Backpropagation based training algorithm for Takagi - Sugeno type MIMO neuro-fuzzy network to forecast electrical load time series

IEEE International Conference on Fuzzy Systems

Volumn 1, Issue , 2002, Pages 86-91

  Palit, Ajoy Kumar ^a   Doeding, Gerhard ^a   Anheier, Walter ^b   Popovic, Dobrivoje ^b  

^a deneg GmbH   (Germany)

^b UNIVERSITY OF BREMEN   (Germany)

Author keywords

Backpropagation algorithm; Electrical load time series; Forecasting; MIMO neuro fuzzy network; Takagi Sugeno model

Indexed keywords

BACKPROPAGATION ALGORITHM; SUM SQUARED ERROR; TAKAGI-SUGENO MODEL; TRAINING ALGORITHM;

BACKPROPAGATION; ELECTRIC LOAD FORECASTING; ERROR ANALYSIS; FEEDFORWARD NEURAL NETWORKS; FUZZY SETS; GRADIENT METHODS; MATHEMATICAL MODELS; MEMBERSHIP FUNCTIONS; MULTILAYER NEURAL NETWORKS; PARAMETER ESTIMATION; PERFORMANCE; TIME SERIES ANALYSIS;

LEARNING ALGORITHMS;

EID: 0036456215     PISSN: 10987584     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (6)

1. L. X. Wang, and J. M. Mendel, "Back-Propagation Fuzzy System as Nonlinear Dynamic System Identifiers," ISBN: 0-7803-0236-2/92 IEEE, FUZZ-IEEE 1992, pp. 1409-1418.
2. A. K. Palit, and D. Popovic, "Forecasting Chaotic Time Series Using Neuro-Fuzzy Approach," IEEE-IJCNN 199, 10-16th July, 1999, Washington D.C., USA, pp. 1538 - 1543, paper no. - 88, CD ROM proceedings.
3. A. K. Palit, and R. Babuška, "Efficient training algorithm for Takagi-Sugeno type Neuro-fuzzy network," FUZZ-IEEE 2001, Melbourne, Australia, 2nd-5th December, 2001, paper no. - P382, CD ROM proceedings.
4. D. Popovic, and D. Xiaosong, "Structural Optimization of Neural Networks for Modeling," SYSID 1997, 11th IFAC Symposium on System Identification, Fukuoka, Japan, 8-11 July 1997, pp. 771-775 (invited paper).
5. M. Setnes, R. Babuška, U. Kaymark, et al., "Similarity measures in fuzzy rule base simplification," IEEE Transaction on System, Man and Cybernetics, 1998, Part-B, Vol. 28, June 1998, pp. 376-386.
6. A. K. Palit, "Training Takagi-Sugeno Type Multi-Input Multi-Output Neuro-Fuzzy Networks with the Levenberg-Marquardt Algorithm to Generate Long Term Forecasts of Electrical Load Time Series," Technical Report - TR-NF01-2002, January 2002, deneg GmbH, Bremen, Germany.