Dealing with sensor displacement in motion-based onbody activity recognition systems

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%.

REFERENCES

• 1: Ryan Aylward , Joseph A. Paradiso, Sensemble: a wireless, compact, multi-user sensor system for interactive dance, Proceedings of the 2006 conference on New interfaces for musical expression, June 04-08, 2006, Paris, France
• 2: Helene Brashear , Thad Starner , Paul Lukowicz , Holger Junker, Using Multiple Sensors for Mobile Sign Language Recognition, Proceedings of the 7th IEEE International Symposium on Wearable Computers, p.45, October 21-23, 2003
• 3: Nicky Kern , Bernt Schiele , Holger Junker , Paul Lukowicz , Gerhard Tröster, Wearable sensing to annotate meeting recordings, Personal and Ubiquitous Computing, v.7 n.5, p.263-274, October 2003 [doi>10.1007/s00779-003-0242-y]
• 4: Kunze, K., Lukowicz, P., Junker, H., Troester, G.: Where am i: Recognizing on-body positions of wearable sensors. LOCA'04: International Workshop on Locationand Context- ... (2005)
• 5: Andreas Krause , Asim Smailagic , Daniel P. Siewiorek, Context-Aware Mobile Computing: Learning Context-Dependent Personal Preferences from a Wearable Sensor Array, IEEE Transactions on Mobile Computing, v.5 n.2, p.113-127, February 2006 [doi>10.1109/TMC.2006.18]
• 6: Lester, J., Hannaford, B., Boriello, G.: Are you with me?--using accelerometers to determine if two devices are carried by the same person. Pervasive Computing: Second International Conference (2004)
• 7: Lester, J., Choudhury, T., Borriello, G.: A practical approach to recognizing physical activities. Proceedings of Pervasive (2006)
• 8: Mantyjarvi, J., Himberg, J., Seppanen, T., Center, N. R.: Recognizing human motion with multiple acceleration sensors. Systems, Man, and Cybernetics, 2001 IEEE International Conference on 2 (2001)
• 9: Uwe Maurer , Asim Smailagic , Daniel P. Siewiorek , Michael Deisher, Activity Recognition and Monitoring Using Multiple Sensors on Different Body Positions, Proceedings of the International Workshop on Wearable and Implantable Body Sensor Networks, p.113-116, April 03-05, 2006 [doi>10.1109/BSN.2006.6]
• 10: David Mizell, Using Gravity to Estimate Accelerometer Orientation, Proceedings of the 7th IEEE International Symposium on Wearable Computers, p.252, October 21-23, 2003
• 11: Thomas Stiefmeier , Daniel Roggen , Georg Ogris , Paul Lukowicz , Gerhard Tröster, Wearable Activity Tracking in Car Manufacturing, IEEE Pervasive Computing, v.7 n.2, p.42-50, April 2008 [doi>10.1109/MPRV.2008.40]
• 12: Cliff Randell , Henk Muller, Context Awareness by Analyzing Accelerometer Data, Proceedings of the 4th IEEE International Symposium on Wearable Computers, p.175, October 18-21, 2000
• 13: Roggen, D., Bharatula, N., Stager, M., Lukowicz, P., Troster, G.: From sensors to miniature networked sensorbuttons. Proceedings of the 3rd International Conference on Networked Sensing Systems (INSS06) (2006)
• 14: Kristof Van Laerhoven , Andre Kvist Aronsen, Memorizing What You Did Last Week: Towards Detailed Actigraphy With A Wearable Sensor, Proceedings of the 27th International Conference on Distributed Computing Systems Workshops, p.47, June 22-29, 2007 [doi>10.1109/ICDCSW.2007.43]
• 15: Kristof Van Laerhoven , Ozan Cakmakci, What Shall We Teach Our Pants?, Proceedings of the 4th IEEE International Symposium on Wearable Computers, p.77, October 18-21, 2000
• 16: Kristof Van Laerhoven , Hans-Werner Gellersen, Spine versus Porcupine: A Study in Distributed Wearable Activity Recognition, Proceedings of the Eighth International Symposium on Wearable Computers, p.142-149, October 31-November 03, 2004 [doi>10.1109/ISWC.2004.40]
• 17: Tracy Westeyn , Kristin Vadas , Xuehai Bian , Thad Starner , Gregory D. Abowd, Recognizing Mimicked Autistic Self-Stimulatory Behaviors Using HMMs, Proceedings of the Ninth IEEE International Symposium on Wearable Computers, p.164-169, October 18-21, 2005 [doi>10.1109/ISWC.2005.45]
• 18: Zinnen, A., van Laerhoven, K., Schiele, B.: Toward recognition of short and non-repetitive activities from wearable sensors. (European Conference on Ambient Intelligence 2007)

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology

Keywords:
fitness exercises, motion sensors, opportunistic activity recognition, sensor displacement