Golf Swing Segmentation from a Single IMU Using Machine Learning

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.

Location Matters-Can a Smart Golf Club Detect Where the Club Face Hits the Ball?

In golf, the location of the impact, where the clubhead hits the ball, is of imperative nature for a successful ballflight. Direct feedback to the athlete where he/she hits the ball could improve a practice session. Currently, this information can be measured via, e.g., dual laser technology; however, this is a stationary and external method. A mobile measurement method would give athletes the freedom to gain the information of the impact location without the limitation to be stationary. Therefore, the aim of this study was to investigate whether it is possible to detect the impact location via a motion sensor mounted on the shaft of the golf club. To answer the question, an experiment was carried out. Within the experiment data were gathered from one athlete performing 282 golf swings with an 7 iron. The impact location was recorded and labeled during each swing with a Trackman providing the classes for a neural network. Simultaneously, the motion of the golf club was gathered with an IMU from the Noraxon Ultium Motion Series. In the next step, a neural network was designed and trained to estimate the impact location class based on the motion data. Based on the motion data, a classification accuracy of 93.8% could be achieved with a ResNet architecture.

A Neural Network Approach for Inertial Measurement Unit-Based Estimation of Three-Dimensional Spinal Curvature

The spine is an important part of the human body. Thus, its curvature and shape are closely monitored, and treatment is required if abnormalities are detected. However, the current method of spinal examination mostly relies on two-dimensional static imaging, which does not provide real-time information on dynamic spinal behaviour. Therefore, this study explored an easier and more efficient method based on machine learning and sensors to determine the curvature of the spine. Fifteen participants were recruited and performed tests to generate data for training a neural network. This estimated the spinal curvature from the readings of three inertial measurement units and had an average absolute error of 0.261161 cm.

The swing performance Index: Developing a single-score index of golf swing rotational biomechanics quantified with 3D kinematics

Introduction

Golf swing generates power through coordinated rotations of the pelvis and upper torso, which are highly consistent among professionals. Currently, golf performance is graded on handicap, length-of-shot, and clubhead-speed-at-impact. No performance indices are grading the technique of pelvic and torso rotations. As an initial step toward developing a performance index, we collected kinematic metrics of swing rotational biomechanics and hypothesized that a set of these metrics could differentiate between amateur and pro players. The aim of this study was to develop a single-score index of rotational biomechanics based on metrics that are consistent among pros and could be derived in the future using inertial measurement units (IMU).

Methods

Golf swing rotational biomechanics was analyzed using 3D kinematics on eleven professional (age 31.0 ± 5.9 years) and five amateur (age 28.4 ± 6.9 years) golfers. Nine kinematic metrics known to be consistent among professionals and could be obtained using IMUs were selected as candidate variables. Oversampling was used to account for dataset imbalances. All combinations, up to three metrics, were tested for suitability for factor analysis using Kaiser-Meyer-Olkin tests. Principal component analysis was performed, and the logarithm of Euclidean distance of principal components between golf swings and the average pro vector was used to classify pro vs. amateur golf swings employing logistic regression and leave-one-out cross-validation. The area under the receiver operating characteristic curve was used to determine the optimal set of kinematic metrics.

Results

A single-score index calculated using peak pelvic rotational velocity pre-impact, pelvic rotational velocity at impact, and peak upper torso rotational velocity post-impact demonstrated strong predictive performance to differentiate pro (mean ± SD:100 ± 10) vs. amateur (mean ± SD:82 ± 4) golfers with an AUC of 0.97 and a standardized mean difference of 2.12.

Discussion

In this initial analysis, an index derived from peak pelvic rotational velocity pre-impact, pelvic rotational velocity at impact, and peak upper torso rotational velocity post-impact demonstrated strong predictive performance to differentiate pro from amateur golfers. Swing Performance Index was developed using a limited sample size; future research is needed to confirm results. The Swing Performance Index aims to provide quantified feedback on swing technique to improve performance, expedite training, and prevent injuries.

Design, Assessment and Deployment of an Efficient Golf Game Dynamics Management System Based on Flexible Wireless Technologies

The practice of sports has been steadily evolving, taking advantage of different technological tools to improve different aspects such as individual/collective training, support in match development or enhancement of audience experience. In this work, an in-house implemented monitoring system for golf training and competition is developed, composed of a set of distributed end devices, gateways and routers, connected to a web-based platform for data analysis, extraction and visualization. Extensive wireless channel analysis has been performed, by means of deterministic 3D radio channel estimations and radio frequency measurements, to provide coverage/capacity estimations for the specific use case of golf courses. The monitoring system has been fully designed considering communication as well as energy constraints, including wireless power transfer (WPT) capabilities in order to provide flexible node deployment. System validation has been performed in a real golf course, validating end-to-end connectivity and information handling to improve overall user experience.

Pilot Study of Embedded IMU Sensors and Machine Learning Algorithms for Automated Ice Hockey Stick Fitting

The aims of this study were to evaluate the feasibility of using IMU sensors and machine learning algorithms for the instantaneous fitting of ice hockey sticks. Ten experienced hockey players performed 80 shots using four sticks of differing constructions (i.e., each stick differed in stiffness, blade pattern, or kick point). Custom IMUs were embedded in a pair of hockey gloves to capture resultant linear acceleration and angular velocity of the hands during shooting while an 18-camera optical motion capture system and retroreflective markers were used to identify key shot events and measure puck speed, accuracy, and contact time with the stick blade. MATLAB R2020a’s Machine Learning Toolbox was used to build and evaluate the performance of machine learning algorithms using principal components of the resultant hand kinematic signals using principal components accounting for 95% of the variability and a five-fold cross validation. Fine k-nearest neighbors algorithms were found to be highly accurate, correctly classifying players by optimal stick flex, blade pattern, and kick point with 90–98% accuracy for slap shots and 93–97% accuracy for wrist shots in fractions of a second. Based on these findings, it appears promising that wearable sensors and machine learning algorithms can be used for reliable, rapid, and portable hockey stick fitting.

Competitive Golf: How Longer Courses Are Changing Athletes and Their Approach to the Game

Nutritional guidance for competitive golfers to improve performance is limited. Recommendations and study conclusions from older research used smaller golf courses compared to today and require a reevaluation of energy expenditure. This review identifies aerobic fitness, in addition to strength, as a key determinant of success. A novel nutritional approach that incorporates carbohydrate supplementation to support aerobic fitness without sacrificing the ability to build strength is presented since longer courses require more stamina. Strategies for training, competition, and recovery are outlined based on different skill levels. American College of Sports Medicine (ACSM) guidelines for carbohydrates, protein, and hydration intake are tailored specifically for competitive golf based on this approach. Putting requires precise movement and can be affected by fatigue. Nutritional studies in golf and similar sports that require focused movements are presented, exhibiting an improvement with adequate hydration and carbohydrate status and caffeine use. Competitive golf poses unique challenges to an athlete and commonly used ergogenic supplements that can improve performance in a variety of circumstances during training, competition, and while traveling are reviewed.

Using Inertial Sensors to Determine Head Motion-A Review

Human activity recognition and classification are some of the most interesting research fields, especially due to the rising popularity of wearable devices, such as mobile phones and smartwatches, which are present in our daily lives. Determining head motion and activities through wearable devices has applications in different domains, such as medicine, entertainment, health monitoring, and sports training. In addition, understanding head motion is important for modern-day topics, such as metaverse systems, virtual reality, and touchless systems. The wearability and usability of head motion systems are more technologically advanced than those which use information from a sensor connected to other parts of the human body. The current paper presents an overview of the technical literature from the last decade on state-of-the-art head motion monitoring systems based on inertial sensors. This study provides an overview of the existing solutions used to monitor head motion using inertial sensors. The focus of this study was on determining the acquisition methods, prototype structures, preprocessing steps, computational methods, and techniques used to validate these systems. From a preliminary inspection of the technical literature, we observed that this was the first work which looks specifically at head motion systems based on inertial sensors and their techniques. The research was conducted using four internet databases-IEEE Xplore, Elsevier, MDPI, and Springer. According to this survey, most of the studies focused on analyzing general human activity, and less on a specific activity. In addition, this paper provides a thorough overview of the last decade of approaches and machine learning algorithms used to monitor head motion using inertial sensors. For each method, concept, and final solution, this study provides a comprehensive number of references which help prove the advantages and disadvantages of the inertial sensors used to read head motion. The results of this study help to contextualize emerging inertial sensor technology in relation to broader goals to help people suffering from partial or total paralysis of the body.

Injury risk-factor differences between two golf swing styles: a biomechanical analysis of the lumbar spine, hip and knee

The golf swing has been associated with mechanical injury risk factors at many joints. One swing, the Minimalist Golf Swing, was hypothesised to reduce lumbar spine, lead hip, and lead knee ranges of motion and peak net joint moments, while affecting swing performance, compared to golfers' existing swings. Existing and MGS swings of 15 golfers with handicaps ranging from +2 to -20 were compared. During MGS downswing, golfers had 18.3% less lumbar spine transverse plane ROM, 40.7 and 41.8% less lead hip sagittal and frontal plane ROM, and 39.2% less lead knee sagittal plane ROM. MGS reduced lead hip extensor, abductor, and internal rotator moments by 17.8, 19.7 and 43%, while lead knee extensor, abductor, adductor and external rotator moments were reduced by 24.1, 26.6, 37 and 68.8% respectively. With MGS, club approach was 2° shallower, path 4° more in-to-out and speed 2 m/s slower. MGS reduced certain joint ROM and moments that are linked to injury risk factors, while influencing club impact factors with varying effect. Most golf injuries are from overuse, so reduced loads per cycle with MGS may extend the healthy life of joints, and permit golfers to play injury-free for more years.

Use of IMU in Differential Analysis of the Reverse Punch Temporal Structure in Relation to the Achieved Maximal Hand Velocity

To achieve good performance, athletes need to synchronize a series of movements in an optimal manner. One of the indicators used to monitor this is the order of occurrence of relevant events in the movement timeline. However, monitoring of this characteristic of rapid movement is practically limited to the laboratory settings, in which motion tracking systems can be used to acquire relevant data. Our motivation is to implement a simple-to-use and robust IMU-based solution suitable for everyday praxis. In this way, repetitive execution of technique can be constantly monitored. This provides augmented feedback to coaches and athletes and is relevant in the context of prevention of stabilization of errors, as well as monitoring for the effects of fatigue. In this research, acceleration and rotational speed signal acquired from a pair of IMUs (Inertial Measurement Unit) is used for detection of the time of occurrence of events. The research included 165 individual strikes performed by 14 elite and national-level karate competitors. All strikes were classified as slow, average, or fast based on the achieved maximal velocity of the hand. A Kruskal–Wallis test revealed significant general differences in the order of occurrence of hand acceleration start, maximal hand velocity, maximal body velocity, maximal hand acceleration, maximal body acceleration, and vertical movement onset between the groups. Partial differences were determined using a Mann–Whitney test. This paper determines the differences in the temporal structure of the reverse punch in relation to the achieved maximal velocity of the hand as a performance indicator. Detecting the time of occurrence of events using IMUs is a new method for measuring motion synchronization that provides a new insight into the coordination of articulated human movements. Such application of IMU can provide additional information about the studied structure of rapid discrete movements in various sporting activities that are otherwise imperceptible to human senses.

Chen B. A Data-Driven Approach to Predict Fatigue in Exercise Based on Motion Data from Wearable Sensors or Force Plate

Fatigue increases the risk of injury during sports training and rehabilitation. Early detection of fatigue during exercises would help adapt the training in order to prevent over-training and injury. This study lays the foundation for a data-driven model to automatically predict the onset of fatigue and quantify consequent fatigue changes using a force plate (FP) or inertial measurement units (IMUs). The force plate and body-worn IMUs were used to capture movements associated with exercises (squats, high knee jacks, and corkscrew toe-touch) to estimate participant-specific fatigue levels in a continuous fashion using random forest (RF) regression and convolutional neural network (CNN) based regression models. Analysis of unseen data showed high correlation (up to 89%, 93%, and 94% for the squat, jack, and corkscrew exercises, respectively) between the predicted fatigue levels and self-reported fatigue levels. Predictions using force plate data achieved similar performance as those with IMU data; the best results in both cases were achieved with a convolutional neural network. The displacement of the center of pressure (COP) was found to be correlated with fatigue compared to other commonly used features of the force plate. Bland-Altman analysis also confirmed that the predicted fatigue levels were close to the true values. These results contribute to the field of human motion recognition by proposing a deep neural network model that can detect fairly small changes of motion data in a continuous process and quantify the movement. Based on the successful findings with three different exercises, the general nature of the methodology is potentially applicable to a variety of other forms of exercises, thereby contributing to the future adaptation of exercise programs and prevention of over-training and injury as a result of excessive fatigue.