Context awareness via a single device-attached accelerometer during mobile computing

ABSTRACT

Interest in context-aware computing has expanded the use of sensing technologies. The accelerometer is one of the most widely used sensors for capturing context because it is small, inexpensive, lightweight, and self-operable. In efforts to obtain behavioral patterns, many studies have reported the use of multiple accelerometers attached to the human body. However, this is difficult to implement in real-life situations and may not fully address the context of user interaction. In contrast, the present study employed a single tri-axial accelerometer attached to a handheld computing device instead of to a user. The objective was to determine what contextual information could be obtained from this more feasible, albeit limited, source of acceleration data. Data analyses confirmed that changes in both mobility and lighting conditions induced statistically significant differences in the output of the accelerometer.

REFERENCES

• 1: Bao, L. Physical Activity Recognition from Acceleration Data under Semi-naturalistic Conditions. Massachusetts Institute of Technology, Cambridge, MA, M.Eng. Thesis Thesis, 2003.
• 2: Bao, L. and Intille, S. S. Activity recognition from user-annotated acceleration data in Proceedings of Pervasive 2004: the Second International Conference on Pervasive Computing (2004).
• 3: Leon Barnard , Ji Soo Yi , Julie A. Jacko , Andrew Sears, An empirical comparison of use-in-motion evaluation scenarios for mobile computing devices, International Journal of Human-Computer Studies, v.62 n.4, p.487-520, April 2005 [doi>10.1016/j.ijhcs.2004.12.002]
• 4: Barnard, L., Yi, J. S., Jacko, J. A., and Sears, A. A new perspective on mobile device evaluation methods. Personal and Ubiquitous Computing (in press).
• 5: Cakmakci, O., Coutaz, J., Laerhoven, K. V., and Gellersen, H.-W. Context Awareness in Systems with Limited Resources in Proceedings of the third workshop on Artificial Intelligence in Mobile Systems (AIMS), ECAI 2002 (Lyon, France, 2002), 21--29.
• 6: Guanling Chen , David Kotz, A Survey of Context-Aware Mobile Computing Research, Dartmouth College, Hanover, NH, 2000
• 7: Clayton, M. M. and Schamhardt, H. C., "Measurement Techniques for Gait Analysis", in Equine Locomotion, Back, W. and Clayton, H. M., Eds., 2000, pp. 400.
• 8: Edmison, J., Jones, M., Lockhart, T., and Martin, T. An E-Textile System for Motion Analysis in Proceedings of the International Workshop on a New Generation of Wearable Systems for eHealth, NGWSH (Lucca, Italy, Dec, 2003).
• 9: Griffin, M. J. Handbook of human vibration. Academic Press, 1990.
• 10: Kern, K., Schiele, B., and Schmidt, A. Multi-Sensor Activity Context Detection for Wearable Computing in Proceedings of European Symposium on Ambient Intelligence (EUSAI) (Eindhoven, The Netherlands, November, 2003).
• 11: Kim, Y. H., Yi, J. B., and Rhee, K. H. Acceleration Patterns of the Body Center in Level Walking: Normal and Hemiplegic Patients. in Proceedings of World Congress on Medical Physics and Biomedical Engineering (Sydney, Australia, Aug 24-29, 2003), Paper No. 606.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)
          Subjects: Interaction styles (e.g., commands, menus, forms, direct manipulation)

General Terms:
Experimentation, Human Factors, Measurement

Keywords:
accelerometer, context-awareness, gait, mobile computing, pen-based handheld device, sitting, treadmill, walking