sEMG Onset Detection Via Bidirectional Recurrent Neural Networks With Applications to Sports Science

TY - JOUR

T1 - sEMG Onset Detection Via Bidirectional Recurrent Neural Networks With Applications to Sports Science

AU - Ergeneci, Mert

AU - Carter, Daryl

AU - Kosmas, Panagiotis

N1 - Publisher Copyright: IEEE

PY - 2022/10/1

Y1 - 2022/10/1

N2 - Surface electromyography (sEMG) provides physiological information that can be used in sports science. In many applications, sEMG signal activity, i.e., contractions, needs to be detected in the stream of sensor recordings. During sports exercises, the impact of any collision on the body due to an athlete's movement (e.g., jump) forms an additive noise called motion-induced artifact (MIA) in sEMG recordings. This study proposes a bidirectional long short-term memory recurrent neural network (BLSTM-RNN) to automatically identify sEMG signal activity in measurements that include MIA. The proposed model is compared with the state-of-the-art techniques that are envelope, sample entropy (SampEn), modified adaptive linear energy detector (M-ALED), and adaptive contraction detection (ACD). As hamstring strain injuries (HSIs) are the most frequent and recurring injuries in professional football, this article uses sEMG data of different hamstring exercises performed by first-team players of the Leeds United Football Club. On data recorded using state-of-the-art sensors, the classification accuracy of the proposed solution is 96.73%, while the other methods reach 61.41% (sEMG envelope), 84.95% (SampEn), 58.86% (M-ALED), and 65.54% (ACD).

AB - Surface electromyography (sEMG) provides physiological information that can be used in sports science. In many applications, sEMG signal activity, i.e., contractions, needs to be detected in the stream of sensor recordings. During sports exercises, the impact of any collision on the body due to an athlete's movement (e.g., jump) forms an additive noise called motion-induced artifact (MIA) in sEMG recordings. This study proposes a bidirectional long short-term memory recurrent neural network (BLSTM-RNN) to automatically identify sEMG signal activity in measurements that include MIA. The proposed model is compared with the state-of-the-art techniques that are envelope, sample entropy (SampEn), modified adaptive linear energy detector (M-ALED), and adaptive contraction detection (ACD). As hamstring strain injuries (HSIs) are the most frequent and recurring injuries in professional football, this article uses sEMG data of different hamstring exercises performed by first-team players of the Leeds United Football Club. On data recorded using state-of-the-art sensors, the classification accuracy of the proposed solution is 96.73%, while the other methods reach 61.41% (sEMG envelope), 84.95% (SampEn), 58.86% (M-ALED), and 65.54% (ACD).

KW - artefact

KW - Contraction Detection

KW - Data models

KW - Entropy

KW - Hamstring Strain Injury

KW - Injuries

KW - Injury Prevention

KW - Motion Induced Noise

KW - Muscles

KW - Neural Networks

KW - Onset Detection

KW - Recording

KW - Sensors

KW - Sports

KW - Sports Science

KW - Surface Electromyography

KW - Temporal Learning

UR - http://www.scopus.com/inward/record.url?scp=85136864242&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2022.3198882

DO - 10.1109/JSEN.2022.3198882

M3 - Article

AN - SCOPUS:85136864242

SN - 1530-437X

VL - 22

SP - 18751

EP - 18761

JO - IEEE SENSORS JOURNAL

JF - IEEE SENSORS JOURNAL

IS - 19

ER -