MARS: a muscle activity recognition system enabling self-configuring musculoskeletal sensor networks

Authors:
Frank O. Mokaya;Brian Nguyen;Cynthia Kuo;Quinn Jacobson;Anthony Rowe;Pei Zhang
Affiliations:
Carnegie Mellon University, Pittsburgh, PA, USA;Vibrado Technologies, Mountain View, CA, USA;Vibrado Technologies, Mountain View, CA, USA;Vibrado Technologies, Mountain View, CA, USA;Carnegie Mellon University, Pittsburgh, PA, USA;Carnegie Mellon University, Pittsburgh, PA, USA
Venue:
Proceedings of the 12th international conference on Information processing in sensor networks
Year:
2013

Citing 9
Cited 0

Motion Tracking: No Silver Bullet, but a Respectable Arsenal

IEEE Computer Graphics and Applications
MOCA: a low-power, low-cost motion capture system based on integrated accelerometers

Advances in Multimedia
Using FSR based muscule activity monitoring to recognize manipulative arm gestures

ISWC '07 Proceedings of the 2007 11th IEEE International Symposium on Wearable Computers
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
A body sensor network with electromyogram and inertial sensors: multimodal interpretation of muscular activities

IEEE Transactions on Information Technology in Biomedicine - Special section on affective and pervasive computing for healthcare
Motion capture from body-mounted cameras

ACM SIGGRAPH 2011 papers
A dynamic sliding window approach for activity recognition

UMAP'11 Proceedings of the 19th international conference on User modeling, adaption, and personalization
Detecting and interpreting muscle activity with wearable force sensors

PERVASIVE'06 Proceedings of the 4th international conference on Pervasive Computing
Active capacitive sensing: exploring a new wearable sensing modality for activity recognition

Pervasive'10 Proceedings of the 8th international conference on Pervasive Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Poor posture and incorrect muscle usage are a leading cause of many injuries in sports and fitness. For this reason, non- invasive, fine-grained sensing and monitoring of human motion and muscles is important for mitigating injury and improving fitness efficacy. Current sensing systems either de- pend on invasive techniques or unscalable approaches whose accuracy is highly dependent on body sensor placement. As a result these systems are not suitable for use in active sports or fitness training where sensing needs to be scalable, accurate and un-inhibitive to the activity being performed. We present MARS, a system that detects both body motion and individual muscle group activity during physical human activity by only using unobtrusive, non-invasive in- ertial sensors. MARS not only accurately senses and recreates human motion down to the muscles, but also allows for fast personalized system setup by determining the individual identities of the instrumented muscles, obtained with minimal system training. In a real world human study con- ducted to evaluate MARS, the system achieves greater than 95% accuracy in identifying muscle groups.