformer-PVAQ. Its one-second ADE and FDE were 0.216 and 0.339 m. On a Raspberry Pi 5 CPU using one FP32 thread and batch size one, median neural forward-pass latency was 0.88 ms, well below the 20 ms model-update interval. The results show that gravity-resolved inertial and orientation histories improve multi-horizon prediction, while TCN-PVAQ remains an attractive lower-latency alternative. Full article