Drift-Free Foot Orientation Estimation in Running Using Wearable IMU

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.

Predicting overstriding with wearable IMUs during treadmill and overground running

Running injuries are prevalent, but their exact mechanisms remain unknown largely due to limited real-world biomechanical analysis. Reducing overstriding, the horizontal distance that the foot lands ahead of the body, may be relevant to reducing injury risk. Here, we leverage the geometric relationship between overstriding and lower extremity sagittal segment angles to demonstrate that wearable inertial measurement units (IMUs) can predict overstriding during treadmill and overground running in the laboratory. Ten recreational runners matched their strides to a metronome to systematically vary overstriding during constant-speed treadmill running and showed similar overstriding variation during comfortable-speed overground running. Linear mixed models were used to analyze repeated measures of overstriding and sagittal segment angles measured with motion capture and IMUs. Sagittal segment angles measured with IMUs explained 95% and 98% of the variance in overstriding during treadmill and overground running, respectively. We also found that sagittal segment angles measured with IMUs correlated with peak braking force and explained 88% and 80% of the variance during treadmill and overground running, respectively. This study highlights the potential for IMUs to provide insights into landing and loading patterns over time in real-world running environments, and motivates future research on feedback to modify form and prevent injury.

Can inertial measurement unit sensors evaluate foot kinematics in drop foot patients using functional electrical stimulation?

The accuracy of inertial measurement units (IMUs) in measuring foot motion in the sagittal plane has been previously compared to motion capture systems for healthy and impaired participants. Studies analyzing the accuracy of IMUs in measuring foot motion in the frontal plane are lacking. Drop foot patients use functional electrical stimulation (FES) to improve walking and reduce the risk of tripping and falling by improving foot dorsiflexion and inversion-eversion. Therefore, this study aims to evaluate if IMUs can estimate foot angles in the frontal and sagittal planes to help understand the effects of FES on drop foot patients in clinical settings. Two Gait Up sensors were used to estimate foot dorsi-plantar flexion and inversion-eversion angles in 13 unimpaired participants and 9 participants affected by drop foot while walking 6 m in a straight line. Unimpaired participants were asked to walk normally at three self-selected speeds and to simulate drop foot. Impaired participants walked with and without FES assistance. Foot angles estimated by the IMUs were compared with those measured from a motion capture system using curve RMSE and Bland Altman limits of agreement. Between participant groups, overall errors of 7.95° ± 3.98°, -1.12° ± 4.20°, and 1.38° ± 5.05° were obtained for the dorsi-plantar flexion range of motion, dorsi-plantar flexion at heel strike, and inversion-eversion at heel strike, respectively. The between-system comparison of their ability to detect dorsi-plantar flexion and inversion-eversion differences associated with FES use on drop foot patients provided limits of agreement too large for IMUs to be able to accurately detect the changes in foot kinematics following FES intervention. To the best of the authors' knowledge, this is the first study to evaluate IMU accuracy in the estimation of foot inversion-eversion and analyze the potential of using IMUs in clinical settings to assess gait for drop foot patients and evaluate the effects of FES. From the results, it can be concluded that IMUs do not currently represent an alternative to motion capture to evaluate foot kinematics in drop foot patients using FES.

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.

Automatic Body Segment and Side Recognition of an Inertial Measurement Unit Sensor during Gait

Inertial measurement unit (IMU) sensors are widely used for motion analysis in sports and rehabilitation. The attachment of IMU sensors to predefined body segments and sides (left/right) is complex, time-consuming, and error-prone. Methods for solving the IMU-2-segment (I2S) pairing work properly only for a limited range of gait speeds or require a similar sensor configuration. Our goal was to propose an algorithm that works over a wide range of gait speeds with different sensor configurations while being robust to footwear type and generalizable to pathologic gait patterns. Eight IMU sensors were attached to both feet, shanks, thighs, sacrum, and trunk, and 12 healthy subjects (training dataset) and 22 patients (test dataset) with medial compartment knee osteoarthritis walked at different speeds with/without insole. First, the mean stride time was estimated and IMU signals were scaled. Using a decision tree, the body segment was recognized, followed by the side of the lower limb sensor. The accuracy and precision of the whole algorithm were 99.7% and 99.0%, respectively, for gait speeds ranging from 0.5 to 2.2 m/s. In conclusion, the proposed algorithm was robust to gait speed and footwear type and can be widely used for different sensor configurations.

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

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

Wearables for Running Gait Analysis: A Systematic Review

BACKGROUND

Running gait assessment has traditionally been performed using subjective observation or expensive laboratory-based objective technologies, such as three-dimensional motion capture or force plates. However, recent developments in wearable devices allow for continuous monitoring and analysis of running mechanics in any environment. Objective measurement of running gait is an important (clinical) tool for injury assessment and provides measures that can be used to enhance performance.

OBJECTIVES

We aimed to systematically review the available literature investigating how wearable technology is being used for running gait analysis in adults.

METHODS

A systematic search of the literature was conducted in the following scientific databases: PubMed, Scopus, Web of Science and SPORTDiscus. Information was extracted from each included article regarding the type of study, participants, protocol, wearable device(s), main outcomes/measures, analysis and key findings.

RESULTS

A total of 131 articles were reviewed: 56 investigated the validity of wearable technology, 22 examined the reliability and 77 focused on applied use. Most studies used inertial measurement units (n = 62) [i.e. a combination of accelerometers, gyroscopes and magnetometers in a single unit] or solely accelerometers (n = 40), with one using gyroscopes alone and 31 using pressure sensors. On average, studies used one wearable device to examine running gait. Wearable locations were distributed among the shank, shoe and waist. The mean number of participants was 26 (± 27), with an average age of 28.3 (± 7.0) years. Most studies took place indoors (n = 93), using a treadmill (n = 62), with the main aims seeking to identify running gait outcomes or investigate the effects of injury, fatigue, intrinsic factors (e.g. age, sex, morphology) or footwear on running gait outcomes. Generally, wearables were found to be valid and reliable tools for assessing running gait compared to reference standards.

CONCLUSIONS

This comprehensive review highlighted that most studies that have examined running gait using wearable sensors have done so with young adult recreational runners, using one inertial measurement unit sensor, with participants running on a treadmill and reporting outcomes of ground contact time, stride length, stride frequency and tibial acceleration. Future studies are required to obtain consensus regarding terminology, protocols for testing validity and the reliability of devices and suitability of gait outcomes.

CLINICAL TRIAL REGISTRATION

CRD42021235527.

Augmented Cooper test: Biomechanical contributions to endurance performance

Running mechanics are modifiable with training and adopting an economical running technique can improve running economy and hence performance. While field measurement of running economy is cumbersome, running mechanics can be assessed accurately and conveniently using wearable inertial measurement units (IMUs). In this work, we extended this wearables-based approach to the Cooper test, by assessing the relative contribution of running biomechanics to the endurance performance. Furthermore, we explored different methods of estimating the distance covered in the Cooper test using a wearable global navigation satellite system (GNSS) receiver. Thirty-three runners (18 highly trained and 15 recreational) performed an incremental laboratory treadmill test to measure their maximum aerobic speed (MAS) and speed at the second ventilatory threshold (sVT2). They completed a 12-minute Cooper running test with foot-worm IMUs and a chest-worn GNSS-IMU on a running track 1–2 weeks later. Using the GNSS receiver, an accurate estimation of the 12-minute distance was obtained (accuracy of 16.5 m and precision of 1.1%). Using this distance, we showed a reliable estimation [R² > 0.9, RMSE ϵ (0.07, 0.25) km/h] of the MAS and sVT2. Biomechanical metrics were extracted using validated algorithm and their association with endurance performance was estimated. Additionally, the high-/low-performance runners were compared using pairwise statistical testing. All performance variables, MAS, sVT2, and average speed during Cooper test, were predicted with an acceptable error (R² ≥ 0.65, RMSE ≤ 1.80 kmh⁻¹) using only the biomechanical metrics. The most relevant metrics were used to develop a biomechanical profile representing the running technique and its temporal evolution with acute fatigue, identifying different profiles for runners with highest and lowest endurance performance. This profile could potentially be used in standardized functional capacity measurements to improve personalization of training and rehabilitation programs.

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.

Concurrent Evolution of Biomechanical and Physiological Parameters With Running-Induced Acute Fatigue

Understanding the influence of running-induced acute fatigue on the homeostasis of the body is essential to mitigate the adverse effects and optimize positive adaptations to training. Fatigue is a multifactorial phenomenon, which influences biomechanical, physiological, and psychological facets. This work aimed to assess the evolution of these three facets with acute fatigue during a half-marathon. 13 recreational runners were equipped with one inertial measurement unit (IMU) on each foot, one combined global navigation satellite system-IMU-electrocardiogram sensor on the chest, and an Android smartphone equipped with an audio recording application. Spatio-temporal parameters for the running gait, along with the heart rate, its variability and complexity were computed using validated algorithms. Perceived fatigability was assessed using the rating-of-fatigue (ROF) scale at every 10 min of the race. The data was split into eight equal segments, corresponding to at least one ROF value per segment, and only level running parts were retained for analysis. During the race, contact time, duty factor, and trunk anteroposterior acceleration increased, and the foot strike angle and vertical stiffness decreased significantly. Heart rate showed a progressive increase, while the metrics for heart rate variability and complexity decreased during the race. The biomechanical parameters showed a significant alteration even with a small change in perceived fatigue, whereas the heart rate dynamics altered at higher changes. When divided into two groups, the slower runners presented a higher change in heart rate dynamics throughout the race than the faster runners; they both showed similar trends for the gait parameters. When tested for linear and non-linear correlations, heart rate had the highest association with biomechanical parameters, while the trunk anteroposterior acceleration had the lowest association with heart rate dynamics. These results indicate the ability of faster runners to better judge their physiological limits and hint toward a higher sensitivity of perceived fatigue to neuromuscular changes in the running gait. This study highlights measurable influences of acute fatigue, which can be studied only through concurrent measurement of biomechanical, physiological, and psychological facets of running in real-world conditions.

Drift-Free 3D Orientation and Displacement Estimation for Quasi-Cyclical Movements Using One Inertial Measurement Unit: Application to Running

A Drift-Free 3D Orientation and Displacement estimation method (DFOD) based on a single inertial measurement unit (IMU) is proposed and validated. Typically, body segment orientation and displacement methods rely on a constant- or zero-velocity point to correct for drift. Therefore, they are not easily applicable to more proximal segments than the foot. DFOD uses an alternative single sensor drift reduction strategy based on the quasi-cyclical nature of many human movements. DFOD assumes that the quasi-cyclical movement occurs in a quasi-2D plane and with an approximately constant cycle average velocity. DFOD is independent of a constant- or zero-velocity point, a biomechanical model, Kalman filtering or a magnetometer. DFOD reduces orientation drift by assuming a cyclical movement, and by defining a functional coordinate system with two functional axes. These axes are based on the mean acceleration and rotation axes over multiple complete gait cycles. Using this drift-free orientation estimate, the displacement of the sensor is computed by again assuming a cyclical movement. Drift in displacement is reduced by subtracting the mean value over five gait cycle from the free acceleration, velocity, and displacement. Estimated 3D sensor orientation and displacement for an IMU on the lower leg were validated with an optical motion capture system (OMCS) in four runners during constant velocity treadmill running. Root mean square errors for sensor orientation differences between DFOD and OMCS were 3.1 ± 0.4° (sagittal plane), 5.3 ± 1.1° (frontal plane), and 5.0 ± 2.1° (transversal plane). Sensor displacement differences had a root mean square error of 1.6 ± 0.2 cm (forward axis), 1.7 ± 0.6 cm (mediolateral axis), and 1.6 ± 0.2 cm (vertical axis). Hence, DFOD is a promising 3D drift-free orientation and displacement estimation method based on a single IMU in quasi-cyclical movements with many advantages over current methods.

A Single Sacral-Mounted Inertial Measurement Unit to Estimate Peak Vertical Ground Reaction Force, Contact Time, and Flight Time in Running

Peak vertical ground reaction force (Fz,max), contact time (tc), and flight time (tf) are key variables of running biomechanics. The gold standard method (GSM) to measure these variables is a force plate. However, a force plate is not always at hand and not very portable overground. In such situation, the vertical acceleration signal recorded by an inertial measurement unit (IMU) might be used to estimate Fz,max, tc, and tf. Hence, the first purpose of this study was to propose a method that used data recorded by a single sacral-mounted IMU (IMU method: IMUM) to estimate Fz,max. The second aim of this study was to estimate tc and tf using the same IMU data. The vertical acceleration threshold of an already existing IMUM was modified to detect foot-strike and toe-off events instead of effective foot-strike and toe-off events. Thus, tc and tf estimations were obtained instead of effective contact and flight time estimations. One hundred runners ran at 9, 11, and 13 km/h. IMU data (208 Hz) and force data (200 Hz) were acquired by a sacral-mounted IMU and an instrumented treadmill, respectively. The errors obtained when comparing Fz,max, tc, and tf estimated using the IMUM to Fz,max, tc, and tf measured using the GSM were comparable to the errors obtained using previously published methods. In fact, a root mean square error (RMSE) of 0.15 BW (6%) was obtained for Fz,max while a RMSE of 20 ms was reported for both tc and tf (8% and 18%, respectively). Moreover, even though small systematic biases of 0.07 BW for Fz,max and 13 ms for tc and tf were reported, the RMSEs were smaller than the smallest real differences [Fz,max: 0.28 BW (11%), tc: 32.0 ms (13%), and tf: 32.0 ms (30%)], indicating no clinically important difference between the GSM and IMUM. Therefore, these results support the use of the IMUM to estimate Fz,max, tc, and tf for level treadmill runs at low running speeds, especially because an IMU has the advantage to be low-cost and portable and therefore seems very practical for coaches and healthcare professionals.

A Multivariate Polynomial Regression to Reconstruct Ground Contact and Flight Times Based on a Sine Wave Model for Vertical Ground Reaction Force and Measured Effective Timings

Effective contact (tce) and flight (tfe) times, instead of ground contact (tc) and flight (tf) times, are usually collected outside the laboratory using inertial sensors. Unfortunately, tce and tfe cannot be related to tc and tf because the exact shape of vertical ground reaction force is unknown. However, using a sine wave approximation for vertical force, tce and tc as well as tfe and tf could be related. Indeed, under this approximation, a transcendental equation was obtained and solved numerically over a tce x tfe grid. Then, a multivariate polynomial regression was applied to the numerical outcome. In order to reach a root-mean-square error of 0.5 ms, the final model was given by an eighth-order polynomial. As a direct application, this model was applied to experimentally measured tce values. Then, reconstructed tc (using the model) was compared to corresponding experimental ground truth. A systematic bias of 35 ms was depicted, demonstrating that ground truth tc values were larger than reconstructed ones. Nonetheless, error in the reconstruction of tc from tce was coming from the sine wave approximation, while the polynomial regression did not introduce further error. The presented model could be added to algorithms within sports watches to provide robust estimations of tc and tf in real time, which would allow coaches and practitioners to better evaluate running performance and to prevent running-related injuries.

Validation of an inertial-based contact and swing time algorithm for running analysis from a foot mounted IoT enabled wearable

Running gait assessment for shoe type recommendation to avoid injury often takes place within commercial premises. That is not representative of a natural running environment and may influence normal/usual running characteristics. Typically, assessments are costly and performed by an untrained biomechanist or physiotherapist. Thus, use of a low-cost assessment of running gait to recommend shoe type is warranted. Indeed, the recent impact of COVID has heightened the need for a shift toward remote assessment in general due to social-distancing guidelines and restriction of movement to bespoke assessment facilities. Mymo is a Bluetooth-enabled, inertial measurement unit (IMU) wearable worn on the foot. The wearable transmits inertial data via a smartphone application to the Cloud, where algorithms work to recommend a running shoe based upon the users/runner's pronation and foot-strike location/pattern. Here, an additional algorithm is presented to quantify ground contact time and swing/flight time within the Mymo platform to further inform the assessment of a runner's gait. A large cohort of healthy adult and adolescents (n=203, 91M:112F) were recruited to run on a treadmill while wearing the Mymo wearable. Validity of the inertial-based algorithm to quantify ground contact time was established through manual labelling of reference standard ground truth video data, with a presented accuracy between 96.6-98.7% across the two classes with respect to each foot.Clinical Relevance-This establishes the validity of a ground contact and swing times for runner with a low-cost IoT wearable.

Estimating effective contact and flight times using a sacral-mounted inertial measurement unit

Effective ground contact (t_ce) and flight (t_fe) times were proven to be more appropriate to decipher the landing-take-off asymmetry of running than usual ground contact (t_c) and flight (t_f) times. To measure these effective timings, force plate is the gold standard method (GSM), though not very portable overground. In such situation, alternatives could be to use portable tools such as inertial measurement unit (IMU). Therefore, the purpose of this study was to propose a method that uses the vertical acceleration recorded using a sacral-mounted IMU to estimate t_ce and t_fe and to compare these estimations to those from GSM. Besides, t_ce and t_fe were used to evaluate the landing-take-off asymmetry, which was further compared to GSM. One hundred runners ran at 9, 11, and 13 km/h. Force data (200 Hz) and IMU data (208 Hz) were acquired by an instrumented treadmill and a sacral-mounted IMU, respectively. The comparison between GSM and IMU method depicted root mean square error ≤22 ms (≤14%) for t_ce and t_fe along with small systematic biases (≤20 ms) for each tested speed. These errors are similar to previously published methods that estimated usual t_c and t_f. The systematic biases on t_ce and t_fe were subtracted before calculating the landing-take-off asymmetry, which permitted to correctly evaluate it at a group level. Therefore, the findings of this study support the use of this method based on vertical acceleration recorded using a sacral-mounted IMU to estimate t_ce and t_fe for level treadmill runs and to evaluate the landing-take-off asymmetry but only after subtraction of systematic biases and at a group level.

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.

Continuous Analysis of Marathon Running Using Inertial Sensors: Hitting Two Walls?

Marathon running involves complex mechanisms that cannot be measured with objective metrics or laboratory equipment. The emergence of wearable sensors introduced new opportunities, allowing the continuous recording of relevant parameters. The present study aimed to assess the evolution of stride-by-stride spatio-temporal parameters, stiffness, and foot strike angle during a marathon and determine possible abrupt changes in running patterns. Twelve recreational runners were equipped with a Global Navigation Satellite System watch, and two inertial measurement units clamped on each foot during a marathon race. Data were split into eight 5-km sections and only level parts were analyzed. We observed gradual increases in contact time and duty factor as well as decreases in flight time, swing time, stride length, speed, maximal vertical force and stiffness during the race. Surprisingly, the average foot strike angle decreased during the race, but each participant maintained a rearfoot strike until the end. Two abrupt changes were also detected around km 25 and km 35. These two breaks are possibly due to the alteration of the stretch-shortening cycle combined with physiological limits. This study highlights new measurable phenomena that can only be analyzed through continuous monitoring of runners over a long period of time.

Classification of Cross-Country Ski Skating Sub-Technique Can Be Automated Using Carrier-Phase Differential GNSS Measurements of the Head's Position

Position–time tracking of athletes during a race can provide useful information about tactics and performance. However, carrier-phase differential global navigation satellite system (dGNSS)-based tracking, which is accurate to about 5 cm, might also allow for the extraction of variables reflecting an athlete’s technique. Such variables include cycle length, cycle frequency, and choice of sub-technique. The aim of this study was to develop a dGNSS-based method for automated determination of sub-technique and cycle characteristics in cross-country ski skating. Sub-technique classification was achieved using a combination of hard decision rules and a neural network classifier (NNC) on position measurements from a head-mounted dGNSS antenna. The NNC was trained to classify the three main sub-techniques (G2–G4) using optical marker motion data of the head trajectory of six subjects during treadmill skiing. Hard decision rules, based on the head’s sideways and vertical movement, were used to identify phases of turning, tucked position and G5 (skating without poles). Cycle length and duration were derived from the components of the head velocity vector. The classifier’s performance was evaluated on two subjects during an in-field roller skiing test race by comparison with manual classification from video recordings. Classification accuracy was 92–97% for G2–G4, 32% for G5, 75% for turning, and 88% for tucked position. Cycle duration and cycle length had a root mean square (RMS) deviation of 2–3%, which was reduced to <1% when cycle duration and length were averaged over five cycles. In conclusion, accurate dGNSS measurements of the head’s trajectory during cross-country skiing contain sufficient information to classify the three main skating sub-techniques and characterize cycle length and duration.

Running Speed Estimation Using Shoe-Worn Inertial Sensors: Direct Integration, Linear, and Personalized Model

The overground speed is a key component of running analysis. Today, most speed estimation wearable systems are based on GNSS technology. However, these devices can suffer from sparse communication with the satellites and have a high-power consumption. In this study, we propose three different approaches to estimate the overground speed in running based on foot-worn inertial sensors and compare the results against a reference GNSS system. First, a method is proposed by direct strapdown integration of the foot acceleration. Second, a feature-based linear model and finally a personalized online-model based on the recursive least squares' method were devised. We also evaluated the performance differences between two sets of features; one automatically selected set (i.e., optimized) and a set of features based on the existing literature. The data set of this study was recorded in a real-world setting, with 33 healthy individuals running at low, preferred, and high speed. The direct estimation of the running speed achieved an inter-subject mean ± STD accuracy of 0.08 ± 0.1 m/s and a precision of 0.16 ± 0.04 m/s. In comparison, the best feature-based linear model achieved 0.00 ± 0.11 m/s accuracy and 0.11 ± 0.05 m/s precision, while the personalized model obtained a 0.00 ± 0.01 m/s accuracy and 0.09 ± 0.06 m/s precision. The results of this study suggest that (1) the direct estimation of the velocity of the foot are biased, and the error is affected by the overground velocity and the slope; (2) the main limitation of a general linear model is the relatively high inter-subject variance of the bias, which reflects the intrinsic differences in gait patterns among individuals; (3) this inter-subject variance can be nulled using a personalized model.

Does the Position of Foot-Mounted IMU Sensors Influence the Accuracy of Spatio-Temporal Parameters in Endurance Running?

Wearable sensor technology already has a great impact on the endurance running community. Smartwatches and heart rate monitors are heavily used to evaluate runners' performance and monitor their training progress. Additionally, foot-mounted inertial measurement units (IMUs) have drawn the attention of sport scientists due to the possibility to monitor biomechanically relevant spatio-temporal parameters outside the lab in real-world environments. Researchers developed and investigated algorithms to extract various features using IMU data of different sensor positions on the foot. In this work, we evaluate whether the sensor position of IMUs mounted to running shoes has an impact on the accuracy of different spatio-temporal parameters. We compare both the raw data of the IMUs at different sensor positions as well as the accuracy of six endurance running-related parameters. We contribute a study with 29 subjects wearing running shoes equipped with four IMUs on both the left and the right shoes and a motion capture system as ground truth. The results show that the IMUs measure different raw data depending on their position on the foot and that the accuracy of the spatio-temporal parameters depends on the sensor position. We recommend to integrate IMU sensors in a cavity in the sole of a running shoe under the foot's arch, because the raw data of this sensor position is best suitable for the reconstruction of the foot trajectory during a stride.

A Practical Sensor-Based Methodology for the Quantitative Assessment and Classification of Chronic Non Specific Low Back Patients (NSLBP) in Clinical Settings

The successful clinical application of patient-specific personalized medicine for the management of low back patients remains elusive. This study aimed to classify chronic nonspecific low back pain (NSLBP) patients using our previously developed and validated wearable inertial sensor (SHARIF-HMIS) for the assessment of trunk kinematic parameters. One hundred NSLBP patients consented to perform repetitive flexural movements in five different planes of motion (PLM): 0° in the sagittal plane, as well as 15° and 30° lateral rotation to the right and left, respectively. They were divided into three subgroups based on the STarT Back Screening Tool. The sensor was placed on the trunk of each patient. An ANOVA mixed model was conducted on the maximum and average angular velocity, linear acceleration and maximum jerk, respectively. The effect of the three-way interaction of Subgroup by direction by PLM on the mean trunk acceleration was significant. Subgrouping by STarT had no main effect on the kinematic indices in the sagittal plane, although significant effects were observed in the asymmetric directions. A significant difference was also identified during pre-rotation in the transverse plane, where the velocity and acceleration decreased while the jerk increased with increasing asymmetry. The acceleration during trunk flexion was significantly higher than that during extension, in contrast to the velocity, which was higher in extension. A Linear Discriminant Analysis, utilized for classification purposes, demonstrated that 51% of the total performance classifying the three STarT subgroups (65% for high risk) occurred at a position of 15° of rotation to the right during extension. Greater discrimination (67%) was obtained in the classification of the high risk vs. low-medium risk. This study provided a smart "sensor-based" practical methodology for quantitatively assessing and classifying NSLBP patients in clinical settings. The outcomes may also be utilized by leveraging cost-effective inertial sensors, already available in today's smartphones, as objective tools for various health applications towards personalized precision medicine.