Ground reaction force (GRF) data is often collected for the biomechanical analysis of running, due to the performance and injury risk insights that GRF analysis can provide. Traditional methods typically limit GRF collection to controlled lab environments, recent studies have looked to combine the ease of use of wearable sensors with the statistical power of machine learning to estimate continuous GRF data outside of these restrictions. Before such systems can be deployed with confidence outside of the lab they must be shown to be a valid and accurate tool for a wide range of users. The aim of this study was to evaluate how accurately a consumer-priced sensor system could estimate GRFs whilst a heterogeneous group of runners completed a treadmill protocol with three different personalised running speeds and three gradients. Fifty runners (25 female, 25 male) wearing pressure insoles made up of 16 resistive sensors and an inertial measurement unit ran at various speeds and gradients on an instrumented treadmill. A long short term memory (LSTM) neural network was trained to estimate both vertical ( G R F v ) and anteroposterior ( G R F a p ) force traces using leave one subject out validation. The average relative root mean squared error (rRMSE) was 3.2% and 3.1%, respectively. The mean ( G R F v ) rRMSE across the evaluated participants ranged from 0.8% to 8.8% and from 1.3% to 17.3% in the ( G R F a p ) estimation. The findings from this study suggest that current consumer-priced sensors could be used to accurately estimate two-dimensional GRFs for a wide range of runners at a variety of running intensities. The estimated kinetics could be used to provide runners with individualised feedback as well as form the basis of data collection for running injury risk factor studies on a much larger scale than is currently possible with lab based methods.

The utilization of inertial measurement units as wearable sensors is proliferating across various domains, such as health care, sports, and rehabilitation. This expansion has produced a market of devices tailored to accommodate very specific ranges of operational demands. Simultaneously, this growth is creating opportunities for the development of a new class of devices more oriented towards general-purpose use and capable of capturing both high-frequency signals for short-term, event-driven motion analysis and low-frequency signals for extended monitoring. For such a design, which combines flexibility and low cost, a rigorous evaluation of the device in terms of deviation, noise levels, and precision is essential. This evaluation is crucial for identifying potential improvements and refining the design accordingly, yet it is rarely addressed in the literature. This paper presents the development process of such a device. The results of the design process demonstrate acceptable performance in optimizing energy consumption and storage capacity while highlighting the most critical optimizations needed to advance the device towards the goal of a smart, general-purpose unit for human motion monitoring.

OBJECTIVE: This study aimed to assess the feasibility of early detection of fatigued gait patterns for older adults through the development of a smart portable device.
METHODS: The smart device incorporated seven force sensors and a single inertial measurement unit (IMU) to measure regional plantar forces and foot kinematics. Data were collected from 18 older adults walking briskly on a treadmill for 60 min. The optimal feature set for each recognition model was determined using forward sequential feature selection in a wrapper fashion through fivefold cross-validation. The recognition model was selected from four machine learning models through leave-one-subject-out cross-validation.
RESULTS: Five selected characteristics that best represented the state of fatigue included impulse at the medial and lateral arches (increased, p = 0.002 and p < 0.001), contact angle and rotation range of angle in the sagittal plane (increased, p < 0.001), and the variability of the resultant swing angular acceleration (decreased, p < 0.001). The detection accuracy based on the dual signal source of IMU and plantar force was 99%, higher than the 95% accuracy based on the single source. The intelligent portable device demonstrated excellent generalization (ranging from 93 to 100%), real-time performance (2.79 ms), and portability (32 g).
CONCLUSIONS: The proposed smart device can detect fatigue patterns with high precision and in real time.
CONCLUSIONS: The application of this device possesses the potential to reduce the injury risk for older adults related to fatigue during gait.

Human Activity Recognition (HAR), alongside Ambient Assisted Living (AAL), are integral components of smart homes, sports, surveillance, and investigation activities. To recognize daily activities, researchers are focusing on lightweight, cost-effective, wearable sensor-based technologies as traditional vision-based technologies lack elderly privacy, a fundamental right of every human. However, it is challenging to extract potential features from 1D multi-sensor data. Thus, this research focuses on extracting distinguishable patterns and deep features from spectral images by time-frequency-domain analysis of 1D multi-sensor data. Wearable sensor data, particularly accelerator and gyroscope data, act as input signals of different daily activities, and provide potential information using time-frequency analysis. This potential time series information is mapped into spectral images through a process called use of \'scalograms\', derived from the continuous wavelet transform. The deep activity features are extracted from the activity image using deep learning models such as CNN, MobileNetV3, ResNet, and GoogleNet and subsequently classified using a conventional classifier. To validate the proposed model, SisFall and PAMAP2 benchmark datasets are used. Based on the experimental results, this proposed model shows the optimal performance for activity recognition obtaining an accuracy of 98.4% for SisFall and 98.1% for PAMAP2, using Morlet as the mother wavelet with ResNet-101 and a softmax classifier, and outperforms state-of-the-art algorithms.

Hand-intensive work is strongly associated with work-related musculoskeletal disorders (WMSDs) of the hand/wrist and other upper body regions across diverse occupations, including office work, manufacturing, services, and healthcare. Addressing the prevalence of WMSDs requires reliable and practical exposure measurements. Traditional methods like electrogoniometry and optical motion capture, while reliable, are expensive and impractical for field use. In contrast, small inertial measurement units (IMUs) may provide a cost-effective, time-efficient, and user-friendly alternative for measuring hand/wrist posture during real work. This study compared six orientation algorithms for estimating wrist angles with an electrogoniometer, the current gold standard in field settings. Six participants performed five simulated hand-intensive work tasks (involving considerable wrist velocity and/or hand force) and one standardised hand movement. Three multiplicative Kalman filter algorithms with different smoothers and constraints showed the highest agreement with the goniometer. These algorithms exhibited median correlation coefficients of 0.75-0.78 for flexion/extension and 0.64 for radial/ulnar deviation across the six subjects and five tasks. They also ranked in the top three for the lowest mean absolute differences from the goniometer at the 10th, 50th, and 90th percentiles of wrist flexion/extension (9.3°, 2.9°, and 7.4°, respectively). Although the results of this study are not fully acceptable for practical field use, especially for some work tasks, they indicate that IMU-based wrist angle estimation may be useful in occupational risk assessments after further improvements.

The motivation behind this research is the lack of an underground mining shaft data set in the literature in the form of open access. For this reason, our data set can be used for many research purposes such as shaft inspection, 3D measurements, simultaneous localization and mapping, artificial intelligence, etc. The data collection method incorporates rotated Velodyne VLP-16, Velodyne Ultra Puck VLP-32c, Livox Tele-15, IMU Xsens MTi-30 and Faro Focus 3D. The ground truth data were acquired with a geodetic survey including 15 ground control points and 6 Faro Focus 3D terrestrial laser scanner stations of a total 273,784,932 of 3D measurement points. This data set provides an end-user case study of realistic applications in mobile mapping technology. The goal of this research was to fill the gap in the underground mining data set domain. The result is the first open-access data set for an underground mining shaft (shaft depth -300 m).

The inertial motion unit (IMU) is an effective tool for monitoring and assessing gait impairment in patients with lumbar disc herniation(LDH). However, the current clinical assessment methods for LDH gait focus on patients\' subjective scoring indicators and lack the assessment of kinematic ability; at the same time, individual differences in the motor function degradation of the healthy and affected lower limbs of LDH patients are also ignored. To solve this problem, we propose an LDH gait feature model based on multi-source adaptive Kalman data fusion of acceleration and angular velocity. The gait phase is segmented by using an adaptive Kalman data fusion algorithm to estimate the attitude angle, and obtaining gait events through a zero-velocity update technique and a peak detection algorithm. Two IMUs were used to analyze the gait characteristics of lumbar disc patients and healthy gait people, including 12 gait characteristics such as gait spatiotemporal parameters, kinematic parameters, gait variability and stability. Statistical methods were used to analyze the characteristic model and verify the biological differences between the healthy affected side of LDH and healthy subjects. Finally, feature engineering and machine learning technology were used to identify the gait pattern of inertial movement units in patients with lumbar intervertebral disc disease, and achieved a classification accuracy of 95.50%, providing an effective gait feature set and method for clinical evaluation of LDH.

Camptocormia, a severe flexion deformity of the spine, presents challenges in monitoring its progression outside laboratory settings. This study introduces a customized method utilizing four inertial measurement unit (IMU) sensors for continuous recording of the camptocormia angle (CA), incorporating both the consensual malleolus and perpendicular assessment methods. The setup is wearable and mobile and allows measurements outside the laboratory environment. The practicality for measuring CA across various activities is evaluated for both the malleolus and perpendicular method in a mimicked Parkinson disease posture. Multiple activities are performed by a healthy volunteer. Measurements are compared against a camera-based reference system. Results show an overall root mean squared error (RMSE) of 4.13° for the malleolus method and 2.71° for the perpendicular method. Furthermore, patient-specific calibration during the standing still with forward lean activity significantly reduced the RMSE to 2.45° and 1.68° respectively. This study presents a novel approach to continuous CA monitoring outside the laboratory setting. The proposed system is suitable as a tool for monitoring the progression of camptocormia and for the first time implements the malleolus method with IMU. It holds promise for effectively monitoring camptocormia at home.

Laboratory studies have limitations in screening for anterior cruciate ligament (ACL) injury risk due to their lack of ecological validity. Machine learning (ML) methods coupled with wearable sensors are state-of-art approaches for joint load estimation outside the laboratory in athletic tasks. The aim of this study was to investigate ML approaches in predicting knee joint loading during sport-specific agility tasks. We explored the possibility of predicting high and low knee abduction moments (KAMs) from kinematic data collected in a laboratory setting through wearable sensors and of predicting the actual KAM from kinematics. Xsens MVN Analyze and Vicon motion analysis, together with Bertec force plates, were used. Talented female football (soccer) players (n = 32, age 14.8 ± 1.0 y, height 167.9 ± 5.1 cm, mass 57.5 ± 8.0 kg) performed unanticipated sidestep cutting movements (number of trials analyzed = 1105). According to the findings of this technical note, classification models that aim to identify the players exhibiting high or low KAM are preferable to the ones that aim to predict the actual peak KAM magnitude. The possibility of classifying high versus low KAMs during agility with good approximation (AUC 0.81-0.85) represents a step towards testing in an ecologically valid environment.

Recently, inertial measurement units have been gaining popularity as a potential alternative to optical motion capture systems in the analysis of joint kinematics. In a previous study, the accuracy of knee joint angles calculated from inertial data and an extended Kalman filter and smoother algorithm was tested using ground truth data originating from a joint simulator guided by fluoroscopy-based signals. Although high levels of accuracy were achieved, the experimental setup leveraged multiple iterations of the same movement pattern and an absence of soft tissue artefacts. Here, the algorithm is tested against an optical marker-based system in a more challenging setting, with single iterations of a loaded squat cycle simulated on seven cadaveric specimens on a force-controlled knee rig. Prior to the optimisation of local coordinate systems using the REference FRame Alignment MEthod (REFRAME) to account for the effect of differences in local reference frame orientation, root-mean-square errors between the kinematic signals of the inertial and optical systems were as high as 3.8° ± 3.5° for flexion/extension, 20.4° ± 10.0° for abduction/adduction and 8.6° ± 5.7° for external/internal rotation. After REFRAME implementation, however, average root-mean-square errors decreased to 0.9° ± 0.4° and to 1.5° ± 0.7° for abduction/adduction and for external/internal rotation, respectively, with a slight increase to 4.2° ± 3.6° for flexion/extension. While these results demonstrate promising potential in the approach\'s ability to estimate knee joint angles during a single loaded squat cycle, they highlight the limiting effects that a reduced number of iterations and the lack of a reliable consistent reference pose inflicts on the sensor fusion algorithm\'s performance. They similarly stress the importance of adapting underlying assumptions and correctly tuning filter parameters to ensure satisfactory performance. More importantly, our findings emphasise the notable impact that properly aligning reference-frame orientations before comparing joint kinematics can have on results and the conclusions derived from them.