Skip navigation
Please use this identifier to cite or link to this item: http://repository.iitr.ac.in/handle/123456789/17059
Title: Chaotic time series prediction with functional link extreme learning ANFIS (FL-ELANFIS)
Authors: Nhabangue M.F.C.
Pillai, Gopinatha Nath
Sharma, Mukat Lal
Published in: Proceedings of 2018 IEEE International Conference on Power, Instrumentation, Control and Computing, PICC 2018
Abstract: In this paper, a combined model Functional Link Extreme Learning ANFIS is proposed to predict chaotic systems. The model incorporates the concept of functional link neural network (FLNN) to the Extreme Learning ANFIS providing enhanced performance results. The premise parameters are randomly selected subjected to certain constraints and the consequent parameters are trained using Moore-Penrose inverse providing good prediction results in a short time. The combined model is used for multi-step-ahead prediction and simulation results shows that the model obtains improved performance when compared with other models. © 2018 IEEE.
Citation: Proceedings of 2018 IEEE International Conference on Power, Instrumentation, Control and Computing, PICC 2018, (2018), 1- 6
URI: https://doi.org/10.1109/PICC.2018.8384761
http://repository.iitr.ac.in/handle/123456789/17059
Issue Date: 2018
Publisher: Institute of Electrical and Electronics Engineers Inc.
Keywords: Chaotic Series Prediction
Extreme Learning
Neuro-Fuzzy Systems
ISBN: 9.78E+12
Author Scopus IDs: 57202991516
7005839948
7403269008
Author Affiliations: Nhabangue, M.F.C., Department of Electrical Engineering, Indian Institute of Technology, Roorkee, India
Pillai, G.N., Department of Electrical Engineering, Indian Institute of Technology, Roorkee, India
Sharma, M.L., Department of Electrical Engineering, Indian Institute of Technology, Roorkee, India
Appears in Collections:Conference Publications [EE]
Conference Publications [EQ]

Files in This Item:
There are no files associated with this item.
Show full item record


Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.