Location and Activity Recognition Using eWatch: A Wearable Sensor Platform
The eWatch is a wearable sensing, notification, and computing platform built into a wrist watch form factor making it highly available, instantly viewable, ideally located for sensors, and unobtrusive to users. Bluetooth communication provides a wireless link to a cellular phone or stationary computer. eWatch senses light, motion, audio, and temperature and provides visual, audio, and tactile notification. The system provides ample processing capabilities with multiple day battery life enabling realistic user studies. This paper provides the motivation for developing a wearable computing platform, a description of the power aware hardware and software architectures, and results showing how online nearest neighbor classification can identify and recognize a set of frequently visited locations. We then design an activity recognition and monitoring system that identifies the user’s activity in realtime using multiple sensors. We compare multiple time domain feature sets and sampling rates, and analyze the tradeoff between recognition accuracy and computational complexity. The classification accuracy on different body positions used for wearing electronic devices was evaluated.
KeywordsRecognition Accuracy Activity Recognition Light Sensor Fall Detection Defense Advance Research Project Agency
Unable to display preview. Download preview PDF.
- 2.Bharatula, N.B., Stäger, M., Lukowicz, P., Tröster, G.: Empirical Study of Design Choices in Multi-Sensor Context Recognition Systems. In: IFAWC: 2nd International Forum on Applied Wearable Computing, March 2005, pp. 79–93 (2005)Google Scholar
- 3.Bharatula, N.B., Stäger, M., Lukowicz, P., Tröster, G.: Power and Size Optimized Multisensor Context Recognition Platform. In: ISWC 2005: Proceedings of the 9th IEEE International Symposium on Wearable Computers, pp. 194–195 (October 2005)Google Scholar
- 4.DeVaul, R.W., Pentland, S.: The MIThril Real-Time Context Engine and Activity Classification. Tech. rep., MIT Media Lab (2003)Google Scholar
- 5.Dougherty, J., Kohavi, R., Sahami, M.: Supervised and unsupervised discretization of continuous features. In: International Conference on Machine Learning, pp. 194–202 (1995)Google Scholar
- 6.Gould, C.: Dick Tracy. Comic, Chicago Tribune (October 1931)Google Scholar
- 7.Hans, M., Schafer, R.: Lossless Compression of Digital Audio. IEEE Signal Processing 18, July 2001, pp. 21–32 (2001)Google Scholar
- 8.Krause, A., Siewiorek, D.P., Smailagic, A., Farringdon, J.: Unsupervised, dynamic identification of physiological and activity context in wearable computing. In: Seventh IEEE International Symposium on Wearable Computers (ISWC 2003), pp. 88–97 (2003)Google Scholar
- 10.Narayanaswami, C., Raghunath, M.T.: Application design for a smart watch with a high resolution display. In: ISWC 2000: Proceedings of the 4th IEEE International Symposium on Wearable Computers, Washington, DC, USA, p. 7 (2000)Google Scholar
- 11.Noury, N.: A smart sensor for the remote follow up of activity and fall detection of the elderly. In: Proc. of the IEEE Special Topic Conference on Microtechnologies in Medicine & Biology (May 2002)Google Scholar
- 13.Smailagic, A., Siewiorek, D.P., Maurer, U., Rowe, A., Tang, K.: eWatch: Context-Sensitive Design Case Study. In: Proc. of the IEEE Annual VLSI Symposium, pp. 98–103. IEEE Computer Society Press, Los Alamitos (2005)Google Scholar
- 14.Want, R., Hopper, A., Falcao, V., Gibbons, J.: The active badge location system. Tech. Rep. 92.1, ORL, 24a Trumpington Street, Cambridge CB2 1QA (1992)Google Scholar