Journal
IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE
Volume 14, Issue 5, Pages 1211-1215Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TITB.2010.2055060
Keywords
Binary decision tree; classifier personalization; real-time activity recognition
Categories
Funding
- TEKES (The Finnish Funding Agency for Technology and Innovation)
Ask authors/readers for more resources
Inactive and sedentary lifestyle is a major problem in many industrialized countries today. Automatic recognition of type of physical activity can be used to show the user the distribution of his daily activities and to motivate him into more active lifestyle. In this study, an automatic activity-recognition system consisting of wireless motion bands and a PDA is evaluated. The system classifies raw sensor data into activity types online. It uses a decision tree classifier, which has low computational cost and low battery consumption. The classifier parameters can be personalized online by performing a short bout of an activity and by telling the system which activity is being performed. Data were collected with seven volunteers during five everyday activities: lying, sitting/standing, walking, running, and cycling. The online system can detect these activities with overall 86.6% accuracy and with 94.0% accuracy after classifier personalization.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available