Stephanie R. Moore

Bio: Stephanie R. Moore is an academic researcher from University of Salzburg. The author has contributed to research in topics: Medicine & Center of pressure (terrestrial locomotion). The author has an hindex of 1, co-authored 7 publications receiving 2 citations.

Foot Strike Angle Prediction and Pattern Classification Using LoadsolTM Wearable Sensors: A Comparison of Machine Learning Techniques

Abstract: The foot strike pattern performed during running is an important variable for runners, performance practitioners, and industry specialists. Versatile, wearable sensors may provide foot strike information while encouraging the collection of diverse information during ecological running. The purpose of the current study was to predict foot strike angle and classify foot strike pattern from LoadsolTM wearable pressure insoles using three machine learning techniques (multiple linear regression-MR, conditional inference tree-TREE, and random forest-FRST). Model performance was assessed using three-dimensional kinematics as a ground-truth measure. The prediction-model accuracy was similar for the regression, inference tree, and random forest models (RMSE: MR = 5.16°, TREE = 4.85°, FRST = 3.65°; MAPE: MR = 0.32°, TREE = 0.45°, FRST = 0.33°), though the regression and random forest models boasted lower maximum precision (13.75° and 14.3°, respectively) than the inference tree (19.02°). The classification performance was above 90% for all models (MR = 90.4%, TREE = 93.9%, and FRST = 94.1%). There was an increased tendency to misclassify mid foot strike patterns in all models, which may be improved with the inclusion of more mid foot steps during model training. Ultimately, wearable pressure insoles in combination with simple machine learning techniques can be used to predict and classify a runner's foot strike with sufficient accuracy.

A Comprehensive Comparison and Validation of Published Methods to Detect Turn Switch during Alpine Skiing.

Abstract: The instant of turn switch (TS) in alpine skiing has been assessed with a variety of sensors and TS concepts. Despite many published methodologies, it is unclear which is best or how comparable they are. This study aimed to facilitate the process of choosing a TS method by evaluating the accuracy and precision of the methodologies previously used in literature and to assess the influence of the sensor type. Optoelectronic motion capture, inertial measurement units, pressure insoles, portable force plates, and electromyography signals were recorded during indoor treadmill skiing. All TS methodologies were replicated as stated in their respective publications. The method proposed by Supej assessed with optoelectronic motion capture was used as a comparison reference. TS time differences between the reference and each methodology were used to assess accuracy and precision. All the methods analyzed showed an accuracy within 0.25 s, and ten of them within 0.05 s. The precision ranged from ~0.10 s to ~0.60 s. The TS methodologies with the best performance (accuracy and precision) were Klous Video, Sporri PI (pressure insoles), Martinez CTD (connected boot), and Yamagiwa IMU (inertial measurement unit). In the future, the specific TS methodology should be chosen with respect to sensor selection, performance, and intended purpose.

Consistency and validity of acute foot-strike pattern alterations during laboratory-based running

Abstract: Due to the limited learning time allotted in most foot strike pattern modification studies, the reliability of pattern alterations may be jeopardized. The purpose of the current study was to investigate the reliability and validity of requested acute alteration of foot strike patterns performed by participants in a laboratory environment. Participants employed a high degree of consistency within foot strike pattern conditions and across the steps within a condition (average within subjects 95% confidence interval = 0.5° 4°). On a group level, participants accurately performed all foot strike conditions with the exception of the midfoot strike pattern. Thus, even with the alteration of foot strike pattern, a generally reliable and valid foot strike angle performance is evidenced.

Influence of footwear, foot-strike pattern and step frequency on spatiotemporal parameters and lower-body stiffness in running.

Abstract: This study aimed to determine the influence of footwear condition, foot-strike pattern and step frequency on running spatiotemporal parameters and lower-body stiffness during treadmill running. Thirty-one amateur endurance runners performed a two-session protocol (shod and barefoot). Each session consisted of two trials at 12 km · h-1 over 5 minutes altering step frequency every minute (150, 160, 170, 180 and 190 spm). First, participants were instructed to land with the heel first; after completion, the same protocol was repeated landing with the forefoot first. Repeated measures ANOVAs showed significant differences for footwear condition, foot-strike pattern and step frequency for each variable: percent contact time, percent flight time, vertical stiffness and leg stiffness (all p < 0.001). The results demonstrate greater estimated vertical and leg stiffness when running barefoot for both foot-strike patterns showing the largest values for barefoot+forefoot condition. Likewise, both vertical and leg stiffness became greater as step frequency increased. The proper manipulation of these variables facilitates our understanding of running performance and assist in training programmes design and injury management.

The modified German subjective vitality scale (SVS-GM): Psychometric properties and application in daily life

Abstract: Subjective vitality describes the positive feeling of experiencing physical and mental energy, which can lead to purposive actions, but no German instruments exist with action-oriented verbiage: This work supports the development and modification of already existing German Subjective Vitality Scales and provides further evidence for its psychometric properties. In a first step (N = 56) two modified (action-oriented) short-forms were developed. An extension of time perspectives (past, present, future) should also enrich the scale by enhancing the accuracy of self-reports. Study 1 (N = 183) then examined the psychometric properties for each time perspective. Study 2 (N = 27) was a 6-day diary study to identify the reliability of within- and between-person differences in vitality over time and working days with responses recorded three times per day. The exploratory factor analysis from study 1 revealed a three-factor solution with three items each. Test-retest reliability was moderate for the past and future time perspective and less stable for state subjective vitality. The modified German Subjective Vitality Scale (SVS-GM) showed divergent validity with fatigue, negative affect, and optimism, and convergent but distinguishable validity with life satisfaction, positive affect, and perceived self-efficacy. High reliability for daily vitality measures (with lower vitality rates in the morning) was found in study 2, but no substantial variation was found between working days and days off. The SVS-GM shows good psychometric properties in different settings and provides researchers with a 3-item (for cross-sectional or longitudinal studies) and 1-item (for short screenings) version to measure subjective vitality in German-speaking populations.

Machine Learning for Healthcare Wearable Devices: The Big Picture

Abstract: Using artificial intelligence and machine learning techniques in healthcare applications has been actively researched over the last few years. It holds promising opportunities as it is used to track human activities and vital signs using wearable devices and assist in diseases' diagnosis, and it can play a great role in elderly care and patient's health monitoring and diagnostics. With the great technological advances in medical sensors and miniaturization of electronic chips in the recent five years, more applications are being researched and developed for wearable devices. Despite the remarkable growth of using smart watches and other wearable devices, a few of these massive research efforts for machine learning applications have found their way to market. In this study, a review of the different areas of the recent machine learning research for healthcare wearable devices is presented. Different challenges facing machine learning applications on wearable devices are discussed. Potential solutions from the literature are presented, and areas open for improvement and further research are highlighted.

Wearables for Running Gait Analysis: A Systematic Review

Abstract: 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.We aimed to systematically review the available literature investigating how wearable technology is being used for running gait analysis in adults.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.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.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.CRD42021235527.

Foot Strike Angle Prediction and Pattern Classification Using LoadsolTM Wearable Sensors: A Comparison of Machine Learning Techniques

Abstract: The foot strike pattern performed during running is an important variable for runners, performance practitioners, and industry specialists. Versatile, wearable sensors may provide foot strike information while encouraging the collection of diverse information during ecological running. The purpose of the current study was to predict foot strike angle and classify foot strike pattern from LoadsolTM wearable pressure insoles using three machine learning techniques (multiple linear regression-MR, conditional inference tree-TREE, and random forest-FRST). Model performance was assessed using three-dimensional kinematics as a ground-truth measure. The prediction-model accuracy was similar for the regression, inference tree, and random forest models (RMSE: MR = 5.16°, TREE = 4.85°, FRST = 3.65°; MAPE: MR = 0.32°, TREE = 0.45°, FRST = 0.33°), though the regression and random forest models boasted lower maximum precision (13.75° and 14.3°, respectively) than the inference tree (19.02°). The classification performance was above 90% for all models (MR = 90.4%, TREE = 93.9%, and FRST = 94.1%). There was an increased tendency to misclassify mid foot strike patterns in all models, which may be improved with the inclusion of more mid foot steps during model training. Ultimately, wearable pressure insoles in combination with simple machine learning techniques can be used to predict and classify a runner's foot strike with sufficient accuracy.

Deep Learning for Walking Behaviour Detection in Elderly People Using Smart Footwear.

Abstract: The increase in the proportion of elderly in Europe brings with it certain challenges that society needs to address, such as custodial care. We propose a scalable, easily modulated and live assistive technology system, based on a comfortable smart footwear capable of detecting walking behaviour, in order to prevent possible health problems in the elderly, facilitating their urban life as independently and safety as possible. This brings with it the challenge of handling the large amounts of data generated, transmitting and pre-processing that information and analysing it with the aim of obtaining useful information in real/near-real time. This is the basis of information theory. This work presents a complete system aiming at elderly people that can detect different user behaviours/events (sitting, standing without imbalance, standing with imbalance, walking, running, tripping) through information acquired from 20 types of sensor measurements (16 piezoelectric pressure sensors, one accelerometer returning reading for the 3 axis and one temperature sensor) and warn the relatives about possible risks in near-real time. For the detection of these events, a hierarchical structure of cascading binary models is designed and applied using artificial neural network (ANN) algorithms and deep learning techniques. The best models are achieved with convolutional layered ANN and multilayer perceptrons. The overall event detection performance achieves an average accuracy and area under the ROC curve of 0.84 and 0.96, respectively.

Estimation of Fine-Grained Foot Strike Patterns with Wearable Smartwatch Devices

Abstract: People who exercise may benefit or be injured depending on their foot striking (FS) style. In this study, we propose an intelligent system that can recognize subtle differences in FS patterns while walking and running using measurements from a wearable smartwatch device. Although such patterns could be directly measured utilizing pressure distribution of feet while striking on the ground, we instead focused on analyzing hand movements by assuming that striking patterns consequently affect temporal movements of the whole body. The advantage of the proposed approach is that FS patterns can be estimated in a portable and less invasive manner. To this end, first, we developed a wearable system for measuring inertial movements of hands and then conducted an experiment where participants were asked to walk and run while wearing a smartwatch. Second, we trained and tested the captured multivariate time series signals in supervised learning settings. The experimental results obtained demonstrated high and robust classification performances (weighted-average F1 score > 90%) when recent deep neural network models, such as 1D-CNN and GRUs, were employed. We conclude this study with a discussion of potential future work and applications that increase benefits while walking and running properly using the proposed approach.