Incremental Learning, Recognition, and Generation of Time-Series Patterns Based on Self-Organizing Segmentation
Shogo Okada, and Osamu Hasegawa
Tokyo Institute of Technology, R2-52, 4259 Nagatsuta, Midori-ku, Yokohama 226-8503, Japan
We segments and symbolizes image information on a series of human behavior as an aggregate unit of motions in a self-organizing manner and proposes a system that recognizes the entire behavior as a symbol string. This system symbolizes the motion unit incrementally and also generates motion from a symbol. To implement the system, we used a mixture of experts with a non-monotonous recurrent neural network used as the expert and our own DP matching method. In addition, our proposal makes not only teacher-labeled patterns, but also teacher-unlabeled patterns available for learning. By using this function, we proposed semi-supervised learning using our proposal in this paper. We verified the evaluation of the effectiveness of our proposal and semi-supervised learning function by two experiments using moving images including seven gestures.
-  M. Morita, “Memory and learning of sequential patterns by nonmonotone neural networks,” Neural Networks, No.9, pp. 1477-1489, 1996.
-  Y. Kuniyoshi, and M. Shimozaki, “A Self-Organizing Neural Model for Context-Based Action Recognition,” Proc. IEEE EMBS Conf. on Neural Engineering, pp. 442-445, 2003.
-  M. Simozaki, T. Inamura, and Y. Nakamura, “Recognition memorization and generation of human motion pattern by an associative memory,” Proc. ROBOMEC ’01, pp. 2P1-B11, 2001.
-  T. Inamura, Y. Nakamura, and M. Simozaki, “Integration of behavior recognition and generation processes based on associative memory,” Proc. Annual Conf. of Robotics Soc. of Japan, pp. 1237-1238, 2001.
-  R. A. Jacobs, M. I. Jordan, S. J. Nowlan, and G. E. Hinton, “Adaptive mixture of local experts,” Neural Computation, 3, pp. 79-87, 1991.
-  T. Kobayashi, and N. Otsu, “Action and Simultaneous Multiple Persons Identification Using Cubic Higher-order Local Auto-Correlation,” Proc. International Conference on Pattern Recognition (ICPR), UK, Aug., 2004.
-  J. Yamato, J. Ohya, and K. Ishii, “Recognizing human action in time-sequential images using hidden Markov models,” Proc. IEEE International Conference on Computer Vision (ICCV), pp. 379-387, 1992.
-  A. Elgammal, V. Shet, Y. Yacoob, and L. S. Davis, “Learning Dynamics for Exemplar-based Gesture Recognition,” Proc. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Madison, Wisconsin, pp. 16-22, June, 2003.
-  M. Inoue, and N. Ueda, “Extended Tied-Mixture HMMs for Both Labeled and Unlabeled Time Series Data,” Journal of VLSI Signal Processing, 37, pp. 189-197, 2004.
-  T. Nishimura, N. Sekimoto, J. X. Zhang, M. Ihara, T. Akasaka, H. Takahashi, and R. Oka, “Methodology for Retrieving Time Sequence Pattern,” Proc. of IWHIT/SM’99, pp. 1-9, 1999.
-  N. Sekimoto, T. Nishimura, H. Takahashi, and R. Oka, “Realtime and Time-warping Retrieval of Video Image Sequence,” Proc. of Fifth World Multi-Conference on Systemics, Cybernetics and Informatics, Vol.VII, pp. 298-301, 2001.
-  N. Ueda, “The Theory and Algorithm of Semi-supervised Learning,” Technical report of the Institute of Electronics, Information and Communication Engineers, NLC2004-101, PRMU2004-183(2005-2), pp. 25-30, 2005.
-  T. Inamura, I. Toshima, H. Tanie, and Y. Nakamura, “Embodied Symbol Emergence based on Mimesis Theory,” International Journal of Robotics Research, Vol.23, No.4, pp. 363-377, 2004.
-  K. Samejima, K. Doya, and M. Kawato, “Intra-module credit assignment in multiple model-based reinforcement learning,” Neural Networks, Vol.16, pp. 985-994, 2003.
-  D. Wolpert, C. Miall, and M. Kawato, “Internal models in the cerebellum,” Trends in Cognitive Sciences, 2 (c), Elsevier Science Ltd., pp. 338-347, 1998.
-  K. Doya, K. Samejima, K. Katagiri, and M. Kawato, “Multiple model-based reinforcement learning,” Neural Computation, Vol.14, pp. 1347-1369, 2002.
-  K. Samejima, K. Katagiri, K. Doya, and M. Kawato, “Multiple model-based reinforcement learning of nonlinear control Transactions of the Institute of Electronics,” Information and Communication Engineers, J84-D-II(9), pp. 2092-2106, 2001.
-  K. Samejima, K. Katagiri, K. Doya, and M. Kawato, “Symbolization and imitation learning of motion sequence using competitive modules,” Transactions of the Institute of Electronics, Information and Communication Engineers, J85-D-II(1), pp. 90-100, 2002.
-  K. G. Derpanis, R. P. Wildes, and J. K. Tsotsos, “Hand Gesture Recognition within a Linguistics-Based Framework,” Proc. European Conference on Computer Vision (ECCV), pp. 282-296, 2004.
-  P. Smyth, “Clustering sequences with hidden markov models,” Advances in Neural Information Processing Systems, Vol.9, The MIT Press, pp. 648-655, 1997.
-  C. M. David, and R. W. Christopher, “Finding Temporal Patterns by Data Decomposition,” Proc. IEEE International Conference on Automatic Face and Gesture Recognition, Seoul, Korea, pp. 608-613, May, 2004.
-  G. A. Carpenter, and S. Grossberg, “The ART of Adaptive Pattern Recognition,” IEEE Computer, Vol.21, No.3, pp. 77-88, Mar., 1988.
-  R. Beale, and T. Jackson, “Neural Computing: An Introduction,” IOP Publishing Ltd., 1990.
This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.