Estimating Lower Extremity Running Gait Kinematics with a Single Accelerometer: A Deep Learning Approach

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.

A systematic review of the application of deep learning techniques in the physiotherapeutic therapy of musculoskeletal pathologies

Physiotherapy is a critical area of healthcare that involves the assessment and treatment of physical disabilities and injuries. The use of Artificial Intelligence (AI) in physiotherapy has gained significant attention due to its potential to enhance the accuracy and effectiveness of clinical decision-making and treatment outcomes. Nevertheless, it is still a rather innovative field of application of these techniques and there is a need to find what aspects are highly developed and what possible job niches can be exploited. This systematic review aims to evaluate the current state of research on the use of a particular AI called deep learning models in physiotherapy and identify the key trends, challenges, and opportunities in this field. The findings of this review, conducted following the PRISMA guidelines, provide valuable insights for researchers and clinicians. The most relevant databases included were PubMed, Web of Science, Scopus, Astrophysics Data System, and Central Citation Export. Inclusion and exclusion criteria were established to determine which items would be considered for further review. These criteria were used to screen the items during the first and second peer review processes. A set of quality criteria was developed to select the papers obtained after the second screening. Finally, of the 214 initial papers, 23 studies were selected. From our analysis of the selected articles, we can draw the following conclusions: Concerning deep learning models, innovation is primarily seen in the adoption of hybrid models, with convolutional models being extensively utilized. In terms of data, it's unsurprising that body signals and images are predominantly used. However, texts and structured data present promising avenues for groundbreaking work in the field. Additionally, medical tests that involve the collection of 3D images, Functional Movement Screening, or thermographies emerge as novel areas to explore applications within the scope of physiotherapy.

3D gait analysis in children using wearable sensors: feasibility of predicting joint kinematics and kinetics with personalized machine learning models and inertial measurement units

Introduction: Children's walking patterns evolve with age, exhibiting less repetitiveness at a young age and more variability than adults. Three-dimensional gait analysis (3DGA) is crucial for understanding and treating lower limb movement disorders in children, traditionally performed using Optical Motion Capture (OMC). Inertial Measurement Units (IMUs) offer a cost-effective alternative to OMC, although challenges like drift errors persist. Machine learning (ML) models can mitigate these issues in adults, prompting an investigation into their applicability to a heterogeneous pediatric population. This study aimed at 1) quantifying personalized and generalized ML models' performance for predicting gait time series in typically developed (TD) children using IMUs data, 2) Comparing random forest (RF) and convolutional neural networks (CNN) models' performance, 3) Finding the optimal number of IMUs required for accurate predictions. Methodology: Seventeen TD children, aged 6 to 15, participated in data collection involving OMC, force plates, and IMU sensors. Joint kinematics and kinetics (targets) were computed from OMC and force plates' data using OpenSim. Tsfresh, a Python package, extracted features from raw IMU data. Each target's ten most important features were input in the development of personalized and generalized RF and CNN models. This procedure was initially conducted with 7 IMUs placed on all lower limb segments and then performed using only two IMUs on the feet. Results: Findings suggested that the RF and CNN models demonstrated comparable performance. RF predicted joint kinematics with a 9.5% and 19.9% NRMSE for personalized and generalized models, respectively, and joint kinetics with an NRMSE of 10.7% for personalized and 15.2% for generalized models in TD children. Personalized models provided accurate estimations from IMU data in children, while generalized models lacked accuracy due to the limited dataset. Furthermore, reducing the number of IMUs from 7 to 2 did not affect the results, and the performance remained consistent. Discussion: This study proposed a promising personalized approach for gait time series prediction in children, involving an RF model and two IMUs on the feet.

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.

The Fundamentals and Applications of Wearable Sensor Devices in Sports Medicine: A Scoping Review

PURPOSE

To (1) characterize the various forms of wearable sensor devices (WSDs) and (2) review the peer-reviewed literature of applied wearable technology within sports medicine.

METHODS

A systematic search of PubMed and EMBASE databases, from inception through 2023, was conducted to identify eligible studies using WSDs within sports medicine. Data extraction was performed of study demographics and sensor specifications. Included studies were categorized by application: athletic training, rehabilitation, and research.

RESULTS

In total, 43 studies met criteria for inclusion in this review. Forms of WSDs include pedometers, accelerometers, encoders (consisting of magnetometers and gyroscopes), force sensors, global positioning system trackers, and inertial measurement units. Outcome metrics include step counts; gait, limb motion, and angular positioning; foot and skin pressure; change of direction and inclination, including analysis of both body parts and athletes on a field; displacement and velocity of body segments and joints; heart rate; plethysmography; sport-specific kinematics; range of motion, symmetry, and alignment; head impact; sleep; throwing biomechanics; and kinetic and spatiotemporal running metrics. WSDs are used in athletic training to assess sport-specific biomechanics and workload with a goal of injury prevention and training optimization, as well as for rehabilitation monitoring and research such as for risk predicting and aiding diagnosis.

CONCLUSIONS

WSDs enable real-time monitoring of human performance across a variety of implementations and settings, allowing collection of metrics otherwise not achievable. WSDs are powerful tools with multiple applications within athletic training, patient rehabilitation, and orthopaedic and sports medicine research.

CLINICAL RELEVANCE

Wearable technology may represent the missing link to quantitatively addressing return to play and previous performance. WSDs are commercially available and portable adjuncts that allow clinicians, trainers, and individual athletes to monitor biomechanical parameters, workload, and recovery status to better contextualize personalized training, injury risk, and rehabilitation.

E-Textiles for Sports and Fitness Sensing: Current State, Challenges, and Future Opportunities

E-textiles have emerged as a fast-growing area in wearable technology for sports and fitness due to the soft and comfortable nature of textile materials and the capability for smart functionality to be integrated into familiar sports clothing. This review paper presents the roles of wearable technologies in sport and fitness in monitoring movement and biosignals used to assess performance, reduce injury risk, and motivate training/exercise. The drivers of research in e-textiles are discussed after reviewing existing non-textile and textile-based commercial wearable products. Different sensing components/materials (e.g., inertial measurement units, electrodes for biosignals, piezoresistive sensors), manufacturing processes, and their applications in sports and fitness published in the literature were reviewed and discussed. Finally, the paper presents the current challenges of e-textiles to achieve practical applications at scale and future perspectives in e-textiles research and development.

Knee Angle Estimation with Dynamic Calibration Using Inertial Measurement Units for Running

The knee flexion angle is an important measurement for studies of the human gait. Running is a common activity with a high risk of knee injury. Studying the running gait in realistic situations is challenging because accurate joint angle measurements typically come from optical motion-capture systems constrained to laboratory settings. This study considers the use of shank and thigh inertial sensors within three different filtering algorithms to estimate the knee flexion angle for running without requiring sensor-to-segment mounting assumptions, body measurements, specific calibration poses, or magnetometers. The objective of this study is to determine the knee flexion angle within running applications using accelerometer and gyroscope information only. Data were collected for a single test participant (21-year-old female) at four different treadmill speeds and used to validate the estimation results for three filter variations with respect to a Vicon optical motion-capture system. The knee flexion angle filtering algorithms resulted in root-mean-square errors of approximately three degrees. The results of this study indicate estimation results that are within acceptable limits of five degrees for clinical gait analysis. Specifically, a complementary filter approach is effective for knee flexion angle estimation in running applications.

Prediction of knee biomechanics with different tibial component malrotations after total knee arthroplasty: conventional machine learning vs. deep learning

The precise alignment of tibiofemoral components in total knee arthroplasty is a crucial factor in enhancing the longevity and functionality of the knee. However, it is a substantial challenge to quickly predict the biomechanical response to malrotation of tibiofemoral components after total knee arthroplasty using musculoskeletal multibody dynamics models. The objective of the present study was to conduct a comparative analysis between a deep learning method and four conventional machine learning methods for predicting knee biomechanics with different tibial component malrotation during a walking gait after total knee arthroplasty. First, the knee contact forces and kinematics with different tibial component malrotation in the range of ±5° in the three directions of anterior/posterior slope, internal/external rotation, and varus/valgus rotation during a walking gait after total knee arthroplasty were calculated based on the developed musculoskeletal multibody dynamics model. Subsequently, deep learning and four conventional machine learning methods were developed using the above 343 sets of biomechanical data as the dataset. Finally, the results predicted by the deep learning method were compared to the results predicted by four conventional machine learning methods. The findings indicated that the deep learning method was more accurate than four conventional machine learning methods in predicting knee contact forces and kinematics with different tibial component malrotation during a walking gait after total knee arthroplasty. The deep learning method developed in this study enabled quickly determine the biomechanical response with different tibial component malrotation during a walking gait after total knee arthroplasty. The proposed method offered surgeons and surgical robots the ability to establish a calibration safety zone, which was essential for achieving precise alignment in both preoperative surgical planning and intraoperative robotic-assisted surgical navigation.

Estimation of Lower Limb Joint Angles and Joint Moments during Different Locomotive Activities Using the Inertial Measurement Units and a Hybrid Deep Learning Model

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.

Estimating Joint Kinematics and Muscles Forces During Robotic Rehabilitation to Detect and Counteract Reduced Ankle Mobility

The paper presents a solution to detect active ankle joint movement while a patient undergoes therapy with a robotic lower limb rehabilitation device that neither restricts nor actively supports ankle dorsi- or plantarflexion. The presented method requires the addition of only two accelerometer sensors to the system as well as a musculoskeletal model of the lower limb. Using forward kinematics and inverse dynamics, it enables knee and ankle joint kinematic tracking in the sagittal plane and muscle force estimation. This is an extension of a previous work in which only hip joint tracking was possible and, thus, muscle force estimation was limited. The correlation results of the current validation study with 12 healthy subjects show high correlation (R=0.88±0.09) between the kinematics estimated with the proposed method and those calculated from a gold standard motion capture setup for all three joints (hip, knee, and ankle). The correlation results of the estimated m. tibialis anterior muscle force against electromyography measurements (R = 0.62±0.27) are promising and a first application to a patient data set shows potential for future clinical application.

Estimation of horizontal running power using foot-worn inertial measurement units

Feedback of power during running is a promising tool for training and determining pacing strategies. However, current power estimation methods show low validity and are not customized for running on different slopes. To address this issue, we developed three machine-learning models to estimate peak horizontal power for level, uphill, and downhill running using gait spatiotemporal parameters, accelerometer, and gyroscope signals extracted from foot-worn IMUs. The prediction was compared to reference horizontal power obtained during running on a treadmill with an embedded force plate. For each model, we trained an elastic net and a neural network and validated it with a dataset of 34 active adults across a range of speeds and slopes. For the uphill and level running, the concentric phase of the gait cycle was considered, and the neural network model led to the lowest error (median ± interquartile range) of 1.7% ± 12.5% and 3.2% ± 13.4%, respectively. The eccentric phase was considered relevant for downhill running, wherein the elastic net model provided the lowest error of 1.8% ± 14.1%. Results showed a similar performance across a range of different speed/slope running conditions. The findings highlighted the potential of using interpretable biomechanical features in machine learning models for the estimating horizontal power. The simplicity of the models makes them suitable for implementation on embedded systems with limited processing and energy storage capacity. The proposed method meets the requirements for applications needing accurate near real-time feedback and complements existing gait analysis algorithms based on foot-worn IMUs.

BioMAT: An Open-Source Biomechanics Multi-Activity Transformer for Joint Kinematic Predictions Using Wearable Sensors

Through wearable sensors and deep learning techniques, biomechanical analysis can reach beyond the lab for clinical and sporting applications. Transformers, a class of recent deep learning models, have become widely used in state-of-the-art artificial intelligence research due to their superior performance in various natural language processing and computer vision tasks. The performance of transformer models has not yet been investigated in biomechanics applications. In this study, we introduce a Biomechanical Multi-activity Transformer-based model, BioMAT, for the estimation of joint kinematics from streaming signals of multiple inertia measurement units (IMUs) using a publicly available dataset. This dataset includes IMU signals and the corresponding sagittal plane kinematics of the hip, knee, and ankle joints during multiple activities of daily living. We evaluated the model's performance and generalizability and compared it against a convolutional neural network long short-term model, a bidirectional long short-term model, and multi-linear regression across different ambulation tasks including level ground walking (LW), ramp ascent (RA), ramp descent (RD), stair ascent (SA), and stair descent (SD). To investigate the effect of different activity datasets on prediction accuracy, we compared the performance of a universal model trained on all activities against task-specific models trained on individual tasks. When the models were tested on three unseen subjects' data, BioMAT outperformed the benchmark models with an average root mean square error (RMSE) of 5.5 ± 0.5°, and normalized RMSE of 6.8 ± 0.3° across all three joints and all activities. A unified BioMAT model demonstrated superior performance compared to individual task-specific models across four of five activities. The RMSE values from the universal model for LW, RA, RD, SA, and SD activities were 5.0 ± 1.5°, 6.2 ± 1.1°, 5.8 ± 1.1°, 5.3 ± 1.6°, and 5.2 ± 0.7° while these values for task-specific models were, 5.3 ± 2.1°, 6.7 ± 2.0°, 6.9 ± 2.2°, 4.9 ± 1.4°, and 5.6 ± 1.3°, respectively. Overall, BioMAT accurately estimated joint kinematics relative to previous machine learning algorithms across different activities directly from the sequence of IMUs signals instead of time-normalized gait cycle data.

A comparison of machine learning models' accuracy in predicting lower-limb joints' kinematics, kinetics, and muscle forces from wearable sensors

A combination of wearable sensors' data and Machine Learning (ML) techniques has been used in many studies to predict specific joint angles and moments. The aim of this study was to compare the performance of four different non-linear regression ML models to estimate lower-limb joints' kinematics, kinetics, and muscle forces using Inertial Measurement Units (IMUs) and electromyographys' (EMGs) data. Seventeen healthy volunteers (9F, 28 ± 5 years) were asked to walk over-ground for a minimum of 16 trials. For each trial, marker trajectories and three force-plates data were recorded to calculate pelvis, hip, knee, and ankle kinematics and kinetics, and muscle forces (the targets), as well as 7 IMUs and 16 EMGs. The features from sensors' data were extracted using the Tsfresh python package and fed into 4 ML models; Convolutional Neural Networks (CNN), Random Forest (RF), Support Vector Machine, and Multivariate Adaptive Regression Spline for targets' prediction. The RF and CNN models outperformed the other ML models by providing lower prediction errors in all intended targets with a lower computational cost. This study suggested that a combination of wearable sensors' data with an RF or a CNN model is a promising tool to overcome the limitations of traditional optical motion capture for 3D gait analysis.

Lower body kinematics estimation during walking using an accelerometer

Measuring and predicting accurate joint angles are important to developing analytical tools to gauge users' progress. Such measurement is usually performed in laboratory settings, which is difficult and expensive. So, the aim of this study was continuous estimation of lower limb joint angles during walking using an accelerometer and random forest (RF). Thus, 73 subjects (26 women and 47 men) voluntarily participated in this study. The subjects walked at the slow, moderate, and fast speeds on a walkway, which was covered with 10 Vicon camera. Acceleration was used as input for a RF to estimate ankle, knee, and hip angles (in transverse, frontal, and sagittal planes). Pearson correlation coefficient (r) and Mean Square Error (MSE) were computed between the experimental and estimated data. Paired statistical parametric mapping (SPM) t-test was used to compare the experimental and estimated data throughout gait cycle. The results of this study showed that the MSE of joint angles between the experimental and estimated data ranged from 0.04 to 24.29 and r > 0.91. Moreover, the findings of SPM indicated that there was no significant difference between the experimental and estimated data of ankle, knee, and hip angles in all three planes throughout gait cycle. The results of our research developed a more accessible, portable procedure to quantifying lower limb joint angles by an accelerometer and RF. So, such wearable-based joint angles have the potential to be used in outside-laboratory settings to measure walking kinematics.

Development of Tiny Vane-Type Magnetorheological Brake Considering Quality Function Deployment

Many studies focus on the torque-to-dimension ratio when designing magnetorheological brakes (MRB), especially for ankle foot orthosis (AFO) devices. Vane MRB is one type of MRB with a limited angle of motion that is naturally suitable to be applied to AFO. However, very few implement quality function deployment (QFD) when making MRB, whereas QFD is an essential factor in making product designs. In this study, a tiny vane-type MR brake (TVMRB) was successfully made using the QFD method. Torque characteristics are determined by analysis of magnetic flux density, theoretically, by 3D simulation, and by using Ansys Maxwell experimentally. For consideration, the analysis was carried out with fluid gap variations (0.5 mm, 0.75 mm, and 1 mm) and current variations (0.5-2 A with 0.5 A increments). As a result, ignoring the leakage of MR fluid (MRF), at a constant rotation of 10 rpm, the smallest torque of 6.14 Nm was obtained at the fluid gap variation of 1 mm and input current of 0.5 A, whereas the largest torque was 46.71 Nm at the fluid gap variation of 0.5 mm and input current of 2 A. Apart from torque, this article will also discuss other brake performances in the form of operational range and power consumption. Finally, the structure of the TVMRB design is compared with other designs presented in the House of Quality (HOQ).

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.

Cross-Leg Prediction of Running Kinematics across Various Running Conditions and Drawing from a Minimal Data Set Using a Single Wearable Sensor

The feasibility of prediction of same-limb kinematics using a single inertial measurement unit attached to the same limb has been demonstrated using machine learning. This study was performed to see if a single inertial measurement unit attached to the tibia can predict the opposite leg’s kinematics (cross-leg prediction). It also investigated if there is a minimal or smaller data set in a convolutional neural network model to predict lower extremity running kinematics under other running conditions and with what accuracy for the intra- and inter-participant situations. Ten recreational runners completed running exercises under five conditions, including treadmill running at speeds of 2, 2.5, 3, and 3.5 m/s and level-ground running at their preferred speed. A one-predict-all scheme was adopted to determine which running condition could be used to best predict a participant’s overall running kinematics. Running kinematic predictions were performed for intra- and inter-participant scenarios. Among the tested running conditions, treadmill running at 3 m/s was found to be the optimal condition for accurately predicting running kinematics under other conditions, with R2 values ranging from 0.880 to 0.958 and 0.784 to 0.936 for intra- and inter-participant scenarios, respectively. The feasibility of cross-leg prediction was demonstrated but with significantly lower accuracy than the same leg. The treadmill running condition at 3 m/s showed the highest intra-participant cross-leg prediction accuracy. This study proposes a novel, deep-learning method for predicting running kinematics under different conditions on a small training data set.

Predicting the Internal Knee Abduction Impulse During Walking Using Deep Learning

Knee joint moments are commonly calculated to provide an indirect measure of knee joint loads. A shortcoming of inverse dynamics approaches is that the process of collecting and processing human motion data can be time-consuming. This study aimed to benchmark five different deep learning methods in using walking segment kinematics for predicting internal knee abduction impulse during walking. Three-dimensional kinematic and kinetic data used for the present analyses came from a publicly available dataset on walking (participants n = 33). The outcome for prediction was the internal knee abduction impulse over the stance phase. Three-dimensional (3D) angular and linear displacement, velocity, and acceleration of the seven lower body segment’s center of mass (COM), relative to a fixed global coordinate system were derived and formed the predictor space (126 time-series predictors). The total number of observations in the dataset was 6,737. The datasets were split into training (75%, n = 5,052) and testing (25%, n = 1685) datasets. Five deep learning models were benchmarked against inverse dynamics in quantifying knee abduction impulse. A baseline 2D convolutional network model achieved a mean absolute percentage error (MAPE) of 10.80%. Transfer learning with InceptionTime was the best performing model, achieving the best MAPE of 8.28%. Encoding the time-series as images then using a 2D convolutional model performed worse than the baseline model with a MAPE of 16.17%. Time-series based deep learning models were superior to an image-based method when predicting knee abduction moment impulse during walking. Future studies looking to develop wearable technologies will benefit from knowing the optimal network architecture, and the benefit of transfer learning for predicting joint moments.

Recent Trends and Practices Toward Assessment and Rehabilitation of Neurodegenerative Disorders: Insights From Human Gait

The study of human movement and biomechanics forms an integral part of various clinical assessments and provides valuable information toward diagnosing neurodegenerative disorders where the motor symptoms predominate. Conventional gait and postural balance analysis techniques like force platforms, motion cameras, etc., are complex, expensive equipment requiring specialist operators, thereby posing a significant challenge toward translation to the clinics. The current manuscript presents an overview and relevant literature summarizing the umbrella of factors associated with neurodegenerative disorder management: from the pathogenesis and motor symptoms of commonly occurring disorders to current alternate practices toward its quantification and mitigation. This article reviews recent advances in technologies and methodologies for managing important neurodegenerative gait and balance disorders, emphasizing assessment and rehabilitation/assistance. The review predominantly focuses on the application of inertial sensors toward various facets of gait analysis, including event detection, spatiotemporal gait parameter measurement, estimation of joint kinematics, and postural balance analysis. In addition, the use of other sensing principles such as foot-force interaction measurement, electromyography techniques, electrogoniometers, force-myography, ultrasonic, piezoelectric, and microphone sensors has also been explored. The review also examined the commercially available wearable gait analysis systems. Additionally, a summary of recent progress in therapeutic approaches, viz., wearables, virtual reality (VR), and phytochemical compounds, has also been presented, explicitly targeting the neuro-motor and functional impairments associated with these disorders. Efforts toward therapeutic and functional rehabilitation through VR, wearables, and different phytochemical compounds are presented using recent examples of research across the commonly occurring neurodegenerative conditions [viz., Parkinson's disease (PD), Alzheimer's disease (AD), multiple sclerosis, Huntington's disease (HD), and amyotrophic lateral sclerosis (ALS)]. Studies exploring the potential role of Phyto compounds in mitigating commonly associated neurodegenerative pathologies such as mitochondrial dysfunction, α-synuclein accumulation, imbalance of free radicals, etc., are also discussed in breadth. Parameters such as joint angles, plantar pressure, and muscle force can be measured using portable and wearable sensors like accelerometers, gyroscopes, footswitches, force sensors, etc. Kinetic foot insoles and inertial measurement tools are widely explored for studying kinematic and kinetic parameters associated with gait. With advanced correlation algorithms and extensive RCTs, such measurement techniques can be an effective clinical and home-based monitoring and rehabilitation tool for neuro-impaired gait. As evident from the present literature, although the vast majority of works reported are not clinically and extensively validated to derive a firm conclusion about the effectiveness of such techniques, wearable sensors present a promising impact toward dealing with neurodegenerative motor disorders.

DeepBBWAE-Net: A CNN-RNN Based Deep SuperLearner For Estimating Lower Extremity Sagittal Plane Joint Kinematics Using Shoe-Mounted IMU Sensors In Daily Living

Measurement of human body movement is an essential step in biomechanical analysis. The current standard for human motion capture systems uses infrared cameras to track reflective markers placed on the subject. While these systems can accurately track joint kinematics, the analyses are spatially limited to the lab environment. Though Inertial Measurement Unit (IMU) can eliminate the spatial limitations of the motion capture system, those systems are impractical for use in daily living due to the need for many sensors, typically one per body segment. Due to the need for practical and accurate estimation of joint kinematics, this study implements a reduced number of IMU sensors and employs machine learning algorithm to map sensor data to joint angles. Our developed algorithm estimates hip, knee, and ankle angles in the sagittal plane using two shoe-mounted IMU sensors in different practical walking conditions: treadmill, level overground, stair, and slope conditions. Specifically, we proposed five deep learning networks that use combinations of Convolutional Neural Networks (CNN) and Gated Recurrent Unit (GRU) based Recurrent Neural Networks (RNN) as base learners for our framework. Using those five baseline models, we proposed a novel framework, DeepBBWAE-Net, that implements ensemble techniques such as bagging, boosting, and weighted averaging to improve kinematic predictions. DeepBBWAE-Net predicts joint kinematics for the three joint angles under all the walking conditions with a Root Mean Square Error (RMSE) 6.93-29.0% lower than base models individually. This is the first study that uses a reduced number of IMU sensors to estimate kinematics in multiple walking environments.

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.

A Survey of Human Gait-Based Artificial Intelligence Applications

We performed an electronic database search of published works from 2012 to mid-2021 that focus on human gait studies and apply machine learning techniques. We identified six key applications of machine learning using gait data: 1) Gait analysis where analyzing techniques and certain biomechanical analysis factors are improved by utilizing artificial intelligence algorithms, 2) Health and Wellness, with applications in gait monitoring for abnormal gait detection, recognition of human activities, fall detection and sports performance, 3) Human Pose Tracking using one-person or multi-person tracking and localization systems such as OpenPose, Simultaneous Localization and Mapping (SLAM), etc., 4) Gait-based biometrics with applications in person identification, authentication, and re-identification as well as gender and age recognition 5) “Smart gait” applications ranging from smart socks, shoes, and other wearables to smart homes and smart retail stores that incorporate continuous monitoring and control systems and 6) Animation that reconstructs human motion utilizing gait data, simulation and machine learning techniques. Our goal is to provide a single broad-based survey of the applications of machine learning technology in gait analysis and identify future areas of potential study and growth. We discuss the machine learning techniques that have been used with a focus on the tasks they perform, the problems they attempt to solve, and the trade-offs they navigate.

Prediction of Lower Extremity Multi-Joint Angles during Overground Walking by Using a Single IMU with a Low Frequency Based on an LSTM Recurrent Neural Network

The joint angle during gait is an important indicator, such as injury risk index, rehabilitation status evaluation, etc. To analyze gait, inertial measurement unit (IMU) sensors have been used in studies and continuously developed; however, they are difficult to utilize in daily life because of the inconvenience of having to attach multiple sensors together and the difficulty of long-term use due to the battery consumption required for high data sampling rates. To overcome these problems, this study propose a multi-joint angle estimation method based on a long short-term memory (LSTM) recurrent neural network with a single low-frequency (23 Hz) IMU sensor. IMU sensor data attached to the lateral shank were measured during overground walking at a self-selected speed for 30 healthy young persons. The results show a comparatively good accuracy level, similar to previous studies using high-frequency IMU sensors. Compared to the reference results obtained from the motion capture system, the estimated angle coefficient of determination (R2) is greater than 0.74, and the root mean square error and normalized root mean square error (NRMSE) are less than 7° and 9.87%, respectively. The knee joint showed the best estimation performance in terms of the NRMSE and R2 among the hip, knee, and ankle joints.

Path Planning and Impedance Control of a Soft Modular Exoskeleton for Coordinated Upper Limb Rehabilitation

The coordinated rehabilitation of the upper limb is important for the recovery of the daily living abilities of stroke patients. However, the guidance of the joint coordination model is generally lacking in the current robot-assisted rehabilitation. Modular robots with soft joints can assist patients to perform coordinated training with safety and compliance. In this study, a novel coordinated path planning and impedance control method is proposed for the modular exoskeleton elbow-wrist rehabilitation robot driven by pneumatic artificial muscles (PAMs). A convolutional neural network-long short-term memory (CNN-LSTM) model is established to describe the coordination relationship of the upper limb joints, so as to generate adaptive trajectories conformed to the coordination laws. Guided by the planned trajectory, an impedance adjustment strategy is proposed to realize active training within a virtual coordinated tunnel to achieve the robot-assisted upper limb coordinated training. The experimental results showed that the CNN-LSTM hybrid neural network can effectively quantify the coordinated relationship between the upper limb joints, and the impedance control method ensures that the robotic assistance path is always in the virtual coordination tunnel, which can improve the movement coordination of the patient and enhance the rehabilitation effectiveness.

The Use of Synthetic IMU Signals in the Training of Deep Learning Models Significantly Improves the Accuracy of Joint Kinematic Predictions

Gait analysis based on inertial sensors has become an effective method of quantifying movement mechanics, such as joint kinematics and kinetics. Machine learning techniques are used to reliably predict joint mechanics directly from streams of IMU signals for various activities. These data-driven models require comprehensive and representative training datasets to be generalizable across the movement variability seen in the population at large. Bottlenecks in model development frequently occur due to the lack of sufficient training data and the significant time and resources necessary to acquire these datasets. Reliable methods to generate synthetic biomechanical training data could streamline model development and potentially improve model performance. In this study, we developed a methodology to generate synthetic kinematics and the associated predicted IMU signals using open source musculoskeletal modeling software. These synthetic data were used to train neural networks to predict three degree-of-freedom joint rotations at the hip and knee during gait either in lieu of or along with previously measured experimental gait data. The accuracy of the models’ kinematic predictions was assessed using experimentally measured IMU signals and gait kinematics. Models trained using the synthetic data out-performed models using only the experimental data in five of the six rotational degrees of freedom at the hip and knee. On average, root mean square errors in joint angle predictions were improved by 38% at the hip (synthetic data RMSE: 2.3°, measured data RMSE: 4.5°) and 11% at the knee (synthetic data RMSE: 2.9°, measured data RMSE: 3.3°), when models trained solely on synthetic data were compared to measured data. When models were trained on both measured and synthetic data, root mean square errors were reduced by 54% at the hip (measured + synthetic data RMSE: 1.9°) and 45% at the knee (measured + synthetic data RMSE: 1.7°), compared to measured data alone. These findings enable future model development for different activities of clinical significance without the burden of generating large quantities of gait lab data for model training, streamlining model development, and ultimately improving model performance.

Prediction of gait trajectories based on the Long Short Term Memory neural networks

The forecasting of lower limb trajectories can improve the operation of assistive devices and minimise the risk of tripping and balance loss. The aim of this work was to examine four Long Short Term Memory (LSTM) neural network architectures (Vanilla, Stacked, Bidirectional and Autoencoders) in predicting the future trajectories of lower limb kinematics, i.e. Angular Velocity (AV) and Linear Acceleration (LA). Kinematics data of foot, shank and thigh (LA and AV) were collected from 13 male and 3 female participants (28 ± 4 years old, 1.72 ± 0.07 m in height, 66 ± 10 kg in mass) who walked for 10 minutes at preferred walking speed (4.34 ± 0.43 km.h-1) and at an imposed speed (5km.h-1, 15.4% ± 7.6% faster) on a 0% gradient treadmill. The sliding window technique was adopted for training and testing the LSTM models with total kinematics time-series data of 10,500 strides. Results based on leave-one-out cross validation, suggested that the LSTM autoencoders is the top predictor of the lower limb kinematics trajectories (i.e. up to 0.1s). The normalised mean squared error was evaluated on trajectory predictions at each time-step and it obtained 2.82-5.31% for the LSTM autoencoders. The ability to predict future lower limb motions may have a wide range of applications including the design and control of bionics allowing improved human-machine interface and mitigating the risk of falls and balance loss.

Comparison between Accelerometer and Gyroscope in Predicting Level-Ground Running Kinematics by Treadmill Running Kinematics Using a Single Wearable Sensor

Wearable sensors facilitate running kinematics analysis of joint kinematics in real running environments. The use of a few sensors or, ideally, a single inertial measurement unit (IMU) is preferable for accurate gait analysis. This study aimed to use a convolutional neural network (CNN) to predict level-ground running kinematics (measured by four IMUs on the lower extremities) by using treadmill running kinematics training data measured using a single IMU on the anteromedial side of the right tibia and to compare the performance of level-ground running kinematics predictions between raw accelerometer and gyroscope data. The CNN model performed regression for intraparticipant and interparticipant scenarios and predicted running kinematics. Ten recreational runners were recruited. Accelerometer and gyroscope data were collected. Intraparticipant and interparticipant R² values of actual and predicted running kinematics ranged from 0.85 to 0.96 and from 0.7 to 0.92, respectively. Normalized root mean squared error values of actual and predicted running kinematics ranged from 3.6% to 10.8% and from 7.4% to 10.8% in intraparticipant and interparticipant tests, respectively. Kinematics predictions in the sagittal plane were found to be better for the knee joint than for the hip joint, and predictions using the gyroscope as the regressor were demonstrated to be significantly better than those using the accelerometer as the regressor.

Combining Inertial Sensors and Machine Learning to Predict vGRF and Knee Biomechanics during a Double Limb Jump Landing Task

(1) Background: Biomechanics during landing tasks, such as the kinematics and kinetics of the knee, are altered following anterior cruciate ligament (ACL) injury and reconstruction. These variables are recommended to assess prior to clearance for return to sport, but clinicians lack access to the current gold-standard laboratory-based assessment. Inertial sensors serve as a potential solution to provide a clinically feasible means to assess biomechanics and augment the return to sport testing. The purposes of this study were to (a) develop multi-sensor machine learning algorithms for predicting biomechanics and (b) quantify the accuracy of each algorithm. (2) Methods: 26 healthy young adults completed 8 trials of a double limb jump landing task. Peak vertical ground reaction force, peak knee flexion angle, peak knee extension moment, and peak sagittal knee power absorption were assessed using 3D motion capture and force plates. Shank- and thigh- mounted inertial sensors were used to collect data concurrently. Inertial data were submitted as inputs to single- and multiple- feature linear regressions to predict biomechanical variables in each limb. (3) Results: Multiple-feature models, particularly when an accelerometer and gyroscope were used together, were valid predictors of biomechanics (R² = 0.68–0.94, normalized root mean square error = 4.6–10.2%). Single-feature models had decreased performance (R² = 0.16–0.60, normalized root mean square error = 10.0–16.2%). (4) Conclusions: The combination of inertial sensors and machine learning provides a valid prediction of biomechanics during a double limb landing task. This is a feasible solution to assess biomechanics for both clinical and real-world settings outside the traditional biomechanics laboratory.

Machine learning for rapid estimation of lower extremity muscle and joint loading during activities of daily living

Joint contact and muscle forces estimated with musculoskeletal modeling techniques offer useful metrics describing movement quality that benefit multiple research and clinical applications. The expensive processing of laboratory data associated with generating these outputs presents challenges to researchers and clinicians, including significant time and expertise requirements that limit the number of subjects typically evaluated. The objective of the current study was to develop and compare machine learning techniques for rapid, data-driven estimation of musculoskeletal metrics from derived gait lab data. OpenSim estimates of patient joint and muscle forces during activities of daily living were simulated using laboratory data from 70 total knee replacement patients and used to develop 4 different machine learning algorithms. Trained machine learning models predicted both trend and magnitude of estimated joint contact (mean correlation coefficients ranging from 0.93 to 0.94 during gait) and muscle forces (mean correlation coefficients ranging from 0.83 to 0.91 during gait) based on anthropometrics, ground reaction forces, and joint angle data. Patient mechanics were accurately predicted by recurrent neural networks, even after removing dependence on key subsets of predictor features. The ability to quickly estimate patient mechanics from derived measurements of movement has the potential to broaden the impact of musculoskeletal modeling by enabling faster assessment in both clinical and research settings.

Treadmill-to-Overground Mapping of Marker Trajectory for Treadmill-Based Continuous Gait Analysis

A treadmill was used to perform continuous walking tests in a limited space that can be covered by marker-based optical motion capture systems. Most treadmill-based gait data are analyzed based on gait cycle percentage. However, achieving continuous walking motion trajectories over time without time normalization is often required, even if tests are performed under treadmill walking conditions. This study presents a treadmill-to-overground mapping method of optical marker trajectories for treadmill-based continuous gait analysis, by adopting a simple concept of virtual origin. The position vector from the backward moving virtual origin to a targeted marker within a limited walking volume is the same as the position vector from the fixed origin to the forward moving marker over the ground. With the proposed method, it is possible (i) to observe the change in physical quantity visually during the treadmill walking, and (ii) to obtain overground-mapped gait data for evaluating the accuracy of the inertial-measurement-unit-based trajectory estimation. The accuracy of the proposed method was verified from various treadmill walking tests, which showed that the total travel displacement error rate was 0.32% on average.