Dealing with sensor displacement in motion-based onbody activity recognition systems
- 21 September 2008
- proceedings article
- Published by Association for Computing Machinery (ACM)
Abstract
We present a set of heuristics that significantly increase the robustness of motion sensor-based activity recognition with respect to sensor displacement. In this paper placement refers to the position within a single body part (e.g, lower arm). We show how, within certain limits and with modest quality degradation, motion sensorbased activity recognition can be implemented in a displacement tolerant way. We first describe the physical principles that lead to our heuristic. We then evaluate them first on a set of synthetic lower arm motions which are well suited to illustrate the strengths and limits of our approach, then on an extended modes of locomotion problem (sensors on the upper leg) and finally on a set of exercises performed on various gym machines (sensors placed on the lower arm). In this example our heuristic raises the displaced recognition rate from 24% for a displaced accelerometer, which had 96% recognition when not displaced, to 82%.Keywords
This publication has 10 references indexed in Scilit:
- Wearable Activity Tracking in Car ManufacturingIEEE Pervasive Computing, 2008
- Memorizing What You Did Last Week: Towards Detailed Actigraphy With A Wearable SensorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Toward Recognition of Short and Non-repetitive Activities from Wearable SensorsPublished by Springer Nature ,2007
- Activity Recognition and Monitoring Using Multiple Sensors on Different Body PositionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- A Practical Approach to Recognizing Physical ActivitiesPublished by Springer Nature ,2006
- Context-aware mobile computing: learning context- dependent personal preferences from a wearable sensor arrayIEEE Transactions on Mobile Computing, 2005
- Recognizing Mimicked Autistic Self-Stimulatory Behaviors Using HMMsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Where am I: Recognizing On-body Positions of Wearable SensorsPublished by Springer Nature ,2005
- Spine versus Porcupine: A Study in Distributed Wearable Activity RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Wearable sensing to annotate meeting recordingsPersonal and Ubiquitous Computing, 2003