Browse > Article
http://dx.doi.org/10.3745/KIPSTB.2004.11B.4.449

A Novel Model, Recurrent Fuzzy Associative Memory, for Recognizing Time-Series Patterns Contained Ambiguity and Its Application  

Kim, Won (전주기전여자대학 실용예술학부)
Lee, Joong-Jae (숭실대학교 대학원 컴퓨터학과)
Kim, Gye-Young (숭실대학교 컴퓨터학부)
Choi, Hyung-Il (숭실대학교 미디어학부)
Publication Information
The KIPS Transactions:PartB / v.11B, no.4, 2004 , pp. 449-456 More about this Journal
Abstract
This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.
Keywords
RFAM; Recurrent Fuzzy Associative Memory; Time-Series Pattern Recognition; Hebbian Learning; World Boundary Detection;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Martin T. Hagan, Howard B. Demuth, 'Neural Network Design,' PWS Publishing Company, 1995
2 J. T. Connor, R. D. Martin and L. E. Atlas, 'Recurrent Neural Networks and Robust Time Series Prediction,' IEEE Transaction on Neural Networks, Vol.5, No.2, 1994   DOI   ScienceOn
3 Alex Aussem, Fionn Murtagh and Marc Sarazin, 'Dyanmical Recurrent Neural Networks - Towards Environmental Time Series Prediction,' International Journal of Neural Systems, Vol.6, No.2, pp.145-170, 1995   DOI   ScienceOn
4 Barak Cohen, Daid Saad and Emanuel Marom, 'Efficient Training of Recurrent Neural Network with Time Delays,' Neural Networks, Vol.10, No.1, pp.51-59, 1997   DOI   ScienceOn
5 장대식, '퍼지연상기억장치에 기반한 퍼지 추론 시스템', 숭실대학교 석사청구논문, 1995
6 D. O. Hebb, 'The Organization of Behavior,' John Wiley & Sons, New York, 1949
7 Gin-Der Wu, Chin-Teng Lin, 'A Recurrent Neural Fuzzy Network for Word Boundary Detection in Variable Noise-Level Environments,' IEEE Systems, Man and Cybernetics, Vol.31, No.1, pp.84-97, 2001   DOI   ScienceOn
8 Gin-Der Wu, Chin-Teng Lin, 'Word Boundary Detection with Mel-Scale Frequency Bank in Noisy Environment,' IEEE Speech and Audio Processing, Vol.8, No.5, pp 541-554, 2000   DOI   ScienceOn
9 J. C. Junqua, B. Mak and B. Reaves, 'A robust algorithm for word boundary detection in the presence of noise,' IEEE Trans. Speech Audio Processing, Vol.2, pp.406-412, 1994   DOI   ScienceOn
10 J. S. R. Jang, 'Self-learning fuzzy controllers based on temporal back propagation,' IEEE Trans. Neural Networks, Vol.3, pp.714-723, 1992   DOI   ScienceOn
11 C. F. Juang and C. T. Lin, 'An on-line self-constructing neural fuzzy inference network and its application,' IEEE Trans. Fuzzy System, Vol.6, pp.12-32, 1998   DOI   ScienceOn