Use of Machine Learning and Wearable Sensors to Predict Energetics and Kinematics of Cutting Maneuvers

Motion Tracking of Daily Living and Physical Activities in Health Care: Systematic Review From Designers' Perspective

BACKGROUND

Motion tracking technologies serve as crucial links between physical activities and health care insights, facilitating data acquisition essential for analyzing and intervening in physical activity. Yet, systematic methodologies for evaluating motion tracking data, especially concerning user activity recognition in health care applications, remain underreported.

OBJECTIVE

This study aims to systematically review motion tracking in daily living and physical activities, emphasizing the critical interaction among devices, users, and environments from a design perspective, and to analyze the process involved in health care application research. It intends to delineate the design and application intricacies in health care contexts, focusing on enhancing motion tracking data's accuracy and applicability for health monitoring and intervention strategies.

METHODS

Using a systematic review, this research scrutinized motion tracking data and their application in health care and wellness, examining studies from Scopus, Web of Science, EBSCO, and PubMed databases. The review used actor network theory and data-enabled design to understand the complex interplay between humans, devices, and environments within these applications.

RESULTS

Out of 1501 initially identified studies, 54 (3.66%) were included for in-depth analysis. These articles predominantly used accelerometer and gyroscope sensors (n=43, 80%) to monitor and analyze motion, demonstrating a strong preference for these technologies in capturing both dynamic and static activities. While incorporating portable devices (n=11, 20%) and multisensor configurations (n=16, 30%), the application of sensors across the body (n=15, 28%) and within physical spaces (n=17, 31%) highlights the diverse applications of motion tracking technologies in health care research. This diversity reflects the application's alignment with activity types ranging from daily movements to specialized scenarios. The results also reveal a diverse participant pool, including the general public, athletes, and specialized groups, with a focus on healthy individuals (n=31, 57%) and athletes (n=14, 26%). Despite this extensive application range, the focus primarily on laboratory-based studies (n=39, 72%) aimed at professional uses, such as precise activity identification and joint functionality assessment, emphasizes a significant challenge in translating findings from controlled environments to the dynamic conditions of everyday physical activities.

CONCLUSIONS

This study's comprehensive investigation of motion tracking technology in health care research reveals a significant gap between the methods used for data collection and their practical application in real-world scenarios. It proposes an innovative approach that includes designers in the research process, emphasizing the importance of incorporating data-enabled design framework. This ensures that motion data collection is aligned with the dynamic and varied nature of daily living and physical activities. Such integration is crucial for developing health applications that are accessible, intuitive, and tailored to meet diverse user needs. By leveraging a multidisciplinary approach that combines design, engineering, and health sciences, the research opens new pathways for enhancing the usability and effectiveness of health technologies.

In-field assessment of change-of-direction ability with a single wearable sensor

The Agility T-test is a standardized method to measure the change-of-direction (COD) ability of athletes in the field. It is traditionally scored based on the total completion time, which does not provide information on the different CODs. Augmenting the T-test with wearable sensors provides the opportunity to explore new metrics. Towards this, data of 23 professional soccer players were recorded with a trunk-worn GNSS-IMU (Global Navigation Satellite System-Inertial Measurement Unit) device. A method for detecting the four CODs based on the wavelet-denoised antero-posterior acceleration signal was developed and validated using video data (60 Hz). Following this, completion time was estimated using GNSS ground speed and validated with the photocell data. The proposed method yields an error (mean ± standard deviation) of 0 ± 66 ms for the COD detection, - 0.16 ± 0.22 s for completion time, and a relative error for each COD duration and each sequential movement durations of less than 3.5 ± 16% and 7 ± 7%, respectively. The presented algorithm can highlight the asymmetric performance between the phases and CODs in the right and left direction. By providing a more comprehensive analysis in the field, this work can enable coaches to develop more personalized training and rehabilitation programs.

Effect of IMU location on estimation of vertical ground reaction force during jumping

Introduction: Several investigations have examined utilizing inertial measurement units (IMU) to estimate ground reaction force (GRF) during exercise. The purpose of this investigation was to determine the effect of inertial measurement units location on the estimation of ground reaction force during vertical jumping. Methods: Eight male subjects completed a series of ten countermovement jumps on a force plate (FP). The subjects had an inertial measurement units attached to the sacrum, back and chest. Ground reaction force was estimated from data from the individual inertial measurement units and by using a two-segment model and combined sensor approach. Results: The peak ground reaction force values for the sacrum, back, chest and combined inertial measurement units were 1,792 ± 278 N, 1,850 ± 341 N, 2,054 ± 346 N and 1,812 ± 323 N, respectively. The sacral inertial measurement units achieved the smallest differences for ground reaction force estimates providing a root mean square error (RMSE) between 88 N and 360 N. The inertial measurement units on the sacrum also showed significant correlations in peak ground reaction force (p < 0.001) and average ground reaction force (p < 0.001) using the Bland-Altman 95% Limits of Agreement (LOA) when in comparison to the force plate. Discussion: Based on assessment of bias, Limits of Agreement, and RMSE, the inertial measurement units located on the sacrum appears to be the best placement to estimate both peak and average ground reaction force during jumping.

Machine learning application in soccer: a systematic review

Due to the chaotic nature of soccer, the predictive statistical models have become in a current challenge to decision-making based on scientific evidence. The aim of the present study was to systematically identify original studies that applied machine learning (ML) to soccer data, highlighting current possibilities in ML and future applications. A systematic review of PubMed, SPORTDiscus, and FECYT (Web of Sciences, CCC, DIIDW, KJD, MEDLINE, RSCI, and SCIELO) was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. From the 145 studies initially identified, 32 were fully reviewed, and their outcome measures were extracted and analyzed. In summary, all articles were clustered into three groups: injury (n = 7); performance (n = 21), which was classified in match/league outcomes forecasting, physical/physiological forecasting, and technical/tactical forecasting; and the last group was about talent forecasting (n = 5). The development of technology, and subsequently the large amount of data available, has become ML in an important strategy to help team staff members in decision-making predicting dose-response relationship reducing the chaotic nature of this team sport. However, since ML models depend upon the amount of dataset, further studies should analyze the amount of data input needed make to a relevant predictive attempt which makes accurate predicting available.

A review of machine learning applications in soccer with an emphasis on injury risk

This narrative review paper aimed to discuss the literature on machine learning applications in soccer with an emphasis on injury risk assessment. A secondary aim was to provide practical tips for the health and performance staff in soccer clubs on how machine learning can provide a competitive advantage. Performance analysis is the area with the majority of research so far. Other domains of soccer science and medicine with machine learning use are injury risk assessment, players' workload and wellness monitoring, movement analysis, players' career trajectory, club performance, and match attendance. Regarding injuries, which is a hot topic, machine learning does not seem to have a high predictive ability at the moment (models specificity ranged from 74.2%-97.7%. sensitivity from 15.2%-55.6% with area under the curve of 0.66-0.83). It seems, though, that machine learning can help to identify the early signs of elevated risk for a musculoskeletal injury. Future research should account for musculoskeletal injuries' dynamic nature for machine learning to provide more meaningful results for practitioners in soccer.

Predicting Coordination Variability of Selected Lower Extremity Couplings during a Cutting Movement: An Investigation of Deep Neural Networks with the LSTM Structure

There are still few portable methods for monitoring lower limb joint coordination during the cutting movements (CM). This study aims to obtain the relevant motion biomechanical parameters of the lower limb joints at 90°, 135°, and 180° CM by collecting IMU data of the human lower limbs, and utilizing the Long Short-Term Memory (LSTM) deep neural-network framework to predict the coordination variability of selected lower extremity couplings at the three CM directions. There was a significant (p < 0.001) difference between the three couplings during the swing, especially at 90° vs the other directions. At 135° and 180°, t13-he coordination variability of couplings was significantly greater than at 90° (p < 0.001). It is important to note that the coordination variability of Hip rotation/Knee flexion-extension was significantly higher at 90° than at 180° (p < 0.001). By the LSTM, the CM coordination variability for 90° (CMC = 0.99063, RMSE = 0.02358), 135° (CMC = 0.99018, RMSE = 0.02465) and 180° (CMC = 0.99485, RMSE = 0.01771) were accurately predicted. The predictive model could be used as a reliable tool for predicting the coordination variability of different CM directions in patients or athletes and real-world open scenarios using inertial sensors.

The Use of Wearable Sensors for Preventing, Assessing, and Informing Recovery from Sport-Related Musculoskeletal Injuries: A Systematic Scoping Review

Wearable technologies are often indicated as tools that can enable the in-field collection of quantitative biomechanical data, unobtrusively, for extended periods of time, and with few spatial limitations. Despite many claims about their potential for impact in the area of injury prevention and management, there seems to be little attention to grounding this potential in biomechanical research linking quantities from wearables to musculoskeletal injuries, and to assessing the readiness of these biomechanical approaches for being implemented in real practice. We performed a systematic scoping review to characterise and critically analyse the state of the art of research using wearable technologies to study musculoskeletal injuries in sport from a biomechanical perspective. A total of 4952 articles were retrieved from the Web of Science, Scopus, and PubMed databases; 165 were included. Multiple study features-such as research design, scope, experimental settings, and applied context-were summarised and assessed. We also proposed an injury-research readiness classification tool to gauge the maturity of biomechanical approaches using wearables. Five main conclusions emerged from this review, which we used as a springboard to propose guidelines and good practices for future research and dissemination in the field.

Foot Position Measurement during Assistive Motion for Sit-to-Stand Using a Single Inertial Sensor and Shoe-Type Force Sensors

Assistive motion for sit-to-stand causes lower back pain (LBP) among caregivers. Considering previous studies that showed that foot position adjustment could reduce lumbar load during assistive motion for sit-to-stand, quantitative monitoring of and instructions on foot position could contribute toward reducing LBP among caregivers. The present study proposes and evaluates a new method for the quantitative measurement of foot position during assistive motion for sit-to-stand using a few wearable sensors that are not limited to the measurement area. The proposed method measures quantitative foot position (anteroposterior and mediolateral distance between both feet) through a machine learning technique using features obtained from only a single inertial sensor on the trunk and shoe-type force sensors. During the experiment, the accuracy of the proposed method was investigated by comparing the obtained values with those from an optical motion capture system. The results showed that the proposed method produced only minor errors (less than 6.5% of body height) when measuring foot position during assistive motion for sit-to-stand. Furthermore, Bland–Altman plots suggested no fixed errors between the proposed method and the optical motion capture system. These results suggest that the proposed method could be utilized for measuring foot position during assistive motion for sit-to-stand.

Machine-Learning Based Determination of Gait Events from Foot-Mounted Inertial Units

A promising but still scarcely explored strategy for the estimation of gait parameters based on inertial sensors involves the adoption of machine learning techniques. However, existing approaches are reliable only for specific conditions, inertial measurements unit (IMU) placement on the body, protocols, or when combined with additional devices. In this paper, we tested an alternative gait-events estimation approach which is fully data-driven and does not rely on a priori models or assumptions. High-frequency (512 Hz) data from a commercial inertial unit were recorded during 500 steps performed by 40 healthy participants. Sensors’ readings were synchronized with a reference ground reaction force system to determine initial/terminal contacts. Then, we extracted a set of features from windowed data labeled according to the reference. Two gray-box approaches were evaluated: (1) classifiers (decision trees) returning the presence of a gait event in each time window and (2) a classifier discriminating between stance and swing phases. Both outputs were submitted to a deterministic algorithm correcting spurious clusters of predictions. The stance vs. swing approach estimated the stride time duration with an average error lower than 20 ms and confidence bounds between ±50 ms. These figures are suitable to detect clinically meaningful differences across different populations.

Classifying Elite From Novice Athletes Using Simulated Wearable Sensor Data

Movement screens are frequently used to identify differences in movement patterns such as pathological abnormalities or skill related differences in sport; however, abnormalities are often visually detected by a human assessor resulting in poor reliability. Therefore, our previous research has focused on the development of an objective movement assessment tool to classify elite and novice athletes’ kinematic data using machine learning algorithms. Classifying elite and novice athletes can be beneficial to objectively detect differences in movement patterns between the athletes, which can then be used to provide higher quality feedback to athletes and their coaches. Currently, the method requires optical motion capture, which is expensive and time-consuming to use, creating a barrier for adoption within industry. Therefore, the purpose of this study was to assess whether machine learning could classify athletes as elite or novice using data that can be collected easily and inexpensively in the field using inertial measurement units (IMUs). A secondary purpose of this study was to refine the architecture of the tool to optimize classification rates. Motion capture data from 542 athletes performing seven dynamic screening movements were analyzed. A principal component analysis (PCA)-based pattern recognition technique and machine learning algorithms with the Euclidean norm of the segment linear accelerations and angular velocities as inputs were used to classify athletes based on skill level. Depending on the movement, using metrics achievable with IMUs and a linear discriminant analysis (LDA), 75.1–84.7% of athletes were accurately classified as elite or novice. We have provided evidence that suggests our objective, data-driven method can detect meaningful differences during a movement screening battery when using data that can be collected using IMUs, thus providing a large methodological advance as these can be collected in the field using sensors. This method offers an objective, inexpensive tool that can be easily implemented in the field to potentially enhance screening, assessment, and rehabilitation in sport and clinical settings.

Artificial Neural Networks in Motion Analysis-Applications of Unsupervised and Heuristic Feature Selection Techniques

The use of machine learning to estimate joint angles from inertial sensors is a promising approach to in-field motion analysis. In this context, the simplification of the measurements by using a small number of sensors is of great interest. Neural networks have the opportunity to estimate joint angles from a sparse dataset, which enables the reduction of sensors necessary for the determination of all three-dimensional lower limb joint angles. Additionally, the dimensions of the problem can be simplified using principal component analysis. Training a long short-term memory neural network on the prediction of 3D lower limb joint angles based on inertial data showed that three sensors placed on the pelvis and both shanks are sufficient. The application of principal component analysis to the data of five sensors did not reveal improved results. The use of longer motion sequences compared to time-normalised gait cycles seems to be advantageous for the prediction accuracy, which bridges the gap to real-time applications of long short-term memory neural networks in the future.

Sport Biomechanics Applications Using Inertial, Force, and EMG Sensors: A Literature Overview

In the last few decades, a number of technological developments have advanced the spread of wearable sensors for the assessment of human motion. These sensors have been also developed to assess athletes' performance, providing useful guidelines for coaching, as well as for injury prevention. The data from these sensors provides key performance outcomes as well as more detailed kinematic, kinetic, and electromyographic data that provides insight into how the performance was obtained. From this perspective, inertial sensors, force sensors, and electromyography appear to be the most appropriate wearable sensors to use. Several studies were conducted to verify the feasibility of using wearable sensors for sport applications by using both commercially available and customized sensors. The present study seeks to provide an overview of sport biomechanics applications found from recent literature using wearable sensors, highlighting some information related to the used sensors and analysis methods. From the literature review results, it appears that inertial sensors are the most widespread sensors for assessing athletes' performance; however, there still exist applications for force sensors and electromyography in this context. The main sport assessed in the studies was running, even though the range of sports examined was quite high. The provided overview can be useful for researchers, athletes, and coaches to understand the technologies currently available for sport performance assessment.

Motion Sensors-Based Machine Learning Approach for the Identification of Anterior Cruciate Ligament Gait Patterns in On-the-Field Activities in Rugby Players

Anterior cruciate ligament (ACL) injuries are common among athletes. Despite a successful return to sport (RTS) for most of the injured athletes, a significant proportion do not return to competitive levels, and thus RTS post ACL reconstruction still represents a challenge for clinicians. Wearable sensors, owing to their small size and low cost, can represent an opportunity for the management of athletes on-the-field after RTS by providing guidance to associated clinicians. In particular, this study aims to investigate the ability of a set of inertial sensors worn on the lower-limbs by rugby players involved in a change-of-direction (COD) activity to differentiate between healthy and post-ACL groups via the use of machine learning. Twelve male participants (six healthy and six post-ACL athletes who were deemed to have successfully returned to competitive rugby and tested in the 5–10 year period following the injury) were recruited for the study. Time- and frequency-domain features were extracted from the raw inertial data collected. Several machine learning models were tested, such as k-nearest neighbors, naïve Bayes, support vector machine, gradient boosting tree, multi-layer perceptron, and stacking. Feature selection was implemented in the learning model, and leave-one-subject-out cross-validation (LOSO-CV) was adopted to estimate training and test errors. Results obtained show that it is possible to correctly discriminate between healthy and post-ACL injury subjects with an accuracy of 73.07% (multi-layer perceptron) and sensitivity of 81.8% (gradient boosting). The results of this study demonstrate the feasibility of using body-worn motion sensors and machine learning approaches for the identification of post-ACL gait patterns in athletes performing sport tasks on-the-field even a number of years after the injury occurred.

Relationships between Body Build and Knee Joint Flexor and Extensor Torque of Polish First-Division Soccer Players

The aim of the study is to identify the relationships between anthropometric variables and knee joint extensor peak torque, knee joint flexor peak torque, and conventional hamstring-to-quadriceps ratio in Polish first-division soccer players. The study examined 37 soccer players aged 19 to 30 years (body mass: 76.8 ± 7.2 kg, body height 1.82 ± 0.06 m). Muscle torques of the knee joint were measured under isometric conditions using a Biodex 4 Pro dynamometer. The anthropometric variables such as body part lengths, breadths, and girths and skinfold thickness were measured. The strongest relationships of knee joint extensors were observed with body mass and variables describing skeleton size and lower-limb muscles. Regarding knee flexor torque, a significant relationship was found only with body mass. However, no significant relationships were observed between the conventional hamstring-to-quadriceps ratio and the anthropometric variables studied. The regression analysis results identified body height, body mass, and thigh and calf girth as the features most associated with knee joint torque. However, anthropometric measurements do not provide full information about the torque proportions of antagonist muscle groups, which is very important for injury prevention. Therefore, measurements using special biomechanical equipment are also necessary for the comprehensive analyses and control of the effects of sports training.