Authors:
Håvard Myklebust
1
;
Neuza Nunes
2
;
Jostein Hallén
1
and
Hugo Gamboa
3
Affiliations:
1
Norwegian School of Sports Sciences, Norway
;
2
FCT-UNL, Portugal
;
3
FCT-UNL and PLUX – Wireless Biosignals, Portugal
Keyword(s):
Cross-country skiing, Accelerometers, Expert-based classification, Biosignals, Signal-processing.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Data Manipulation
;
Detection and Identification
;
Devices
;
Health Engineering and Technology Applications
;
Health Information Systems
;
Human-Computer Interaction
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
;
Wearable Sensors and Systems
Abstract:
Aims: Experience morphology of acceleration signals, extract useful information and classify time periods into defined techniques during cross-country skiing. Method: Three Norwegian cross-country skiers ski skated one lap in the 2011 world championship sprint track as fast as possible with 5 accelerometers attached to their body and equipment. Algorithms for detecting ski/pole hits and leaves and computing specific ski parameters like cycle times (CT), poling/pushing times (PT), recovery times (RT), symmetry between left and right side and technique transition times were developed based on thresholds and validated against video. Results: In stable and repeated techniques, pole hits/leaves and ski leaves were detected 99% correctly, while ski hits were more difficult to detect (77%). From these hit and leave values CT, PT, RT, symmetry and technique transitions were successfully calculated. Conclusion: Accelerometers can definitely contribute to biomechanical research in cross-countr
y skiing and studies combining force, position and accelerometer data will probably be seen more frequently in the future.
(More)