Search

This paper presents a robust and efficient method for validating the accuracy of orientation sensors commonly used in practical applications, leveraging measurements from a commercial robotic manipulator as a high-precision reference. The key concept lies in determining the rotational transformations between the robot's base frame and the sensor's reference, as well as between the TCP (Tool Center Point) frame and the sensor frame, without requiring precise alignment. Key advantages of the proposed method include its independence from the exact measurement of rotations between the reference instrumentation and the sensor, systematic testing capabilities, and the ability to produce repeatable excitation patterns under controlled conditions. This approach enables automated, high-precision, and comparative evaluation of various orientation sensing devices in a reproducible manner. Moreover, it facilitates efficient calibration and analysis of sensor errors, such as drift, noise, and response delays under various motion conditions. The method's effectiveness is demonstrated through experimental validation of an Inertial Navigation System module and the SLAM-IMU fusion capabilities of the HTC VIVE VR headset, highlighting its versatility and reliability in addressing the challenges associated with orientation sensor validation. [ABSTRACT FROM AUTHOR]

The continuous, automated monitoring of sensor-based data for walking capacity and mobility has expanded gait analysis applications beyond controlled laboratory settings to real-world, everyday environments facilitated by the development of portable, cost-efficient wearable sensors. In particular, the integration of Inertial Measurement Units (IMUs) into smart shoes has proven effective for capturing detailed foot movements and spatiotemporal gait characteristics. While IMUs enable accurate foot trajectory estimation through the double integration of acceleration data, challenges such as drift errors necessitate robust correction techniques to ensure reliable performance. This review analyzes current literature on shoe-based systems utilizing IMUs to estimate spatiotemporal gait parameters and foot trajectory characteristics, including foot–ground clearance. We explore the challenges and advancements in achieving accurate 3D foot trajectory estimation using IMUs in smart shoes and the application of advanced techniques like zero-velocity updates and error correction methods. These developments present significant opportunities for achieving reliable and efficient real-time gait assessment in everyday environments. [ABSTRACT FROM AUTHOR]

Vertical jump height from a countermovement jump is a widespread metric to assess the lower limb functionality. Motion capture systems and force platforms are considered gold standards to estimate vertical jump height; however, their use in ecological settings is limited. This study aimed to evaluate the feasibility of low-sampling-rate inertial measurement units as an alternative to the gold standard systems. The validity of three computational methods for IMU-based data—numerical double integration, takeoff velocity, and flight time—was assessed using data from 18 healthy participants who performed five double-leg and ten single-leg countermovement jumps. The data were simultaneously collected from a motion capture system, two force platforms, and an IMU positioned at the L5 level. The comparisons revealed that the numerical double integration method exhibited the highest correlation (0.87) and the lowest bias (2.5 cm) compared to the gold standards and excellent reliability (0.88). Although the takeoff velocity and flight time methods demonstrated comparable performances for double-leg jumps, their accuracy in single-leg jumps was reduced. Overall, the low-sampling-rate IMU with the numerical double integration method seems to be a reliable and feasible alternative for field-based countermovement jump assessment, warranting future investigation across diverse populations and jump modalities. [ABSTRACT FROM AUTHOR]

The evaluation of gait biomechanics using portable inertial measurement units (IMUs) offers real-time feedback and has become a crucial tool for detecting gait disorders. However, many of these devices have not yet been fully validated. The aim of this study was to assess the concurrent validity and relative reliability of the RunScribe™ system for measuring spatiotemporal gait parameters during walking. A total of 460 participants (age: 36 ± 13 years; height: 173 ± 9 cm; body mass: 70 ± 13 kg) were asked to walk on a treadmill at 5 km·h−1. Spatiotemporal parameters of step frequency (SF), step length (SL), step time (ST), contact time (CT), swing time (SwT), stride time (StT), stride length (StL) and normalized stride length (StL%) were measured through RunScribe™ and OptoGait™ systems. Bland–Altman analysis indicated small systematic biases and random errors for all variables. Pearson correlation analysis showed strong correlations (0.70–0.94) between systems. The intraclass correlation coefficient supports these results, except for contact time (ICC = 0.64) and swing time (ICC = 0.34). The paired t-test showed small differences in SL, StL and StL% (≤0.25) and large in CT and SwT (1.2 and 2.2, respectively), with no differences for the rest of the variables. This study confirms the accuracy of the RunScribe™ system for assessing spatiotemporal parameters during walking, potentially reducing the barriers to continuous gait monitoring and early detection of gait issues. [ABSTRACT FROM AUTHOR]

Fatigue plays a critical role in sports science, significantly affecting recovery, training effectiveness, and overall athletic performance. Understanding and predicting fatigue is essential to optimize training, prevent overtraining, and minimize the risk of injuries. The aim of this study is to leverage Human Activity Recognition (HAR) through deep learning methods for dimensionality reduction. The use of Adversarial AutoEncoders (AAEs) is explored to assess and visualize fatigue in a two-dimensional latent space, focusing on both semi-supervised and conditional approaches. By transforming complex time-series data into this latent space, the objective is to evaluate motor changes associated with fatigue within the participants' motor control by analyzing shifts in the distribution of data points and providing a visual representation of these effects. It is hypothesized that increased fatigue will cause significant changes in point distribution, which will be analyzed using clustering techniques to identify fatigue-related patterns. The data were collected using a Wii Balance Board and three Inertial Measurement Units, which were placed on the hip and both forearms (distal part, close to the wrist) to capture dynamic and kinematic information. The participants followed a fatigue-inducing protocol that involved repeating sets of 10 repetitions of four different exercises (Squat, Right Lunge, Left Lunge, and Plank Jump) until exhaustion. Our findings indicate that the AAE models are effective in reducing data dimensionality, allowing for the visualization of fatigue's impact within a 2D latent space. The latent space representation provides insights into motor control variations, revealing patterns that can be used to monitor fatigue levels and optimize training or rehabilitation programs. [ABSTRACT FROM AUTHOR]

Locomotive syndrome (LS) refers to a condition where individuals face challenges in performing activities of daily living. Early detection of such deterioration is crucial to reduce the need for nursing care. The Geriatric Locomotive Function Scale (GLFS-25), a 25-question assessment, has been proposed for categorizing individuals into different stages of LS. However, its subjectivity has prompted interest in technology-based quantitative assessments. In this study, we utilized machine learning and an instrumented five-time sit-to-stand test (FTSTS) to assess LS stages. Younger and older participants were recruited, with older individuals classified into LS stages 0–2 based on their GLFS-25 scores. Equipped with a single inertial measurement unit at the pelvis level, participants performed the FTSTS. Using acceleration data, 144 features were extracted, and seven distinct machine learning models were developed using the features. Remarkably, the multilayer perceptron (MLP) model demonstrated superior performance. Following data augmentation and principal component analysis (PCA), the MLP+PCA model achieved an accuracy of 0.9, a precision of 0.92, a recall of 0.9, and an F1 score of 0.91. This underscores the efficacy of the approach for LS assessment. This study lays the foundation for the future development of a remote LS assessment system using commonplace devices like smartphones. [ABSTRACT FROM AUTHOR]

Unstable gait increases the risk of falls, posing a significant danger, particularly for frail older adults. The margin of stability (MoS) is a quantitative index that reflects the risk of falling due to postural imbalance in both the anterior-posterior and mediolateral directions during walking. Although MoS is a reliable indicator, its computation typically requires specialized equipment, such as motion capture systems, limiting its application to laboratory settings. To address this limitation, we propose a method for estimating MoS using time-series data from the translational and angular velocities of a single body segment—the pelvis. By applying principal motion analysis to process the multivariate time-series data, we successfully estimated MoS. Our results demonstrate that the estimated MoS in the mediolateral direction achieved an RMSE of 0.88 cm and a correlation coefficient of 0.72 with measured values, while in the anterior-posterior direction, the RMSE was 0.73 cm with a correlation coefficient of 0.87. These values for the mediolateral direction are better than those obtained in previous studies using only the three translational velocity components of the pelvis, whereas the values for the anterior direction are comparable to previous approaches. Our findings suggest that MoS can be reliably estimated using six-axial kinematic data of the pelvis, offering a more accessible method for assessing gait stability. [ABSTRACT FROM AUTHOR]

This study proposes a wearable gait assessment method using inertial measurement units (IMUs) to evaluate gait ability in daily environments. By focusing on the estimation of the margin of stability (MoS), a key kinematic stability parameter, a method using a convolutional neural network, was developed to estimate the MoS from IMU acceleration time-series data. The relationship between MoS and other stability indices, such as the Lyapunov exponent and the multi-site time-series (MSTS) index, using data from five IMU sensors placed on various body parts was also examined. To simulate diverse gait conditions, treadmill speed was varied, and a knee–ankle–foot orthosis was used to restrict left knee extension, inducing gait asymmetry. The model achieved over 90% accuracy in classifying MoS in both forward and lateral directions using three-axis acceleration data from the IMUs. However, the correlation between MoS and the Lyapunov exponent or MSTS index was weak, suggesting that these indices may capture different aspects of gait stability. [ABSTRACT FROM AUTHOR]

This study aimed to determine the characteristics of accelerations and angular velocities obtained by an inertial measurement unit (IMU) attached to a cane between older people with and without physical frailty. Community-dwelling older people walked at a comfortable speed using a cane with a built-in IMU. Physical frailty was assessed using exercise-related items extracted from the Kihon Check List. The efficacy of five machine learning models in distinguishing older people with physical frailty was investigated. This study included 48 older people, of which 24 were frail and 24 were not. Compared with the non-frail participants, the older people with physical frailty had a small root mean square value in the vertical and anteroposterior directions and angular velocity in the anteroposterior direction (p < 0.001, r = 0.36; p < 0.001, r = 0.29; p < 0.001, r = 0.30, respectively) and a large mean power frequency value in the vertical direction (p = 0.042, r = 0.18). The decision tree model could most effectively classify physical frailty, with an accuracy, F1 score, and area under the curve of 78.6%, 91.8%, and 0.81, respectively. The characteristics of IMU-attached cane usage by older adults with physical frailty can be utilized to effectively evaluate and determine physical frailty in their usual environments. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to introduce a method of measuring spatiotemporal gait patterns, tibial accelerations, and heart rate that are matched with high resolution geographical terrain features using publicly available data. These methods were demonstrated using data from 218 Marines, who completed loaded outdoor ruck hikes between 5–20 km over varying terrain. Each participant was instrumented with two inertial measurement units (IMUs) and a GPS watch. Custom code synchronized accelerometer and positional data without a priori sensor synchronization, calibrated orientation of the IMUs in the tibial reference frame, detected and separated only periods of walking or running, and computed acceleration and spatiotemporal outcomes. GPS positional data were georeferenced with geographic information system (GIS) maps to extract terrain features such as slope, altitude, and surface conditions. This paper reveals the ease at which similar data can be gathered among relatively large groups of people with minimal setup and automated data processing. The methods described here can be adapted to other populations and similar ground-based activities such as skiing or trail running. [ABSTRACT FROM AUTHOR]

Frozen shoulder (FS) is a common shoulder condition accompanied by shoulder pain and a loss of shoulder range of motion (ROM). The typical clinical assessment tools such as questionnaires and ROM measurement are susceptible to subjectivity and individual bias. To provide an objective evaluation for clinical assessment, this study proposes an inertial measurement unit (IMU)-based identification system to automatically identify shoulder tasks whether performed by healthy subjects or FS patients. Two groups of features (time-domain statistical features and kinematic features), seven machine learning (ML) techniques, and two deep learning (DL) models are applied in the proposed identification system. For the experiments, 24 FS patients and 20 healthy subjects were recruited to perform five daily shoulder tasks with two IMUs attached to the arm and the wrist. The results demonstrate that the proposed system using deep learning presented the best identification performance using all features. The convolutional neural network achieved the best identification accuracy of 88.26%, and the multilayer perceptron obtained the best F1 score of 89.23%. Further analysis revealed that the identification performance based on wrist features had a higher accuracy compared to that based on arm features. The system's performance using time-domain statistical features has better discriminability in terms of identifying FS compared to using kinematic features. We demonstrate that the implementation of the IMU-based identification system using ML is feasible for FS assessment in clinical practice. [ABSTRACT FROM AUTHOR]

Manual wheelchair propulsion represents a repetitive and constraining task, which leads mainly to the development of joint injury in spinal cord-injured people. One of the main reasons is the load sustained by the shoulder joint during the propulsion cycle. Moreover, the load at the shoulder joint is highly correlated with the force and moment acting at the handrim level. The main objective of this study is related to the estimation of handrim reactions forces and moments during wheelchair propulsion using only a single inertial measurement unit per hand. Two approaches are proposed here: Firstly, a method of identification of a non-linear transfer function based on the Hammerstein–Wiener (HW) modeling approach was used. The latter represents a typical multi-input single output in a system engineering modeling approach. Secondly, a specific variant of recurrent neural network called BiLSTM is proposed to predict the time-series data of force and moments at the handrim level. Eleven subjects participated in this study in a linear propulsion protocol, while the forces and moments were measured by a dynamic platform. The two input signals were the linear acceleration as well the angular velocity of the wrist joint. The horizontal, vertical and sagittal moments were estimated by the two approaches. The mean average error (MAE) shows a value of 6.10 N and 4.30 N for the horizontal force for BiLSTM and HW, respectively. The results for the vertical direction show a MAE of 5.91 N and 7.59 N for BiLSTM and HW, respectively. Finally, the MAE for the sagittal moment varies from 0.96 Nm (BiLSTM) to 1.09 Nm for the HW model. The approaches seem similar with respect to the MAE and can be considered accurate knowing that the order of magnitude of the uncertainties of the dynamic platform was reported to be 2.2 N for the horizontal and vertical forces and 2.24 Nm for the sagittal moments. However, it should be noted that HW necessitates the knowledge of the average force and patterns of each subject, whereas the BiLSTM method do not involve the average patterns, which shows its superiority for time-series data prediction. The results provided in this study show the possibility of measuring dynamic forces acting at the handrim level during wheelchair manual propulsion in ecological environments. [ABSTRACT FROM AUTHOR]

Existing methods to obtain position from inertial sensors typically use a combination of multiple sensors and orientation modeling; thus, obtaining position from a single inertial sensor is highly desirable given the decreased setup time and reduced complexity. The dead reckoning method is commonly chosen to obtain position from acceleration; however, when applied to upper limb tracking, the accuracy of position estimates are questionable, which limits feasibility. A new method of obtaining position estimates through the use of zero velocity updates is reported, using a commercial IMU, a push-to-make momentary switch, and a 3D printed object to house the sensors. The generated position estimates can subsequently be converted into sound through sonification to provide audio feedback on reaching movements for rehabilitation applications. An evaluation of the performance of the generated position estimates from a system labeled 'Soniccup' is presented through a comparison with the outputs from a Vicon Nexus system. The results indicate that for reaching movements below one second in duration, the Soniccup produces positional estimates with high similarity to the same movements captured through the Vicon system, corresponding to comparable audio output from the two systems. However, future work to improve the performance of longer-duration movements and reduce the system latency to produce real-time audio feedback is required to improve the acceptability of the system. [ABSTRACT FROM AUTHOR]

Utilizing reliable and accurate positioning and navigation systems is crucial for saving the lives of rescue personnel and accelerating rescue operations. However, Global Navigation Satellite Systems (GNSSs), such as GPS, may not provide stable signals in dense forests. Therefore, integrating multiple sensors like GPS and Inertial Measurement Units (IMUs) becomes essential to enhance the availability and accuracy of positioning systems. To accurately estimate rescuers' positions, this paper employs the Adaptive Unscented Kalman Filter (AUKF) algorithm with measurement noise variance matrix adaptation, integrating IMU and GPS data alongside barometric altitude measurements for precise three-dimensional positioning in complex environments. The AUKF enhances estimation robustness through the adaptive adjustment of the measurement noise variance matrix, particularly excelling when GPS signals are interrupted. This study conducted tests on two-dimensional and three-dimensional road scenarios in forest environments, confirming that the AUKF-algorithm-based integrated navigation system outperforms the traditional Extended Kalman Filter (EKF), Unscented Kalman Filter (UKF), and Adaptive Extended Kalman Filter (AEKF) in emergency rescue applications. The tests further evaluated the system's navigation performance on rugged roads and during GPS signal interruptions. The results demonstrate that the system achieves higher positioning accuracy on rugged forest roads, notably reducing errors by 18.32% in the north direction, 8.51% in the up direction, and 3.85% in the east direction compared to the EKF. Furthermore, the system exhibits good adaptability during GPS signal interruptions, ensuring continuous and accurate personnel positioning during rescue operations. [ABSTRACT FROM AUTHOR]

Inertial measurement units (IMU) are increasingly utilized to capture biomechanical measures such as joint kinematics outside traditional biomechanics laboratories. These wearable sensors have been proven to help clinicians and engineers monitor rehabilitation progress, improve prosthesis development, and record human performance in a variety of settings. The Valor IMU aims to offer a portable motion capture alternative to provide reliable and accurate joint kinematics when compared to industry gold standard optical motion capture cameras. However, IMUs can have disturbances in their measurements caused by magnetic fields, drift, and inappropriate calibration routines. Therefore, the purpose of this investigation is to validate the joint angles captured by the Valor IMU in comparison to an optical motion capture system across a variety of movements. Our findings showed mean absolute differences between Valor IMU and Vicon motion capture across all subjects' joint angles. The tasks ranged from 1.81 degrees to 17.46 degrees, the root mean squared errors ranged from 1.89 degrees to 16.62 degrees, and interclass correlation coefficient agreements ranged from 0.57 to 0.99. The results in the current paper further promote the usage of the IMU system outside traditional biomechanical laboratories. Future examinations of this IMU should include smaller, modular IMUs with non-slip Velcro bands and further validation regarding transverse plane joint kinematics such as joint internal/external rotations. [ABSTRACT FROM AUTHOR]

Accurately estimating single-axis rotational angle changes is crucial in many high-tech domains. However, traditional angle measurement techniques are often constrained by sensor limitations and environmental interferences, resulting in significant deficiencies in precision and stability. Moreover, current methodologies typically rely on fixed-axis rotation models, leading to substantial discrepancies between measured and actual angles due to axis misalignment. To address these issues, this paper proposes an innovative method for single-axis rotational angle estimation. It introduces a calibration technique for installation errors between inertial measurement units and the overall measurement system, effectively translating dynamic rotational inertial outputs to system enclosure outputs. Subsequently, the method employs triaxial accelerometers combined with zero-velocity detection technology to estimate the rotation axis position. Finally, it delves into analyzing the relationship between quaternion and axis–angle, aimed at reducing noise interference for precise rotational angle estimation. Based on this proposed methodology, a Low-Cost, a High Accuracy Measurement System (HAMS) integrating sensor fusion was designed and implemented. Experimental results demonstrate static measurement errors below ±0.15° and dynamic measurement errors below ±0.5° within a ±180° range. [ABSTRACT FROM AUTHOR]

Integrating running gait coordination assessment into athlete monitoring systems could provide unique insight into training tolerance and fatigue-related gait alterations. This study investigated the impact of an overload training intervention and recovery on running gait coordination assessed by field-based self-testing. Fifteen trained distance runners were recruited to perform 1-week of light training (baseline), 2 weeks of heavy training (high intensity, duration, and frequency) designed to overload participants, and a 10-day light taper to allow recovery and adaptation. Field-based running assessments using ankle accelerometry and online short recovery and stress scale (SRSS) surveys were completed daily. Running performance was assessed after each training phase using a maximal effort multi-stage running test-to-exhaustion (RTE). Gait coordination was assessed using detrended fluctuation analysis (DFA) of a stride interval time series. Two participants withdrew during baseline training due to changed personal circumstances. Four participants withdrew during heavy training due to injury. The remaining nine participants completed heavy training and were included in the final analysis. Heavy training reduced DFA values (standardised mean difference (SMD) = −1.44 ± 0.90; p = 0.004), recovery (SMD = −1.83 ± 0.82; p less than 0.001), performance (SMD = −0.36 ± 0.32; p = 0.03), and increased stress (SMD = 1.78 ± 0.94; p = 0.001) compared to baseline. DFA values (p = 0.73), recovery (p = 0.77), and stress (p = 0.73) returned to baseline levels after tapering while performance trended towards improvement from baseline (SMD = 0.28 ± 0.37; p = 0.13). Reduced DFA values were associated with reduced performance (r2 = 0.55) and recovery (r2 = 0.55) and increased stress (r2 = 0.62). Field-based testing of running gait coordination is a promising method of monitoring training tolerance in running athletes during overload training. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is a crucial task in various applications, including healthcare, fitness, and the military. Deep learning models have revolutionized HAR, however, their computational complexity, particularly those involving BiLSTMs, poses significant challenges for deployment on resource-constrained devices like smartphones. While BiLSTMs effectively capture long-term dependencies by processing inputs bidirectionally, their high parameter count and computational demands hinder practical applications in real-time HAR. This study investigates the approximation of the computationally intensive BiLSTM component in a HAR model by using a combination of alternative model components and data flipping augmentation. The proposed modifications to an existing hybrid model architecture replace the BiLSTM with standard and residual LSTM, along with convolutional networks, supplemented by data flipping augmentation to replicate the context awareness typically provided by BiLSTM networks. The results demonstrate that the residual LSTM (ResLSTM) model achieves superior performance while maintaining a lower computational complexity compared to the traditional BiLSTM model. Specifically, on the UCI-HAR dataset, the ResLSTM model attains an accuracy of 96.34% with 576,702 parameters, outperforming the BiLSTM model's accuracy of 95.22% with 849,534 parameters. On the WISDM dataset, the ResLSTM achieves an accuracy of 97.20% with 192,238 parameters, compared to the BiLSTM's 97.23% accuracy with 283,182 parameters, demonstrating a more efficient architecture with minimal performance trade-off. For the KU-HAR dataset, the ResLSTM model achieves an accuracy of 97.05% with 386,038 parameters, showing comparable performance to the BiLSTM model's 98.63% accuracy with 569,462 parameters, but with significantly fewer parameters. [ABSTRACT FROM AUTHOR]

The labor shortage and rising costs in the greenhouse industry have driven the development of automation, with the core of autonomous operations being positioning and navigation technology. However, precise positioning in complex greenhouse environments and narrow aisles poses challenges to localization technologies. This study proposes a multi-sensor fusion positioning and navigation robot based on ultra-wideband (UWB), an inertial measurement unit (IMU), odometry (ODOM), and a laser rangefinder (RF). The system introduces a confidence optimization algorithm based on weakening non-line-of-sight (NLOS) for UWB positioning, obtaining calibrated UWB positioning results, which are then used as a baseline to correct the positioning errors generated by the IMU and ODOM. The extended Kalman filter (EKF) algorithm is employed to fuse multi-sensor data. To validate the feasibility of the system, experiments were conducted in a Chinese solar greenhouse. The results show that the proposed NLOS confidence optimization algorithm significantly improves UWB positioning accuracy by 60.05%. At a speed of 0.1 m/s, the root mean square error (RMSE) for lateral deviation is 0.038 m and for course deviation is 4.030°. This study provides a new approach for greenhouse positioning and navigation technology, achieving precise positioning and navigation in complex commercial greenhouse environments and narrow aisles, thereby laying a foundation for the intelligent development of greenhouses. [ABSTRACT FROM AUTHOR]

Attitude determination based on a micro-electro-mechanical system inertial measurement unit (MEMS-IMU) has attracted extensive attention. The non-gravitational components of the MEMS-IMU have a significant effect on the accuracy of attitude estimation. To improve the attitude estimation of low-dynamic vehicles under uneven soil conditions or vibrations, a robust Kalman filter (RKF) was developed and tested in this paper, where the noise covariance was adaptively changed to compensate for the external acceleration of the vehicle. The state model for MEMS-IMU attitude estimation was initially constructed using a simplified direction cosine matrix. Subsequently, the variance of unmodeled external acceleration was estimated online based on filtering innovations of different window lengths, where the acceleration disturbance was addressed by tradeoffs in time-delay and prescribed computation cost. The effectiveness of the RKF was validated through experiments using a three-axis turntable, an automatic vehicle, and a tractor tillage test. The turntable experiment demonstrated that the angle result of the RKF was 0.051° in terms of root mean square error (RMSE), showing improvements of 65.5% and 29.2% over a conventional KF and MTi-300, respectively. The dynamic attitude estimation of the automatic vehicle showed that the RKF achieves smoother pitch angles than the KF when the vehicle passes over speed bumps at different speeds; the RMSE of pitch was reduced from 0.875° to 0.460° and presented a similar attitude trend to the MTi-300. The tractor tillage test indicated that the RMSE of plough pitch was improved from 0.493° with the KF to 0.259° with the RKF, an enhancement of approximately 47.5%, illustrating the superiority of the RKF in suppressing the external acceleration disturbances of IMU-based attitude estimation. [ABSTRACT FROM AUTHOR]

The aim of this study is to develop a practical software solution for real-time recognition of sign language words using two arms. This will facilitate communication between hearing-impaired individuals and those who can hear. We are aware of several sign language recognition systems developed using different technologies, including cameras, armbands, and gloves. However, the system we propose in this study stands out for its practicality, utilizing surface electromyography (muscle activity) and inertial measurement unit (motion dynamics) data from both arms. We address the drawbacks of other methods, such as high costs, low accuracy due to ambient light and obstacles, and complex hardware requirements, which have limited their practical application. Our software can run on different operating systems using digital signal processing and machine learning methods specific to this study. For the test, we created a dataset of 80 words based on their frequency of use in daily life and performed a thorough feature extraction process. We tested the recognition performance using various classifiers and parameters and compared the results. The random forest algorithm emerged as the most successful, achieving a remarkable 99.875% accuracy, while the naïve Bayes algorithm had the lowest success rate with 87.625% accuracy. The new system promises to significantly improve communication for people with hearing disabilities and ensures seamless integration into daily life without compromising user comfort or lifestyle quality. [ABSTRACT FROM AUTHOR]

Manual wheelchair users (MWUs) are prone to a sedentary life that can negatively affect their physical and cardiovascular health, making regular assessment important to identify appropriate interventions and lifestyle modifications. One mean of assessing MWUs' physical health is the 6 min push test (6MPT), where the user propels themselves as far as they can in six minutes. However, reliance on observer input introduces subjectivity, while limited quantitative data inhibit comprehensive assessment. Incorporating sensors into the 6MPT can address these limitations. Here, ten MWUs performed the 6MPT with additional sensors: two inertial measurement units (IMUs)—one on the wheelchair and one on the wrist together with a heart rate wristwatch. The conventional measurements of distance and laps were recorded by the observer, and the IMU data were used to calculate laps, distance, speed, and cadence. The results demonstrated that the IMU can provide the metrics of the traditional 6MPT with strong significant correlations between calculated laps and observer lap counts (r = 0.947, p < 0.001) and distances (r = 0.970, p < 0.001). Moreover, heart rate during the final minute was significantly correlated with calculated distance (r = 0.762, p = 0.017). Enhanced 6MPT assessment can provide objective, quantitative, and comprehensive data for clinicians to effectively inform interventions in rehabilitation. [ABSTRACT FROM AUTHOR]

Violin is one of the most complex musical instruments to learn. The learning process requires constant training and many hours of exercise and is primarily based on a student–teacher interaction where the latter guides the beginner through verbal instructions, visual demonstrations, and physical guidance. The teacher's instruction and practice allow the student to learn gradually how to perform the correct gesture autonomously. Unfortunately, these traditional teaching methods require the constant supervision of a teacher and the interpretation of non-real-time feedback provided after the performance. To address these limitations, this work presents a novel interface (Visual Interface for Bowing Evaluation—VIBE) to facilitate student's progression throughout the learning process, even in the absence of direct teacher intervention. The proposed interface allows two key parameters of bowing movements to be monitored, namely, the angle between the bow and the string (i.e., α angle) and the bow tilt (i.e., β angle), providing real-time visual feedback on how to correctly move the bow. Results collected on 24 beginners (12 exposed to visual feedback, 12 in a control group) showed a positive effect of the real-time visual feedback on the improvement of bow control. Moreover, the subjects exposed to visual feedback judged the latter as useful to correct their movement and clear in terms of the presentation of data. Although the task was rated as harder when performed with the additional feedback, the subjects did not perceive the presence of a violin teacher as essential to interpret the feedback. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) plays an important role in the automation of various tasks related to activity tracking in such areas as healthcare and eldercare (telerehabilitation, telemonitoring), security, ergonomics, entertainment (fitness, sports promotion, human–computer interaction, video games), and intelligent environments. This paper tackles the problem of real-time recognition and repetition counting of 12 types of exercises performed during athletic workouts. Our approach is based on the deep neural network model fed by the signal from a 9-axis motion sensor (IMU) placed on the chest. The model can be run on mobile platforms (iOS, Android). We discuss design requirements for the system and their impact on data collection protocols. We present architecture based on an encoder pretrained with contrastive learning. Compared to end-to-end training, the presented approach significantly improves the developed model's quality in terms of accuracy (F1 score, MAPE) and robustness (false-positive rate) during background activity. We make the AIDLAB-HAR dataset publicly available to encourage further research. [ABSTRACT FROM AUTHOR]

Investigating aircraft flight dynamics often requires dynamic wind tunnel testing. This paper proposes a non-contact, off-board instrumentation method using vision-based techniques. The method utilises a sequential process of Harris corner detection, Kanade–Lucas–Tomasi tracking, and quaternions to identify the Euler angles from a pair of cameras, one with a side view and the other with a top view. The method validation involves simulating a 3D CAD model for rotational motion with a single degree-of-freedom. The numerical analysis quantifies the results, while the proposed approach is analysed analytically. This approach results in a 45.41% enhancement in accuracy over an earlier direction cosine matrix method. Specifically, the quaternion-based method achieves root mean square errors of 0.0101 rad/s, 0.0361 rad/s, and 0.0036 rad/s for the dynamic measurements of roll rate, pitch rate, and yaw rate, respectively. Notably, the method exhibits a 98.08% accuracy for the pitch rate. These results highlight the performance of quaternion-based attitude estimation in dynamic wind tunnel testing. Furthermore, an extended Kalman filter is applied to integrate the generated on-board instrumentation data (inertial measurement unit, potentiometer gimbal) and the results of the proposed vision-based method. The extended Kalman filter state estimation achieves root mean square errors of 0.0090 rad/s, 0.0262 rad/s, and 0.0034 rad/s for the dynamic measurements of roll rate, pitch rate, and yaw rate, respectively. This method exhibits an improved accuracy of 98.61% for the estimation of pitch rate, indicating its higher efficiency over the standalone implementation of the direction cosine method for dynamic wind tunnel testing. [ABSTRACT FROM AUTHOR]

The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability. [ABSTRACT FROM AUTHOR]

This study focused on developing and evaluating a gyroscope-based step counter algorithm using inertial measurement unit (IMU) readings for precise athletic performance monitoring in soccer. The research aimed to provide reliable step detection and distance estimation tailored to soccer-specific movements, including various running speeds and directional changes. Real-time algorithms utilizing shank angular data from gyroscopes were created. Experiments were conducted on a specially designed soccer-specific testing circuit performed by 15 athletes, simulating a range of locomotion activities such as walking, jogging, and high-intensity actions. The algorithm outcome was compared with manually tagged data from a high-quality video camera-based system for validation, by assessing the agreement between the paired values using limits of agreement, concordance correlation coefficient, and further metrics. Results returned a step detection accuracy of 95.8% and a distance estimation Root Mean Square Error (RMSE) of 17.6 m over about 202 m of track. A sub-sample (N = 6) also wore two pairs of devices concurrently to evaluate inter-unit reliability. The performance analysis suggested that the algorithm was effective and reliable in tracking diverse soccer-specific movements. The proposed algorithm offered a robust and efficient solution for tracking step count and distance covered in soccer, particularly beneficial in indoor environments where global navigation satellite systems are not feasible. This advancement in sports technology widens the spectrum of tools for coaches and athletes in monitoring soccer performance. [ABSTRACT FROM AUTHOR]

This work presents a real-time gait phase estimator using thigh- and shank-mounted inertial measurement units (IMUs). A multi-rate convolutional neural network (CNN) was trained to estimate gait phase for a dataset of 16 participants walking on an instrumented treadmill with speeds varying between 0.1 to 1.9 m/s, and conditions such as asymmetric walking, stop–start, and sudden speed changes. One-subject-out cross-validation was used to assess the robustness of the estimator to the gait patterns of new individuals. The proposed model had a spatial root mean square error of 5.00 ± 1.65 % , and a temporal mean absolute error of 2.78 ± 0.97 % evaluated at the heel strike. A second cross-validation was performed to show that leaving out any of the walking conditions from the training dataset did not result in significant performance degradation. A 2-sample Kolmogorov–Smirnov test showed that there was no significant increase in spatial or temporal error when testing on the abnormal walking conditions left out of the training set. The results of the two cross-validations demonstrate that the proposed model generalizes well across new participants, various walking speeds, and gait patterns, showcasing its potential for use in investigating patient populations with pathological gaits and facilitating robot-assisted walking. [ABSTRACT FROM AUTHOR]

Wearable sensors could be beneficial for the continuous quantification of upper limb motor symptoms in people with Parkinson's disease (PD). This work evaluates the use of two inertial measurement units combined with supervised machine learning models to classify and predict a subset of MDS-UPDRS III subitems in PD. We attached the two compact wearable sensors on the dorsal part of each hand of 33 people with PD and 12 controls. Each participant performed six clinical movement tasks in parallel with an assessment of the MDS-UPDRS III. Random forest (RF) models were trained on the sensor data and motor scores. An overall accuracy of 94% was achieved in classifying the movement tasks. When employed for classifying the motor scores, the averaged area under the receiver operating characteristic values ranged from 68% to 92%. Motor scores were additionally predicted using an RF regression model. In a comparative analysis, trained support vector machine models outperformed the RF models for specific tasks. Furthermore, our results surpass the literature in certain cases. The methods developed in this work serve as a base for future studies, where home-based assessments of pharmacological effects on motor function could complement regular clinical assessments. [ABSTRACT FROM AUTHOR]

After an ACL injury, rehabilitation consists of multiple phases, and progress between these phases is guided by subjective visual assessments of activities such as running, hopping, jump landing, etc. Estimation of objective kinetic measures like knee joint moments and GRF during assessment can help physiotherapists gain insights on knee loading and tailor rehabilitation protocols. Conventional methods deployed to estimate kinetics require complex, expensive systems and are limited to laboratory settings. Alternatively, multiple algorithms have been proposed in the literature to estimate kinetics from kinematics measured using only IMUs. However, the knowledge about their accuracy and generalizability for patient populations is still limited. Therefore, this article aims to identify the available algorithms for the estimation of kinetic parameters using kinematics measured only from IMUs and to evaluate their applicability in ACL rehabilitation through a comprehensive systematic review. The papers identified through the search were categorized based on the modelling techniques and kinetic parameters of interest, and subsequently compared based on the accuracies achieved and applicability for ACL patients during rehabilitation. IMUs have exhibited potential in estimating kinetic parameters with good accuracy, particularly for sagittal movements in healthy cohorts. However, several shortcomings were identified and future directions for improvement have been proposed, including extension of proposed algorithms to accommodate multiplanar movements and validation of the proposed techniques in diverse patient populations and in particular the ACL population. [ABSTRACT FROM AUTHOR]

Inertial measurement units (IMUs) offer a portable and quantitative solution for clinical movement analysis. However, their application in non-specific low back pain (NSLBP) remains underexplored. This study compared the spine and pelvis kinematics obtained from IMUs between individuals with and without NSLBP and across clinical subgroups of NSLBP. A total of 81 participants with NSLBP with flexion (FP; n = 38) and extension (EP; n = 43) motor control impairment and 26 controls (No-NSLBP) completed 10 repetitions of spine movements (flexion, extension, lateral flexion). IMUs were placed on the sacrum, fourth and second lumbar vertebrae, and seventh cervical vertebra to measure inclination at the pelvis, lower (LLx) and upper (ULx) lumbar spine, and lower cervical spine (LCx), respectively. At each location, the range of movement (ROM) was quantified as the range of IMU orientation in the primary plane of movement. The ROM was compared between NSLBP and No-NSLBP using unpaired t-tests and across FP-NSLBP, EP-NSLBP, and No-NSLBP subgroups using one-way ANOVA. Individuals with NSLBP exhibited a smaller ROM at the ULx (p = 0.005), LLx (p = 0.003) and LCx (p = 0.01) during forward flexion, smaller ROM at the LLx during extension (p = 0.03), and a smaller ROM at the pelvis during lateral flexion (p = 0.003). Those in the EP-NSLBP group had smaller ROM than those in the No-NSLBP group at LLx during forward flexion (Bonferroni-corrected p = 0.005), extension (p = 0.013), and lateral flexion (p = 0.038), and a smaller ROM at the pelvis during lateral flexion (p = 0.005). Those in the FP-NSLBP subgroup had smaller ROM than those in the No-NSLBP group at the ULx during forward flexion (p = 0.024). IMUs detected variations in kinematics at the trunk, lumbar spine, and pelvis among individuals with and without NSLBP and across clinical NSLBP subgroups during flexion, extension, and lateral flexion. These findings consistently point to reduced ROM in NSLBP. The identified subgroup differences highlight the potential of IMU for assessing spinal and pelvic kinematics in these clinically verified subgroups of NSLBP. [ABSTRACT FROM AUTHOR]

Lower extremity exercises are considered a standard and necessary treatment for rehabilitation and a well-rounded fitness routine, which builds strength, flexibility, and balance. The efficacy of rehabilitation programs hinges on meticulous monitoring of both adherence to home exercise routines and the quality of performance. However, in a home environment, patients often tend to inaccurately report the number of exercises performed and overlook the correctness of their rehabilitation motions, lacking quantifiable and systematic standards, thus impeding the recovery process. To address these challenges, there is a crucial need for a lightweight, unbiased, cost-effective, and objective wearable motion capture (Mocap) system designed for monitoring and evaluating home-based rehabilitation/fitness programs. This paper focuses on the development of such a system to gather exercise data into usable metrics. Five radio frequency (RF) inertial measurement unit (IMU) devices (RF-IMUs) were developed and strategically placed on calves, thighs, and abdomens. A two-layer long short-term memory (LSTM) model was used for fitness activity recognition (FAR) with an average accuracy of 97.4%. An intelligent smartphone algorithm was developed to track motion, recognize activity, and calculate key exercise variables in real time for squat, high knees, and lunge exercises. Additionally, a 3D avatar on the smartphone App allows users to observe and track their progress in real time or by replaying their exercise motions. A dynamic time warping (DTW) algorithm was also integrated into the system for scoring the similarity in two motions. The system’s adaptability shows promise for applications in medical rehabilitation and sports. [ABSTRACT FROM AUTHOR]

Falls and frailty status are often associated with a decline in physical capacity and multifactorial assessment is highly recommended. Based on the functional and biomechanical parameters measured during clinical tests with an accelerometer integrated into smart eyeglasses, the purpose was to characterize a population of older adults through an unsupervised analysis into different physical performance groups. A total of 84 participants (25 men and 59 women) over the age of sixty-five (age: 74.17 ± 5.80 years; height: 165.70 ± 8.22 cm; body mass: 68.93 ± 13.55 kg) performed a 30 s Sit-to-Stand test, a six-minute walking test (6MWT), and a 3 m Timed Up and Go (TUG) test. The acceleration data measured from the eyeglasses were processed to obtain six parameters: the number of Sit-to-Stands, the maximal vertical acceleration values during Sit-to-Stand movements, step duration and length, and the duration of the TUG test. The total walking distance covered during the 6MWT was also retained. After supervised analyses comparison (i.e., ANOVAs), only one of the parameters (i.e., step length) differed between faller groups and no parameters differed between frail and pre-frail participants. In contrast, unsupervised analysis (i.e., clustering algorithm based on K-means) categorized the population into three distinct physical performance groups (i.e., low, intermediate, and high). All the measured parameters discriminated the low- and high-performance groups. Four of the measured parameters differentiated the three groups. In addition, the low-performance group had a higher proportion of frail participants. These results are promising for monitoring activities in older adults to prevent the decline of physical capacities. [ABSTRACT FROM AUTHOR]

Low back pain (LBP) is a common issue that negatively affects a person's quality of life and imposes substantial healthcare expenses. In this study, we introduce the (Back-pain Movement) BackMov test, using inertial motion capture (MoCap) to assess lumbar movement changes in LBP patients. The test includes flexion–extension, rotation, and lateralization movements focused on the lumbar spine. To validate its reproducibility, we conducted a test-retest involving 37 healthy volunteers, yielding results to build a minimal detectable change (MDC) graph map that would allow us to see if changes in certain variables of LBP patients are significant in relation to their recovery. Subsequently, we evaluated its applicability by having 30 LBP patients perform the movement's test before and after treatment (15 received deep oscillation therapy; 15 underwent conventional therapy) and compared the outcomes with a specialist's evaluations. The test-retest results demonstrated high reproducibility, especially in variables such as range of motion, flexion and extension ranges, as well as velocities of lumbar movements, which stand as the more important variables that are correlated with LBP disability, thus changes in them may be important for patient recovery. Among the 30 patients, the specialist's evaluations were confirmed using a low-back-specific Short Form (SF)-36 Physical Functioning scale, and agreement was observed, in which all patients improved their well-being after both treatments. The results from the specialist analysis coincided with changes exceeding MDC values in the expected variables. In conclusion, the BackMov test offers sensitive variables for tracking mobility recovery from LBP, enabling objective assessments of improvement. This test has the potential to enhance decision-making and personalized patient monitoring in LBP management. [ABSTRACT FROM AUTHOR]

Across five studies, we present the preliminary technical validation of an infant-wearable platform, LittleBeats™, that integrates electrocardiogram (ECG), inertial measurement unit (IMU), and audio sensors. Each sensor modality is validated against data from gold-standard equipment using established algorithms and laboratory tasks. Interbeat interval (IBI) data obtained from the LittleBeats™ ECG sensor indicate acceptable mean absolute percent error rates for both adults (Study 1, N = 16) and infants (Study 2, N = 5) across low- and high-challenge sessions and expected patterns of change in respiratory sinus arrhythmia (RSA). For automated activity recognition (upright vs. walk vs. glide vs. squat) using accelerometer data from the LittleBeats™ IMU (Study 3, N = 12 adults), performance was good to excellent, with smartphone (industry standard) data outperforming LittleBeats™ by less than 4 percentage points. Speech emotion recognition (Study 4, N = 8 adults) applied to LittleBeats™ versus smartphone audio data indicated a comparable performance, with no significant difference in error rates. On an automatic speech recognition task (Study 5, N = 12 adults), the best performing algorithm yielded relatively low word error rates, although LittleBeats™ (4.16%) versus smartphone (2.73%) error rates were somewhat higher. Together, these validation studies indicate that LittleBeats™ sensors yield a data quality that is largely comparable to those obtained from gold-standard devices and established protocols used in prior research. [ABSTRACT FROM AUTHOR]

Mobile fitness applications provide the opportunity to show users real-time feedback on their current fitness activity. For such applications, it is essential to accurately track the user's current fitness activity using available mobile sensors, such as inertial measurement units (IMUs). Convolutional neural networks (CNNs) have been shown to produce strong results in different time series classification tasks, including the recognition of daily living activities. However, fitness activities can present unique challenges to the human activity recognition task (HAR), including greater similarity between individual activities and fewer available data for model training. In this paper, we evaluate the applicability of CNNs to the fitness activity recognition task (FAR) using IMU data and determine the impact of input data size and sensor count on performance. For this purpose, we adapted three existing CNN architectures to the FAR task and designed a fourth CNN variant, which we call the scaling fully convolutional network (Scaling-FCN). We designed a preprocessing pipeline and recorded a running exercise data set with 20 participants, in which we evaluated the respective recognition performances of the four networks, comparing them with three traditional machine learning (ML) methods commonly used in HAR. Although CNN architectures achieve at least 94% test accuracy in all scenarios, two traditional ML architectures surpass them in the default scenario, with support vector machines (SVMs) achieving 99.00 ± 0.34% test accuracy. The removal of all sensors except one foot sensor reduced the performance of traditional ML architectures but improved the performance of CNN architectures on our data set, with our Scaling-FCN reaching the highest accuracy of 99.86 ± 0.11% on the test set. Our results suggest that CNNs are generally well suited for fitness activity recognition, and noticeable performance improvements can be achieved if sensors are dropped selectively, although traditional ML architectures can still compete with or even surpass CNNs when favorable input data are utilized. [ABSTRACT FROM AUTHOR]

Effective retraining of foot elevation and forward propulsion is a critical aspect of gait rehabilitation therapy after stroke, but valuable feedback to enhance these functions is often absent during home-based training. To enable feedback at home, this study assesses the validity of an inertial measurement unit (IMU) to measure the foot strike angle (FSA), and explores eight different kinematic parameters as potential indicators for forward propulsion. Twelve people with stroke performed walking trials while equipped with five IMUs and markers for optical motion analysis (the gold standard). The validity of the IMU-based FSA was assessed via Bland–Altman analysis, ICC, and the repeatability coefficient. Eight different kinematic parameters were compared to the forward propulsion via Pearson correlation. Analyses were performed on a stride-by-stride level and within-subject level. On a stride-by-stride level, the mean difference between the IMU-based FSA and OMCS-based FSA was 1.4 (95% confidence: −3.0; 5.9) degrees, with ICC = 0.97, and a repeatability coefficient of 5.3 degrees. The mean difference for the within-subject analysis was 1.5 (95% confidence: −1.0; 3.9) degrees, with a mean repeatability coefficient of 3.1 (SD: 2.0) degrees. Pearson's r value for all the studied parameters with forward propulsion were below 0.75 for the within-subject analysis, while on a stride-by-stride level the foot angle upon terminal contact and maximum foot angular velocity could be indicative for the peak forward propulsion. In conclusion, the FSA can accurately be assessed with an IMU on the foot in people with stroke during regular walking. However, no suitable kinematic indicator for forward propulsion was identified based on foot and shank movement that could be used for feedback in people with stroke. [ABSTRACT FROM AUTHOR]

In factories, human posture recognition facilitates human–machine collaboration, human risk management, and workflow improvement. Compared to optical sensors, inertial sensors have the advantages of portability and resistance to obstruction, making them suitable for factories. However, existing product-level inertial sensing solutions are generally expensive. This paper proposes a low-cost human motion capture system based on BMI 160, a type of six-axis inertial measurement unit (IMU). Based on WIFI communication, the collected data are processed to obtain the displacement of human joints' rotation angles around XYZ directions and the displacement in XYZ directions, then the human skeleton hierarchical relationship was combined to calculate the real-time human posture. Furthermore, the digital human model was been established on Unity3D to synchronously visualize and present human movements. We simulated assembly operations in a virtual reality environment for human posture data collection and posture recognition experiments. Six inertial sensors were placed on the chest, waist, knee joints, and ankle joints of both legs. There were 16,067 labeled samples obtained for posture recognition model training, and the accumulated displacement and the rotation angle of six joints in the three directions were used as input features. The bi-directional long short-term memory (BiLSTM) model was used to identify seven common operation postures: standing, slightly bending, deep bending, half-squatting, squatting, sitting, and supine, with an average accuracy of 98.24%. According to the experiment result, the proposed method could be used to develop a low-cost and effective solution to human posture recognition for factory operation. [ABSTRACT FROM AUTHOR]

In ubiquitous healthcare systems, energy expenditure estimation based on wearable sensors such as inertial measurement units (IMUs) is important for monitoring the intensity of physical activity. Although several studies have reported data-driven methods to estimate energy expenditure during activities of daily living using wearable sensor signals, few have evaluated the performance while walking at various speeds and inclines. In this study, we present a hybrid model comprising a convolutional neural network (CNN) and long short-term memory (LSTM) to estimate the steady-state energy expenditure under various walking conditions based solely on IMU data. To implement and evaluate the model, we performed level/inclined walking and level running experiments on a treadmill. With regard to the model inputs, the performance of the proposed model based on fixed-size sequential data was compared with that of a method based on stride-segmented data under different conditions in terms of the sensor location, input sequence format, and neural network model. Based on the experimental results, the following conclusions were drawn: (i) the CNN–LSTM model using a two-second sequence from the IMU attached to the lower body yielded optimal performance, and (ii) although the stride-segmented data-based method showed superior performance, the performance difference between the two methods was not significant; therefore, the proposed model based on fixed-size sequential data may be considered more practical as it does not require heel-strike detection. [ABSTRACT FROM AUTHOR]

Monitoring dynamic balance during gait is critical for fall prevention in the elderly. The current study aimed to develop recurrent neural network models for extracting balance variables from a single inertial measurement unit (IMU) placed on the sacrum during walking. Thirteen healthy young and thirteen healthy older adults wore the IMU during walking and the ground truth of the inclination angles (IA) of the center of pressure to the center of mass vector and their rates of changes (RCIA) were measured simultaneously. The IA, RCIA, and IMU data were used to train four models (uni-LSTM, bi-LSTM, uni-GRU, and bi-GRU), with 10% of the data reserved to evaluate the model errors in terms of the root-mean-squared errors (RMSEs) and percentage relative RMSEs (rRMSEs). Independent t-tests were used for between-group comparisons. The sensitivity, specificity, and Pearson's r for the effect sizes between the model-predicted data and experimental ground truth were also obtained. The bi-GRU with the weighted MSE model was found to have the highest prediction accuracy, computational efficiency, and the best ability in identifying statistical between-group differences when compared with the ground truth, which would be the best choice for the prolonged real-life monitoring of gait balance for fall risk management in the elderly. [ABSTRACT FROM AUTHOR]

Using inertial measurement units (IMUs) to estimate lower limb joint kinematics and kinetics can provide valuable information for disease diagnosis and rehabilitation assessment. To estimate gait parameters using IMUs, model-based filtering approaches have been proposed, such as the Kalman filter and complementary filter. However, these methods require special calibration and alignment of IMUs. The development of deep learning algorithms has facilitated the application of IMUs in biomechanics as it does not require particular calibration and alignment procedures of IMUs in use. To estimate hip/knee/ankle joint angles and moments in the sagittal plane, a subject-independent temporal convolutional neural network-bidirectional long short-term memory network (TCN-BiLSTM) model was proposed using three IMUs. A public benchmark dataset containing the most representative locomotive activities in daily life was used to train and evaluate the TCN-BiLSTM model. The mean Pearson correlation coefficient of joint angles and moments estimated by the proposed model reached 0.92 and 0.87, respectively. This indicates that the TCN-BiLSTM model can effectively estimate joint angles and moments in multiple scenarios, demonstrating its potential for application in clinical and daily life scenarios. [ABSTRACT FROM AUTHOR]

Measuring human joint dynamics is crucial for understanding how our bodies move and function, providing valuable insights into biomechanics and motor control. Cerebral palsy (CP) is a neurological disorder affecting motor control and posture, leading to diverse gait abnormalities, including altered knee angles. The accurate measurement and analysis of knee angles in individuals with CP are crucial for understanding their gait patterns, assessing treatment outcomes, and guiding interventions. This paper presents a novel multimodal approach that combines inertial measurement unit (IMU) sensors and electromyography (EMG) to measure knee angles in individuals with CP during gait and other daily activities. We discuss the performance of this integrated approach, highlighting the accuracy of IMU sensors in capturing knee joint movements when compared with an optical motion-tracking system and the complementary insights offered by EMG in assessing muscle activation patterns. Moreover, we delve into the technical aspects of the developed device. The presented results show that the angle measurement error falls within the reported values of the state-of-the-art IMU-based knee joint angle measurement devices while enabling a high-quality EMG recording over prolonged periods of time. While the device was designed and developed primarily for measuring knee activity in individuals with CP, its usability extends beyond this specific use-case scenario, making it suitable for applications that involve human joint evaluation. [ABSTRACT FROM AUTHOR]

We sought to determine the utility of Stryd, a commercially available inertial measurement unit, to quantify running intensity and aerobic fitness. Fifteen (eight male, seven female) runners (age = 30.2 [4.3] years; V · O2max = 54.5 [6.5] ml·kg−1·min−1) performed moderate- and heavy-intensity step transitions, an incremental exercise test, and constant-speed running trials to establish the maximal lactate steady state (MLSS). Stryd running power stability, sensitivity, and reliability were evaluated near the MLSS. Stryd running power was also compared to running speed, V · O2, and metabolic power measures to estimate running mechanical efficiency (EFF) and to determine the efficacy of using Stryd to delineate exercise intensities, quantify aerobic fitness, and estimate running economy (RE). Stryd running power was strongly associated with V · O2 (R2 = 0.84; p < 0.001) and running speed at the MLSS (R2 = 0.91; p < 0.001). Stryd running power measures were strongly correlated with RE at the MLSS when combined with metabolic data (R2 = 0.79; p < 0.001) but not in isolation from the metabolic data (R2 = 0.08; p = 0.313). Measures of running EFF near the MLSS were not different across intensities (~21%; p > 0.05). In conclusion, although Stryd could not quantify RE in isolation, it provided a stable, sensitive, and reliable metric that can estimate aerobic fitness, delineate exercise intensities, and approximate the metabolic requirements of running near the MLSS. [ABSTRACT FROM AUTHOR]

Background: With an increasing number of systems for quantifying lameness-related movement asymmetry, between-system comparisons under non-laboratory conditions are important for multi-centre or referral-level studies. This study compares an artificial intelligence video app to a validated inertial measurement unit (IMU) gait analysis system in a specific group of horses. Methods: Twenty-two reining Quarter horses were equipped with nine body-mounted IMUs while being videoed with a smartphone app. Both systems quantified head and pelvic movement symmetry during in-hand trot (hard/soft ground) and on the lunge (left/right rein, soft ground). Proportional limits of agreement (pLoA) were established. Results: Widths of pLoA were larger for head movement (29% to 50% in-hand; 22% to 38% on lunge) than for pelvic movement (13% to 24% in-hand; 14% to 24% on lunge). Conclusion: The between-system pLoAs exceed current "lameness thresholds" aimed at identifying the affected limb(s) in lame horses. They also exceed published limits of agreement for stride-matched data but are similar to repeatability values and "lameness thresholds" from "non-lame" horses. This is encouraging for multi-centre studies and referral-level veterinary practice. The narrower pLoA values for pelvic movement asymmetry are particularly encouraging, given the difficulty of grading hind limb lameness "by eye". [ABSTRACT FROM AUTHOR]

This paper introduces a Gait Phase Estimation Module (GPEM) and its real-time algorithm designed to estimate gait phases continuously and monotonically across a range of walking speeds and accelerations/decelerations. To address the challenges of real-world applications, we propose a speed-adaptive online gait phase estimation algorithm, which enables precise estimation of gait phases during both constant speed locomotion and dynamic speed changes. Experimental verification demonstrates that the proposed method offers smooth, continuous, and repetitive gait phase estimation when compared to conventional approaches such as the phase portrait method and time-based estimation. The proposed method achieved a 48 % reduction in gait phase deviation compared to time-based estimation and a 48.29 % reduction compared to the phase portrait method. The proposed algorithm is integrated within the GPEM, allowing for its versatile application in controlling gait assistive robots without incurring additional computational burden. The results of this study contribute to the development of robust and efficient gait phase estimation techniques for various robotic applications. [ABSTRACT FROM AUTHOR]

Although global positioning systems and inertial measurement unit systems are often used to quantify physical variables in training, both types of systems need to be compared, considering their frequent use in measuring physical loads. Thus, the purpose of our study was to test the reliability and validity of speed and distance run measurements at different intensities in indoor and outdoor conditions made by Polar Team Pro and Playermaker. Four participants (age = 30.0 ± 5.1 years, body mass = 76.3 ± 5.3 kg, height = 1.79 ± 0.09 m), each wearing three Polar Team Pro and two Playermaker sensors, performed 100 m runs with different prescribed intensities (i.e., criterion measure) varying from 8 to 24 km h−1, in a straight line and/or rectangle under indoor and outdoor conditions. Both systems underestimated total distance; Playermaker underestimated speed, the extent of which increased as speed increased, while Polar Team Pro overestimated mean speed at 8 km h−1 for the straight-line condition. No differences emerged in mean speed estimated by Polar Team Pro at any intensities other than 20 km h−1, which was underestimated by 2%. The reliability of the sensors was good, given a coefficient of variation (CV) of <2% for all conditions except when measuring indoor conditions with Polar Team Pro (CV ≈ 10%). Intraclass correlations (ICCs) for consistency within the sensors varied from 0.47 to 0.99, and significantly lower ICCs were documented at 8, 10, and 12 km h−1. Both systems underestimated distance measured in indoor and outdoor conditions, and distance validity in different intensities seemed to worsen as speeds increased. Although Polar Team Pro demonstrated poor validity and reliability in indoor conditions, both systems exhibited good reliability between their sensors in outdoor conditions, whereas the reliability within their sensors varied with different speeds. [ABSTRACT FROM AUTHOR]

Activity monitoring of living creatures based on the structural vibration of ambient objects is a promising method. For vibration measurement, multi-axial inertial measurement units (IMUs) offer a high sampling rate and a small size compared to geophones, but have higher intrinsic noise. This work proposes a sensing device that combines a single six-axis IMU with a beam structure to enable measurement of small vibrations. The beam structure is integrated into the PCB of the sensing device and connects the IMU to the ambient object. The beam is designed with finite element method (FEM) and optimized to maximize the vibration amplitude. Furthermore, the beam oscillation creates simultaneous translation and rotation of the IMU, which is measured with its accelerometers and gyroscopes. On this basis, a novel sensor fusion algorithm is presented that adaptively combines IMU data in the wavelet domain to reduce intrinsic sensor noise. In experimental evaluation, the proposed sensing device using a beam structure achieves a 6.2-times-higher vibration amplitude and an increase in signal energy of 480% when compared to a directly mounted IMU without a beam. The sensor fusion algorithm provides a noise reduction of 5.6% by fusing accelerometer and gyroscope data at 103 Hz. [ABSTRACT FROM AUTHOR]

This paper discusses the use of networks of Inertial Measurement Units (IMUs) for the reconstruction of trajectories from sensor data. Logistics is a natural application domain to verify the quality of the handling of goods. This is a mass application and the economics of logistics impose that the IMUs to be used must be low-cost and use basic computational devices. The approach in this paper converts a strategy from the literature, used in the multi-target following problem, to reach a consensus in a network of IMUs. This paper presents results on how to achieve the consensus in trajectory reconstruction, along with covariance intersection data fusion of the information obtained by all the nodes in the network. [ABSTRACT FROM AUTHOR]

The nine-axis inertial and measurement unit (IMU)-based three-dimensional (3D) orientation estimation is a fundamental part of inertial motion capture. Recently, owing to the successful utilization of deep learning in various applications, orientation estimation neural networks (NNs) trained on large datasets, including nine-axis IMU signals and reference orientation data, have been developed. During the training process, the limited amount of training data is a critical issue in the development of powerful networks. Data augmentation, which increases the amount of training data, is a key approach for addressing the data shortage problem and thus for improving the estimation performance. However, to the best of our knowledge, no studies have been conducted to analyze the effects of data augmentation techniques on estimation performance in orientation estimation networks using IMU sensors. This paper selects three data augmentation techniques for IMU-based orientation estimation NNs, i.e., augmentation by virtual rotation, bias addition, and noise addition (which are hereafter referred to as rotation, bias, and noise, respectively). Then, this paper analyzes the effects of these augmentation techniques on estimation accuracy in recurrent neural networks, for a total of seven combinations (i.e., rotation only, bias only, noise only, rotation and bias, rotation and noise, and rotation and bias and noise). The evaluation results show that, among a total of seven augmentation cases, four cases including 'rotation' (i.e., rotation only, rotation and bias, rotation and noise, and rotation and bias and noise) occupy the top four. Therefore, it may be concluded that the augmentation effect of rotation is overwhelming compared to those of bias and noise. By applying rotation augmentation, the performance of the NN can be significantly improved. The analysis of the effect of the data augmentation techniques presented in this paper may provide insights for developing robust IMU-based orientation estimation networks. [ABSTRACT FROM AUTHOR]

Introduction. Spatiotemporal gait parameters, e.g., gait stride length, are measurements that are classically derived from instrumented gait analysis. Today, different solutions are available for gait assessment outside the laboratory, specifically for spatiotemporal gait parameters. Such solutions are wearable devices that comprise an inertial measurement unit (IMU) sensor and a microcontroller (MCU). However, these existing wearable devices are resource-constrained. They contain a processing unit with limited processing and memory capabilities which limit the use of machine learning to estimate spatiotemporal gait parameters directly on the device. The solution for this limitation is embedded machine learning or tiny machine learning (tinyML). This study aims to create a machine-learning model for gait stride length estimation deployable on a microcontroller. Materials and Method. Starting from a dataset consisting of 4467 gait strides from 15 healthy people, measured by IMU sensor, and using state-of-the-art machine learning frameworks and machine learning operations (MLOps) tools, a multilayer 1D convolutional float32 and int8 model for gait stride length estimation was developed. Results. The developed float32 model demonstrated a mean accuracy and precision of 0.23 ± 4.3 cm, and the int8 model demonstrated a mean accuracy and precision of 0.07 ± 4.3 cm. The memory usage for the float32 model was 284.5 kB flash and 31.9 kB RAM. The int8 model memory usage was 91.6 kB flash and 13.6 kB RAM. Both models were able to be deployed on a Cortex-M4F 64 MHz microcontroller with 1 MB flash memory and 256 kB RAM. Conclusions. This study shows that estimating gait stride length directly on a microcontroller is feasible and demonstrates the potential of embedded machine learning, or tinyML, in designing wearable sensor devices for gait analysis. [ABSTRACT FROM AUTHOR]