Rehabilitation and motion symmetry analysis with a TACX smart cycling trainer using computational intelligence

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F25%3A63597698" target="_blank" >RIV/70883521:28140/25:63597698 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/25:00388069 RIV/60461373:22340/25:43932959

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/11036716" target="_blank" >https://ieeexplore.ieee.org/document/11036716</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ACCESS.2025.3579804" target="_blank" >10.1109/ACCESS.2025.3579804</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Rehabilitation and motion symmetry analysis with a TACX smart cycling trainer using computational intelligence

Popis výsledku v původním jazyce

Motion analysis provides important information in rehabilitation, performance evaluation, and movement symmetry assessment, with applications including neurology, biomedicine, surgery, and sports monitoring. The integration of virtual reality, wearable sensors, and signal processing forms a robust interdisciplinary platform for such analysis. Specific methods are based on monitoring physiological and motion responses during controlled exercises that simulate real-world motion scenarios. This study focuses on processing of signals from wearable sensors collected from smart indoor trainers, enabling motion monitoring under predefined load conditions. The acquired datasets include heart rate (HR), motion accelerometric and gyrometric signals, and fitness parameters (cycling speed). The research objectives include analysis of motion patterns, evaluation of motion symmetry under varying loads, and examination of heart rate responses to load variations. Signal processing is conducted using advanced methods that include computational intelligence, digital signal processing, and artificial intelligence tools for data classification. Results point to the mean delay of the HR drop to 97% of the HR range in 15s after the change from the cycling on the slope of 8% to the rest period and the following drop to 5% in next 54s. The classification of spectral features evaluated separately for the left and right legs pointed the classification accuracy of 94.5% for accelerometric data and 99.1% for gyrometric data estimated by the use of the two layer neural network and the symmetry coefficient of 1.05 for the slope of 8%. In general, the paper presents selected processing methods and experimental results pointing to the effectiveness of computational intelligence in motion analysis.

Název v anglickém jazyce

Rehabilitation and motion symmetry analysis with a TACX smart cycling trainer using computational intelligence

Popis výsledku anglicky

Motion analysis provides important information in rehabilitation, performance evaluation, and movement symmetry assessment, with applications including neurology, biomedicine, surgery, and sports monitoring. The integration of virtual reality, wearable sensors, and signal processing forms a robust interdisciplinary platform for such analysis. Specific methods are based on monitoring physiological and motion responses during controlled exercises that simulate real-world motion scenarios. This study focuses on processing of signals from wearable sensors collected from smart indoor trainers, enabling motion monitoring under predefined load conditions. The acquired datasets include heart rate (HR), motion accelerometric and gyrometric signals, and fitness parameters (cycling speed). The research objectives include analysis of motion patterns, evaluation of motion symmetry under varying loads, and examination of heart rate responses to load variations. Signal processing is conducted using advanced methods that include computational intelligence, digital signal processing, and artificial intelligence tools for data classification. Results point to the mean delay of the HR drop to 97% of the HR range in 15s after the change from the cycling on the slope of 8% to the rest period and the following drop to 5% in next 54s. The classification of spectral features evaluated separately for the left and right legs pointed the classification accuracy of 94.5% for accelerometric data and 99.1% for gyrometric data estimated by the use of the two layer neural network and the symmetry coefficient of 1.05 for the slope of 8%. In general, the paper presents selected processing methods and experimental results pointing to the effectiveness of computational intelligence in motion analysis.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotika a pokročilá průmyslová výroba</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Access

ISSN

2169-3536

e-ISSN

2169-3536

Svazek periodika

13

Číslo periodika v rámci svazku

Neuveden

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

12

Strana od-do

113495-113501

Kód UT WoS článku

001522922600012

EID výsledku v databázi Scopus

2-s2.0-105008657514