Robust, low-cost, non-intrusive sensing and recognition of seated postures

ABSTRACT

In this paper, we present a methodology for recognizing seated postures using data from pressure sensors installed on a chair. Information about seated postures could be used to help avoid adverse effects of sitting for long periods of time or to predict seated activities for a human-computer interface. Our system design displays accurate near-real-time classification performance on data from subjects on which the posture recognition system was not trained by using a set of carefully designed, subject-invariant signal features. By using a near-optimal sensor placement strategy, we keep the number of required sensors low thereby reducing cost and computational complexity. We evaluated the performance of our technology using a series of empirical methods including (1) cross-validation (classification accuracy of 87% for ten postures using data from 31 sensors), and (2) a physical deployment of our system (78% classification accuracy using data from 19 sensors).

REFERENCES

• 1: Agency for Health Care Policy & Research (AHCPR). Pressure ulcers in adults: Prediction and prevention, clinical practice guideline. AHCPR Publication no. 92-0047, 1992.
• 2: Shigeki Aoki , Yoshio Iwai , Masaki Onishi , Atsuhiro Kojima , Kunio Fukunaga, Learning and recognizing behavioral patterns using position and posture of human body and its application to detection of irregular states, Systems and Computers in Japan, v.36 n.13, p.45-56, November 2005 [doi>10.1002/scj.v36:13]
• 3: Bardsley, G.I. The dundee seating programme. Physiotheraphy, 70, 2 (1984), 59--63.
• 4: Richard Ernest Bellman, Dynamic Programming, Dover Publications, Incorporated, 2003
• 5: J Canny, A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.8 n.6, p.679-698, Nov. 1986 [doi>10.1109/TPAMI.1986.4767851]
• 6: Caselton, W.F. and Zidek, J.V. Optimal monitoring network designs. Statistics & Probability Letters, 2, 4 (1984), 223--227.
• 7: Chvatal, V. A combinatorial theorem in plane geometry. J. of Combinatorial Theory, Series B, 18 (1975), 39--41.
• 8: Cheng, S.Y. and Trivedi, M.M. Human posture estimation using voxel data for "smart" airbag systems: issues and framework. IEEE Intelligent Vehicles Symposium, 2004, pp. 84--89.
• 9: Cohen, D. An objective measure of seat comfort. J. of Aviation, Space, & Env. Medicine, 69, 4 (April 1998), 410--414.
• 10: Thomas M. Cover , Joy A. Thomas, Elements of information theory, Wiley-Interscience, New York, NY, 1991
• 11: Cressie, N.A.C. Statistics for Spatial Data. Wiley, 1991.
• 12: De Looze, M.P., Kuijt-Evers, L.M.F, and Van Dieen, J. Sitting comfort and discomfort and the relationships with objective measures. Ergonomics, 46, 10 (August 2003), 985--997.
• 13: Jodi Forlizzi , Carl DiSalvo , John Zimmerman , Bilge Mutlu , Amy Hurst, The SenseChair: the lounge chair as an intelligent assistive device for elders, Proceedings of the 2005 conference on Designing for User eXperience, November 03-05, 2005, San Francisco, California
• 14: D'Mello, S.K., Craig, S.D., Gholson, B., Franklin, S., Picard, R., and Graesser, A.C. Integrating affect sensors in an intelligent tutoring system. In Affective Interactions: The Computer in the Affective LoopWorkshop at 2005 Intl. Conf. on Intelligent User Interfaces, 2005, pp. 7--13.
• 15: Andrew Fitzgibbon , Maurizio Pilu , Robert B. Fisher, Direct Least Square Fitting of Ellipses, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.21 n.5, p.476-480, May 1999 [doi>10.1109/34.765658]
• 16: François Fleuret, Fast Binary Feature Selection with Conditional Mutual Information, The Journal of Machine Learning Research, 5, p.1531-1555, 12/1/2004
• 17: Friedman, J., Hastie, T., and Tibshirani, R. Additive logistic regression: a statistical view of boosting, Stanford University, Dept. of Statistics Tech. Report, 1998.
• 18: Furugori, S., Yoshizawa, N., Iname, C., and Miura, Y. Measurement of driver's fatigue based on driver's postural change. In Proc. of SICE 2003 An. Conf., 1, 2003, pp. 264--269.
• 19: H. González-Banos, A randomized art-gallery algorithm for sensor placement, Proceedings of the seventeenth annual symposium on Computational geometry, p.232-240, June 2001, Medford, Massachusetts, United States [doi>10.1145/378583.378674]
• 20: Isabelle Guyon , Jason Weston , Stephen Barnhill , Vladimir Vapnik, Gene Selection for Cancer Classification using Support Vector Machines, Machine Learning, v.46 n.1-3, p.389-422, 2002 [doi>10.1023/A:1012487302797]
• 21: Halender, M.G. and Zhang, L. Field studies of comfort and discomfort in sitting. Ergonomics, 40, 9 (1997), 895--915.
• 22: Harada, T., Sato, T., and Mori, T. Estimation of bed-ridden human's gross and slight movement based on pressure sensors distribution bed. In Proc. of IEEE Intl. Conf. on Robotics & Automation, 2002, pp. 3795--3800.
• 23: Hossain, M., Morris, J.N., Brandeis, G.H., Ooi, W.L., and Lipsitz, L.A. A longitudinal study of risk factors associated with the formation of pressure ulcers in nursing homes. J. of American Geriatric Society, 42, 4 (1994).
• 24: Kapoor, A., Mota, S., and Picard, R.W. Towards a learning companion that recognizes affect. In Proc. of Emotional & Intelligent II: The Tangled Knot of Social Cognition, Fall Symposium. AAAI, Nov. 2001.
• 25: Krause, A. and Guestrin, C. A note on the budgeted maximization on submodular functions. Technical Report CMU-CALD-05-103, 2005.
• 26: Krause, A. and Guestrin, C. Near-optimal nonmyopic value of information in graphical models. In Proc. of Uncertainty in A.I., 2005.
• 27: Landwehr, N., Hall, M., and Frank, E. Logistic model trees. In Proc. of ECML/PKDD Conf., 2003, pp. 241--252.
• 28: Monette, M., Weiss-Lambrou, R., and Dansereau, J. In search of a better understanding of wheelchair sitting comfort and discomfort. In Proc. of the RESNA An. Conf., 1999, pp. 218--220.
• 29: Mota, S. and Picard, R.W. Automated Posture Analysis for Detecting Learners Interest Level. In Proc. of Computer Vision & Pattern Recognition Workshop, 2003, pp. 49.
• 30: I. Burak Ozer , Wayne Wolf, Real-time Posture and Activity Recognition, Proceedings of the Workshop on Motion and Video Computing, p.133, December 05-06, 2002
• 31: L. Panini , R. Cucchiara, A MAchine Learning Approach for Human Posture Detection in Domotics Application, Proceedings of the 12th International Conference on Image Analysis and Processing, p.103, September 17-19, 2003
• 32: Pellegrini, S. and Iocchi, L. Human Posture Tracking and Classification through Stereo Vision. In Proc. of Intl. Conf. on Computer Vision Theory & Applications, 2006.
• 33: Prado, M., Reina-Tosina, J., and Roa, L. Distributed intelligent architecture for falling detection and physical activity analysis in the elderly. In Proc. of EMBS/ BMES Conf., 2002, pp. 1910--1911.
• 34: Azriel Rosenfeld , John L. Pfaltz, Sequential Operations in Digital Picture Processing, Journal of the ACM (JACM), v.13 n.4, p.471-494, Oct. 1966 [doi>10.1145/321356.321357]
• 35: Sato, T., Nishida, Y., and Mizoguchi, H. Robotic Room: Symbiosis with human through behavior media. In Robotics & Autonomous Systems, Elsevier, 1996, pp. 185--194.
• 36: Scherer, M.J. User desires for wheelchairs. Rehab Management, 9, 4 (June--July 1996), 121--123.
• 37: Shaw, G. Wheelchair seat comfort for the institutionalized elderly. Assistive Technology, 3, 1 (1992), 11--23.
• 38: Smith, D.M. Pressure ulcers in the nursing home. Annals of Internal Medicine, 123, 6 (Sept. 15, 1995), 433--438.
• 39: Sviridenko, M. A note on maximizing a submodular set function subject to a knapsack constraint. O. R. Letters, 32, 1 (2004), 41--43.
• 40: Tan, H.Z., Slivovsky, L.A., and Pentland, A. A sensing chair using pressure distribution sensors. IEEE/ASME Trans. on Mechatronics, 6, 3 (2001), 261--268.
• 41: Tan, H. Z., Ifung L., and Pentland A. The chair as a novel haptic user interface. In Proc. of Workshop on Perceptual User Interfaces, Banff, Canada, 1997.
• 42: Trivedi, M.M., Shinko, Y.C., Childers, E.M.C., and Krotosky, S.J. Occupant posture analysis with stereo and thermal infrared video: algorithms and experimental evaluation. IEEE Trans. on Vehicular Technology, 53, 6 (2004), 1698--1712.
• 43: Ian H. Witten , Eibe Frank, Data Mining: Practical Machine Learning Tools and Techniques, Second Edition (Morgan Kaufmann Series in Data Management Systems), Morgan Kaufmann Publishers Inc., San Francisco, CA, 2005
• 44: Zhu, M., Martinez, A.M., and Tan, H.Z. Template-based recognition of static sitting postures. In Workshop on Computer Vision & Pattern Recognition for Human-Computer Interaction, 2003.

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: User-centered design

Additional 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: Haptic I/O

  J. Computer Applications
  J.7 COMPUTERS IN OTHER SYSTEMS
      Subjects: Consumer products

General Terms:
Algorithms, Design, Human Factors

Keywords:
haptic interfaces, machine learning, personal technologies, sensor technologies, ubiquitous computing