TY - GEN
T1 - Improving Exertion and Wellbeing Prediction in Outdoor Running Conditions using Audio-based Surface Recognition
AU - Gebhard, Alexander
AU - Triantafyllopoulos, Andreas
AU - Amiriparian, Shahin
AU - Ottl, Sandra
AU - Dieter, Valerie
AU - Gerczuk, Maurice
AU - Jaumann, Mirko
AU - Hildner, David
AU - Schneeweiß, Patrick
AU - Rösel, Inka
AU - Krauß, Inga
AU - Schuller, Björn W.
N1 - Publisher Copyright:
© 2022 ACM.
PY - 2022/10/14
Y1 - 2022/10/14
N2 - Timely detection of runner exertion is crucial for preventing overuse injuries and conditioning training. Similarly, maintaining high levels of wellbeing while running can improve retention rates for onboarders to the sport, with the associated benefits to public health that this entails. Thus, predicting exertion and wellbeing is a promising avenue of research for biomedical sports research. Previous work has shown that exertion and wellbeing can be predicted using biomechanical data collected from wearables attached to the runners' body. However, a particular challenge in outdoor running conditions is the mediating effect of running surface. We experimentally model this mediating effect by using surface-Adapted models, which improve prediction rates for both variables. To that end, we investigate the feasibility of using audio-based surface classification to distinguish three main surface categories: gravel, asphalt, and dirt. Our best models achieve an unweighted average recall (UAR) of .619 and a UAR of .690 on our session-independent and session-dependent test set, respectively, which is an improvement over the .363 UAR achieved by a GPS-based approximation.
AB - Timely detection of runner exertion is crucial for preventing overuse injuries and conditioning training. Similarly, maintaining high levels of wellbeing while running can improve retention rates for onboarders to the sport, with the associated benefits to public health that this entails. Thus, predicting exertion and wellbeing is a promising avenue of research for biomedical sports research. Previous work has shown that exertion and wellbeing can be predicted using biomechanical data collected from wearables attached to the runners' body. However, a particular challenge in outdoor running conditions is the mediating effect of running surface. We experimentally model this mediating effect by using surface-Adapted models, which improve prediction rates for both variables. To that end, we investigate the feasibility of using audio-based surface classification to distinguish three main surface categories: gravel, asphalt, and dirt. Our best models achieve an unweighted average recall (UAR) of .619 and a UAR of .690 on our session-independent and session-dependent test set, respectively, which is an improvement over the .363 UAR achieved by a GPS-based approximation.
KW - computer audition
KW - neural networks
KW - outdoor running
KW - surface classification
UR - http://www.scopus.com/inward/record.url?scp=85141376737&partnerID=8YFLogxK
U2 - 10.1145/3552437.3555700
DO - 10.1145/3552437.3555700
M3 - Conference contribution
AN - SCOPUS:85141376737
T3 - MMSports 2022 - Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports
SP - 19
EP - 27
BT - MMSports 2022 - Proceedings of the 5th International ACM Workshop on Multimedia Content Analysis in Sports
PB - Association for Computing Machinery, Inc
T2 - 5th ACM International Workshop on Multimedia Content Analysis in Sports, MMSports 2022, co-located with ACM Multimedia 2022
Y2 - 14 October 2022
ER -
