Is machine learning and automatic classification of swimming data what unlocks the power of inertial measurement units in swimming?
Researchers have heralded the power of inertial sensors as a reliable swimmer-centric monitoring technology, however, regular uptake of this technology has not become common practice. Twenty-six elite swimmers participated in this study. An IMU (100Hz/500Hz) sensor was secured in the participant's t...
| Publicado en: | Journal of Sports Sciences Vol. 39; no. 18; pp. 2095 - 2115 |
|---|---|
| Autores principales: | , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
Taylor & Francis Ltd
Sep2021
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=152538584&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 152538584 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 02640414 5BV jtl: Journal of Sports Sciences issn: 02640414 maglogo: Y pubinfo: dt: Sep2021 vid: 39 iid: 18 pid: 377 pub: Taylor & Francis Ltd place: Philadelphia, Pennsylvania artinfo: ui: 152538584 150202887 152538584 152538584 10.1080/02640414.2021.1918432 152538584 ppf: 2095 ppct: 20 formats: tig: atl: Is machine learning and automatic classification of swimming data what unlocks the power of inertial measurement units in swimming? aug: au: Worsey, Matthew T.O. Pahl, Rebecca Espinosa, Hugo G. Shepherd, Jonathan B. Thiel, David V. affil: Griffith University Sports Technology (GUST), School of Engineering and Built Environment, Griffith University, Brisbane, QLD Australia sug: subj: Machine Learning Swimming Physiology Wearable Sensors Athletes, Elite Monitoring, Physiologic Human Algorithms Descriptive Statistics Data Analysis Software Mann-Whitney U Test ab: Researchers have heralded the power of inertial sensors as a reliable swimmer-centric monitoring technology, however, regular uptake of this technology has not become common practice. Twenty-six elite swimmers participated in this study. An IMU (100Hz/500Hz) sensor was secured in the participant's third lumbar vertebrae. Features were extracted from swimming data using two techniques: a novel intrastroke cycle segmentation technique and conventional sliding window technique. Six supervised machine learning models were assessed on stroke prediction performance. Models trained using both feature extraction methods demonstrated high performance (≥ 0.99 weighted average precision, recall, F1-score, area under ROC curve and accuracy), low computational training times (< 3 seconds – bar XGB and when hyperparameters were tuned) and low computational prediction times (< 1 second). Significant differences were observed in weighted average stroke prediction F1-score (p = 0.0294) when using different feature extraction methods and model computational training time (p = 0.0007), and prediction time (p = 0.0026) when implementing hyperparameter tuning. Automatic swimming stroke classification offers benefits to observational coding and notational analysis, and opportunities for automated workload and performance monitoring in swimming. This stroke classification algorithm could be the key that unlocks the power of IMUs as a biofeedback tool in swimming. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|