Sensor Arrangement for Classification of Life Activities with Pyroelectric Sensors – Arrangement to Save Sensors and to Quasi-Maximize Classification Precision
Taketoshi Mori, Ryo Urushibata, Hiroshi Noguchi,
Masamichi Shimosaka, Hiromi Sanada, and Tomomasa Sato
The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033, Japan
This paper deals with the sensor arrangement for activity classification systems with a group of pyroelectric sensors to realize a system with high classification performance using as few sensors as possible. It targets the people living alone. We convert this discrete optimization problem, which means whether or not the system select a sensor position candidate, to continuous, convex, and sparse optimization problem, and solve it efficiently by extended multi-class LPBoost via column generation. For some examinations, we showed the advantage of this algorithm. We also confirmed the significance of automatic arrangement system by comparing the arrangement obtained by this algorithm with the arrangement obtained by human judge.
Masamichi Shimosaka, Hiromi Sanada, and Tomomasa Sato, “Sensor Arrangement for Classification of Life Activities with Pyroelectric Sensors – Arrangement to Save Sensors and to Quasi-Maximize Classification Precision,” J. Robot. Mechatron., Vol.23, No.4, pp. 494-504, 2011.
-  S. Intille, “Designing a Home of the Future,” IEEE Pervasive Computing, April-June, pp. 80-86, 2002.
-  T. Mori, R. Urushibata, M. Shimosaka, H. Noguchi, and T. Sato, “Anomaly Detection Algorithm Based on Life Pattern Extraction from Accumulated Pyroelectric Sensor Data,” In IEEE/RSJ Int. Conf. on Intelligent Robots and Systems, pp. 2545-2552, 2008.
-  H. Wang, K. Yao, G. Pottie, and D. Estrin,“Efficient Entropy-based sensor selection heuristic for target localization,” In Proc. of the First Int. Conf. on Wireless Internet, pp. 114-121, 2004.
-  T. Mori, R. Urushibata, M. Shimosaka, H. Noguchi, and T. Sato, “The Optimization of Sensor Arrangement for Activity Recognition by Flow-based Simulation,” In IEICE Technical Report on Pattern Recognition and Media Understanding, Vol.2009, No.46, pp. 115-120, 2009.
-  P. Pudil, J. Novovicova, and J. Kittler, “Floating search methods in feature selection,” In Pattern Recognition Letters, Vol.15, No.11, pp. 1119-1125, 1994.
-  S. Perkins, K. Lacker, and J. Theiler, “Grafting: Fast, Incremental Feature Selection by Gradient Descent in Function Space,” In J. of Machine Learning Research 3, pp. 1333-1356, 2003.
-  A. Demiriz, K. P Bennett, and J. Shawe-Taylor, “Linear Programming Boosting via Column Generation,” In Machine Learning, Vol.46, pp. 225-254, 2002.
-  P. Gehler and S. Nowozin, “On Feature Combination for Multiclass Object Classification,” In IEEE Int. Conf. on Computer Vision (ICCV), p. 221, 2009.
-  G. Ratsch, B. Scholkopf, A. Smola, S. Mika, K-R. Muller, and T. Onoda, “Robust ensemble learning,” In Advances in Large Margin Classifiers, A. J. Smola, P. L. Bartlett, B. Scholkopf, and D. Schuurmans (Eds.), Cambridge, MA: MIT Press, pp. 207-219, 2000.
-  M. Shimosaka, T. Sato, and T. Mori, “Max-margin sensor localization over wireless networks,” The 15th Robotics Symposia, pp. 520-526, 2010 (in Japanese).
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.
Copyright© 2011 by Fuji Technology Press Ltd. and Japan Society of Mechanical Engineers. All right reserved.