Accurate Impact Loading Rate Estimation During Running via a Subject-Independent Convolutional Neural Network Model and Optimal IMU Placement

Enhancing accuracy and convenience of golf swing tracking with a wrist-worn single inertial sensor

In this study, we address two technical challenges to enhance golf swing trajectory accuracy using a wrist-worn inertial sensor: orientation estimation and drift error mitigation. We extrapolated consistent sensor orientation from specific address-phase signal segments and trained the estimation with a convolutional neural network. We then mitigated drift error by applying a constraint on wrist speed at the address, backswing top, and finish, and ensuring that the wrist's finish displacement aligns with a virtual circle on the 3D swing plane. To verify the proposed methods, we gathered data from twenty male right-handed golfers, including professionals and amateurs, using a driver and a 7-iron. The orientation estimation error was about 60% of the baseline, comparable to studies requiring additional sensor information or calibration poses. The drift error was halved and the single-inertial-sensor tracking performance across all swing phases was about 17 cm, on par with multimodal approaches. This study introduces a novel signal processing method for tracking rapid, wide-ranging motions, such as a golf swing, while maintaining user convenience. Our results could impact the burgeoning field of daily motion monitoring for health care, especially with the increasing prevalence of wearable devices like smartwatches.

Rethinking running biomechanics: a critical review of ground reaction forces, tibial bone loading, and the role of wearable sensors

This study presents a comprehensive review of the correlation between tibial acceleration (TA), ground reaction forces (GRF), and tibial bone loading, emphasizing the critical role of wearable sensor technology in accurately measuring these biomechanical forces in the context of running. This systematic review and meta-analysis searched various electronic databases (PubMed, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect) to identify relevant studies. It critically evaluates existing research on GRF and tibial acceleration (TA) as indicators of running-related injuries, revealing mixed findings. Intriguingly, recent empirical data indicate only a marginal link between GRF, TA, and tibial bone stress, thus challenging the conventional understanding in this field. The study also highlights the limitations of current biomechanical models and methodologies, proposing a paradigm shift towards more holistic and integrated approaches. The study underscores wearable sensors' potential, enhanced by machine learning, in transforming the monitoring, prevention, and rehabilitation of running-related injuries.

Estimation of electrical muscle activity during gait using inertial measurement units with convolution attention neural network and small-scale dataset

In general, muscle activity can be directly measured using Electromyography (EMG) or calculated with musculoskeletal models. However, both methods are not suitable for non-technical users and unstructured environments. It is desired to establish more portable and easy-to-use muscle activity estimation methods. Deep learning (DL) models combined with inertial measurement units (IMUs) have shown great potential to estimate muscle activity. However, it frequently occurs in clinical scenarios that a very small amount of data is available and leads to limited performance of the DL models, while the augmentation techniques to efficiently expand a small sample size for DL model training are rarely used. The primary aim of the present study was to develop a novel DL model to estimate the EMG envelope during gait using IMUs with high accuracy. A secondary aim was to develop a novel model-based data augmentation method to improve the performance of the estimation model with small-scale dataset. Therefore, in the present study, a time convolutional network-based generative adversarial network, namely MuscleGAN, was proposed for data augmentation. Moreover, a subject-independent regression DL model was developed to estimate EMG envelope. Results suggested that the proposed two-stage method has better generalization and estimation performance than the commonly used existing methods. Pearson correlation coefficient and normalized root-mean-square errors derived from the proposed method reached up to 0.72 and 0.13, respectively. It was indicated that the MuscleGAN indeed improved the estimation accuracy of lower limb EMG envelope from 70% to 72%. Thus, even using only two IMUs and a very small-scale dataset, the proposed model is still capable of accurately estimating lower limb EMG envelope, demonstrating considerable potential for its application in clinical and daily life scenarios.

Integrating an LSTM framework for predicting ankle joint biomechanics during gait using inertial sensors

The ankle joint plays a crucial role in gait, facilitating the articulation of the lower limb, maintaining foot-ground contact, balancing the body, and transmitting the center of gravity. This study aimed to implement long short-term memory (LSTM) networks for predicting ankle joint angles, torques, and contact forces using inertial measurement unit (IMU) sensors. Twenty-five healthy participants were recruited. Two IMU sensors were attached to the foot dorsum and the vertical axis of the distal anteromedial tibia in the right lower limb to record acceleration and angular velocity during running. We proposed a LSTM-MLP (multilayer perceptron) model for training time-series data from IMU sensors and predicting ankle joint biomechanics. The model underwent validation and testing using a custom nested k-fold cross-validation process. The average values of the coefficient of determination (R2), mean absolute error (MAE), and mean squared error (MSE) for ankle dorsiflexion joint and moment, subtalar inversion joint and moment, and ankle joint contact forces were 0.89 ± 0.04, 0.75 ± 1.04, and 2.96 ± 4.96 for walking, and 0.87 ± 0.07, 0.88 ± 1.26, and 4.1 ± 7.17 for running, respectively. This study demonstrates that IMU sensors, combined with LSTM neural networks, are invaluable tools for evaluating ankle joint biomechanics in lower limb pathological diagnosis and rehabilitation, offering a cost-effective and versatile alternative to traditional experimental settings.

Validity and reliability of the DANU sports system for walking and running gait assessment

Objective. Gait assessments have traditionally been analysed in laboratory settings, but this may not reflect natural gait. Wearable technology may offer an alternative due to its versatility. The purpose of the study was to establish the validity and reliability of temporal gait outcomes calculated by the DANU sports system, against a 3D motion capture reference system.Approach. Forty-one healthy adults (26 M, 15 F, age 36.4 ± 11.8 years) completed a series of overground walking and jogging trials and 60 s treadmill walking and running trials at various speeds (8-14 km hr-1), participants returned for a second testing session to repeat the same testing.Main results. For validity, 1406 steps and 613 trials during overground and across all treadmill trials were analysed respectively. Temporal outcomes generated by the DANU sports system included ground contact time, swing time and stride time all demonstrated excellent agreement compared to the laboratory reference (intraclass correlation coefficient (ICC) > 0.900), aside from ground contact time during overground jogging which had good agreement (ICC = 0.778). For reliability, 666 overground and 511 treadmill trials across all speeds were examined. Test re-test agreement was excellent for all outcomes across treadmill trials (ICC > 0.900), except for swing time during treadmill walking which had good agreement (ICC = 0.886). Overground trials demonstrated moderate to good test re-test agreement (ICC = 0.672-0.750), which may be due to inherent variability of self-selected (rather than treadmill set) pacing between sessions.Significance. Overall, this study showed that temporal gait outcomes from the DANU Sports System had good to excellent validity and moderate to excellent reliability in healthy adults compared to an established laboratory reference.

Indoor running temporal variability for different running speeds, treadmill inclinations, and three different estimation strategies

Inertial measurement units (IMU) constitute a light and cost-effective alternative to gold-standard measurement systems in the assessment of running temporal variables. IMU data collected on 20 runners running at different speeds (80, 90, 100, 110 and 120% of preferred running speed) and treadmill inclination (±2, ±5, and ±8%) were used here to predict the following temporal variables: stride frequency, duty factor, and two indices of running variability such as the detrended fluctuation analysis alpha (DFA-α) and the Higuchi's D (HG-D). Three different estimation methodologies were compared: 1) a gold-standard optoelectronic device (which provided the reference values), 2) IMU placed on the runner's feet, 3) a single IMU on the runner's thorax used in conjunction with a machine learning algorithm with a short 2-second or a long 120-second window as input. A two-way ANOVA was used to test the presence of significant (p<0.05) differences due to the running condition or to the estimation methodology. The findings of this study suggest that using both IMU configurations for estimating stride frequency can be effective and comparable to the gold-standard. Additionally, the results indicate that the use of a single IMU on the thorax with a machine learning algorithm can lead to more accurate estimates of duty factor than the strategy of the IMU on the feet. However, caution should be exercised when using these techniques to measure running variability indices. Estimating DFA-α from a short 2-second time window was possible only in level running but not in downhill running and it could not accurately estimate HG-D across all running conditions. By taking a long 120-second window a machine learning algorithm could improve the accuracy in the estimation of DFA-α in all running conditions. By taking these factors into account, researchers and practitioners can make informed decisions about the use of IMU technology in measuring running biomechanics.

Tracking Bilateral Lower Limb Kinematics of Distance Runners on Treadmill Using a Single Inertial Measurement Unit

Distance running related injuries are common, and many ailments have been associated with faulty posture. Conventional measurement of running kinematics requires sophisticated motion capture system in laboratory. In this study, we developed a wearable solution to accurately predict lower limb running kinematics using a single inertial measurement unit placed on the left lower leg. The running data collected from participants was used to train a model using long short-term memory (LSTM) neural networks with an inter-subject approach that predicted lower limb kinematics with an average accuracy of 80.2%, 85.8%, and 69.4% for sagittal hip, knee and ankle joint angles respectively for the ipsilateral limb. A comparable accuracy range was observed for the contralateral limb. The average RMSE (root mean squared error) of sagittal hip, knee and ankle were 8.76°, 13.13°, and 9.67° respectively for the ipsilateral limb. Analysis of contralateral limb kinematics was performed. The model established in this study can be used as a monitoring device to track essential running kinematics in natural running environments. Besides, the wearable solution can be an integral part of a real-time gait retraining biofeedback system for injury prevention and rehabilitation.

Foot Pronation Prediction with Inertial Sensors during Running: A Preliminary Application of Data-Driven Approaches

Abnormal foot postures may affect foot movement and joint loading during locomotion. Investigating foot posture alternation during running could contribute to injury prevention and foot mechanism study. This study aimed to develop feature-based and deep learning algorithms to predict foot pronation during prolonged running. Thirty-two recreational runners have been recruited for this study. Nine-axial inertial sensors were attached to the right dorsum of the foot and the vertical axis of the distal anteromedial tibia. This study employed feature-based machine learning algorithms, including support vector machine (SVM), extreme gradient boosting (XGBoost), random forest, and deep learning, i.e., one-dimensional convolutional neural networks (CNN1D), to predict foot pronation. A custom nested k-fold cross-validation was designed for hyper-parameter tuning and validating the model's performance. The XGBoot classifier achieved the best accuracy using acceleration and angular velocity data from the foot dorsum as input. Accuracy and the area under curve (AUC) were 74.7 ± 5.2% and 0.82 ± 0.07 for the subject-independent model and 98 ± 0.4% and 0.99 ± 0 for the record-wise method. The test accuracy of the CNN1D model with sensor data at the foot dorsum was 74 ± 3.8% for the subject-wise approach with an AUC of 0.8 ± 0.05. This study found that these algorithms, specifically for the CNN1D and XGBoost model with inertial sensor data collected from the foot dorsum, could be implemented into wearable devices, such as a smartwatch, for monitoring a runner's foot pronation during long-distance running. It has the potential for running shoe matching and reducing or preventing foot posture-induced injuries.

Predicting vertical ground reaction force in rearfoot running: A wavelet neural network model and factor loading

This study proposed a simple method for selecting input variables by factor loading and inputting these variables into a wavelet neural network (WNN) model to predict vertical ground reaction force (vGRF). The kinematic data and vGRF of 9 rearfoot strikers at 12, 14, and 16 km/h were collected using a motion capture system and an instrumented treadmill. The input variables were screened by factor loading and utilized to predict vGRF with the WNN. Nine kinematic variables were selected, corresponding to nine principal components, mainly focusing on the knee and ankle joints. The prediction results of vGRF were effective and accurate at different speeds, namely, the coefficient of multiple correlation (CMC) > 0.98 (0.984-0.988), the normalized root means square error (NRMSE) < 15% (9.34-11.51%). The NRMSEs of impact force (8.18-10.01%), active force (4.92-7.42%), and peak time (7.16-12.52%) were less than 15%. There was a small number (peak, 4.12-6.18%; time, 4.71-6.76%) exceeding the 95% confidence interval (CI) using the Bland-Altman method. The knee joint was the optimal location for estimating vGRF, followed by the ankle. There were high accuracy and agreement for predicting vGRF with the peak and peak time at 12, 14, and 16 km/h. Therefore, factor loading could be a valid method to screen kinematic variables in artificial neural networks.

Extended Application of Inertial Measurement Units in Biomechanics: From Activity Recognition to Force Estimation

Abnormal posture or movement is generally the indicator of musculoskeletal injuries or diseases. Mechanical forces dominate the injury and recovery processes of musculoskeletal tissue. Using kinematic data collected from wearable sensors (notably IMUs) as input, activity recognition and musculoskeletal force (typically represented by ground reaction force, joint force/torque, and muscle activity/force) estimation approaches based on machine learning models have demonstrated their superior accuracy. The purpose of the present study is to summarize recent achievements in the application of IMUs in biomechanics, with an emphasis on activity recognition and mechanical force estimation. The methodology adopted in such applications, including data pre-processing, noise suppression, classification models, force/torque estimation models, and the corresponding application effects, are reviewed. The extent of the applications of IMUs in daily activity assessment, posture assessment, disease diagnosis, rehabilitation, and exoskeleton control strategy development are illustrated and discussed. More importantly, the technical feasibility and application opportunities of musculoskeletal force prediction using IMU-based wearable devices are indicated and highlighted. With the development and application of novel adaptive networks and deep learning models, the accurate estimation of musculoskeletal forces can become a research field worthy of further attention.

Estimation of gait events and kinetic waveforms with wearable sensors and machine learning when running in an unconstrained environment

Wearable sensors and machine learning algorithms are becoming a viable alternative for biomechanical analysis outside of the laboratory. The purpose of this work was to estimate gait events from inertial measurement units (IMUs) and utilize machine learning for the estimation of ground reaction force (GRF) waveforms. Sixteen healthy runners were recruited for this study, with varied running experience. Force sensing insoles were used to measure normal foot-shoe forces, providing a proxy for vertical GRF and a standard for the identification of gait events. Three IMUs were mounted on each participant, two bilaterally on the dorsal aspect of each foot and one clipped to the back of each participant's waistband, approximating their sacrum. Participants also wore a GPS watch to record elevation and velocity. A Bidirectional Long Short Term Memory Network (BD-LSTM) was used to estimate GRF waveforms from inertial waveforms. Gait event estimation from both IMU data and machine learning algorithms led to accurate estimations of contact time. The GRF magnitudes were generally underestimated by the machine learning algorithm when presented with data from a novel participant, especially at faster running speeds. This work demonstrated that estimation of GRF waveforms is feasible across a range of running velocities and at different grades in an uncontrolled environment.

Internet-of-Things-Enabled Markerless Running Gait Assessment from a Single Smartphone Camera

Running gait assessment is essential for the development of technical optimization strategies as well as to inform injury prevention and rehabilitation. Currently, running gait assessment relies on (i) visual assessment, exhibiting subjectivity and limited reliability, or (ii) use of instrumented approaches, which often carry high costs and can be intrusive due to the attachment of equipment to the body. Here, the use of an IoT-enabled markerless computer vision smartphone application based upon Google’s pose estimation model BlazePose was evaluated for running gait assessment for use in low-resource settings. That human pose estimation architecture was used to extract contact time, swing time, step time, knee flexion angle, and foot strike location from a large cohort of runners. The gold-standard Vicon 3D motion capture system was used as a reference. The proposed approach performs robustly, demonstrating good (ICC(2,1) > 0.75) to excellent (ICC(2,1) > 0.90) agreement in all running gait outcomes. Additionally, temporal outcomes exhibit low mean error (0.01−0.014 s) in left foot outcomes. However, there are some discrepancies in right foot outcomes, due to occlusion. This study demonstrates that the proposed low-cost and markerless system provides accurate running gait assessment outcomes. The approach may help routine running gait assessment in low-resource environments.

Inner-Cycle Phases Can Be Estimated from a Single Inertial Sensor by Long Short-Term Memory Neural Network in Roller-Ski Skating

OBJECTIVE

The aim of this study was to provide a new machine learning method to determine temporal events and inner-cycle parameters (e.g., cycle, pole and ski contact and swing time) in cross-country roller-ski skating on the field, using a single inertial measurement unit (IMU).

METHODS

The developed method is based on long short-term memory neural networks to detect the initial and final contact of the poles and skis with the ground during the cyclic movements. Eleven athletes skied four laps of 2.5 km at a low and high intensity using skis with two different rolling coefficients. They were equipped with IMUs attached to the upper back, lower back and to the sternum. Data from force insoles and force poles were used as the reference system.

RESULTS

The IMU placed on the upper back provided the best results, as the LSTM network was able to determine the temporal events with a mean error ranging from -1 to 11 ms and had a standard deviation (SD) of the error between 64 and 70 ms. The corresponding inner-cycle parameters were calculated with a mean error ranging from -11 to 12 ms and an SD between 66 and 74 ms. The method detected 95% of the events for the poles and 87% of the events for the skis.

CONCLUSION

The proposed LSTM method provides a promising tool for assessing temporal events and inner-cycle phases in roller-ski skating, showing the potential of using a single IMU to estimate different spatiotemporal parameters of human locomotion.

Examination of a foot mounted IMU-based methodology for a running gait assessment

Gait assessment is essential to understand injury prevention mechanisms during running, where high-impact forces can lead to a range of injuries in the lower extremities. Information regarding the running style to increase efficiency and/or selection of the correct running equipment, such as shoe type, can minimize the risk of injury, e.g., matching a runner's gait to a particular set of cushioning technologies found in modern shoes (neutral/support cushioning). Awareness of training or selection of the correct equipment requires an understanding of a runner's biomechanics, such as determining foot orientation when it strikes the ground. Previous work involved a low-cost approach with a foot-mounted inertial measurement unit (IMU) and an associated zero-crossing-based methodology to objectively understand a runner's biomechanics (in any setting) to learn about shoe selection. Here, an investigation of the previously presented ZC-based methodology is presented only to determine general validity for running gait assessment in a range of running abilities from novice (8 km/h) to experienced (16 km/h+). In comparison to Vicon 3D motion tracking data, the presented approach can extract pronation, foot strike location, and ground contact time with good [ICC(2,1) > 0.750] to excellent [ICC(2,1) > 0.900] agreement between 8-12 km/h runs. However, at higher speeds (14 km/h+), the ZC-based approach begins to deteriorate in performance, suggesting that other features and approaches may be more suitable for faster running and sprinting tasks.

Recent Machine Learning Progress in Lower Limb Running Biomechanics With Wearable Technology: A Systematic Review

With the emergence of wearable technology and machine learning approaches, gait monitoring in real-time is attracting interest from the sports biomechanics community. This study presents a systematic review of machine learning approaches in running biomechanics using wearable sensors. Electronic databases were retrieved in PubMed, Web of Science, SPORTDiscus, Scopus, IEEE Xplore, and ScienceDirect. A total of 4,068 articles were identified via electronic databases. Twenty-four articles that met the eligibility criteria after article screening were included in this systematic review. The range of quality scores of the included studies is from 0.78 to 1.00, with 40% of articles recruiting participant numbers between 20 and 50. The number of inertial measurement unit (IMU) placed on the lower limbs varied from 1 to 5, mainly in the pelvis, thigh, distal tibia, and foot. Deep learning algorithms occupied 57% of total machine learning approaches. Convolutional neural networks (CNN) were the most frequently used deep learning algorithm. However, the validation process for machine learning models was lacking in some studies and should be given more attention in future research. The deep learning model combining multiple CNN and recurrent neural networks (RNN) was observed to extract different running features from the wearable sensors and presents a growing trend in running biomechanics.

Population and Age-Based Cardiorespiratory Fitness Level Investigation and Automatic Prediction

Maximal oxygen consumption (VO₂max) reflects aerobic capacity and is crucial for assessing cardiorespiratory fitness and physical activity level. The purpose of this study was to classify and predict the population-based cardiorespiratory fitness based on anthropometric parameters, workload, and steady-state heart rate (HR) of the submaximal exercise test. Five hundred and seventeen participants were recruited into this study. This study initially classified aerobic capacity followed by VO₂max predicted using an ordinary least squares regression model with measured VO₂max from a submaximal cycle test as ground truth. Furthermore, we predicted VO₂max in the age ranges 21–40 and above 40. For the support vector classification model, the test accuracy was 75%. The ordinary least squares regression model showed the coefficient of determination (R²) between measured and predicted VO₂max was 0.83, mean absolute error (MAE) and root mean square error (RMSE) were 3.12 and 4.24 ml/kg/min, respectively. R² in the age 21–40 and above 40 groups were 0.85 and 0.75, respectively. In conclusion, this study provides a practical protocol for estimating cardiorespiratory fitness of an individual in large populations. An applicable submaximal test for population-based cohorts could evaluate physical activity levels and provide exercise recommendations.

Objective assessment of fast bowling delivery intensity in amateur male cricketers

Wearable microtechnology is effective in detecting fast deliveries in cricket, however methods to quantify delivery intensity have not been established. This study aimed to investigate the utility of wearable sensors in quantifying cricket fast bowling intensity.Fifteen sub-elite male fast bowlers performed deliveries at warm-up, match, and maximal intensities. A principal component analysis resulted in the selection of perceived exertion and seven variables of bowling exertion derived from trunk- (PlayerLoad™, trunk flexion velocity, trunk forward rotation velocity) and tibia-mounted (tibial acceleration at back foot contact, front foot contact, back foot re-contact and front foot re-contact) inertial measurement units for further analysis. Repeated measures ANOVAs were used to investigate the effect of intensity on outcome variables. Significant main effects of intensity and large effect sizes were identified for all variables (p < .05, n_p² > 0.14). Measures from the match and maximal conditions were significantly larger compared with the warm-up condition (P_holm < .05). No differences were observed between the match and maximal conditions (p > .05). Inertial measurement metrics can distinguish between a warm-up effort and both match and maximal fast bowling delivery intensity. These devices provide a unique, time-efficient approach to cricket fast bowling exertion quantification.

Transfer Learning Improves Accelerometer-Based Child Activity Recognition via Subject-Independent Adult-Domain Adaption

Wearable activity recognition can collate the type, intensity, and duration of each childs physical activity profile, which is important for exploring underlying adolescent health mechanisms. Traditional machine-learning-based approaches require large labeled data sets; however, child activity data sets are typically small and insufficient. Thus, we proposed a transfer learning approach that adapts adult-domain data to train a high-fidelity, subject-independent model for child activity recognition. Twenty children and twenty adults wore an accelerometer wristband while performing walking, running, sitting, and rope skipping activities. Activity classification accuracy was determined via the traditional machine learning approach without transfer learning and with the proposed subject-independent transfer learning approach. Results showed that transfer learning increased classification accuracy to 91.4% as compared to 80.6% without transfer learning. These results suggest that subject-independent transfer learning can improve accuracy and potentially reduce the size of the required child data sets to enable physical activity monitoring systems to be adopted more widely, quickly, and economically for children and provide deeper insights into injury prevention and health promotion strategies.

Classification of runners' performance levels with concurrent prediction of biomechanical parameters using data from inertial measurement units

Identification of runner's performance level is critical to coaching, performance enhancement and injury prevention. Machine learning techniques have been developed to measure biomechanical parameters with body-worn inertial measurement unit (IMU) sensors. However, a robust method to classify runners is still unavailable. In this paper, we developed two models to classify running performance and predict biomechanical parameters of 30 subjects. We named the models RunNet-CNN and RunNet-MLP based on their architectures: convolutional neural network (CNN) and multilayer perceptron (MLP), respectively. In addition, we examined two validation approaches, subject-wise (leave-one-subject-out) and record-wise. RunNet-MLP classified runner's performance levels with an overall accuracy of 97.1%. Our results also showed that RunNet-CNN outperformed RunNet-MLP and gradient boosting decision tree in predicting biomechanical parameters. RunNet-CNN showed good agreement (R² > 0.9) with the ground-truth reference on biomechanical parameters. The prediction accuracy for the record-wise method was better than the subject-wise method regardless of biomechanical parameters or models. Our findings showed the viability of using IMUs to produce reliable prediction of runners' performance levels and biomechanical parameters.