Chaotic time series prediction with functional link extreme learning ANFIS (FL-ELANFIS)
- Resource Type
- Conference
- Authors
- Nhabangue, Moreira F. C.; Pillai, G. N.; Sharma, M. L.
- Source
- 2018 International Conference on Power, Instrumentation, Control and Computing (PICC) Power, Instrumentation, Control and Computing (PICC), 2018 International Conference on. :1-6 Jan, 2018
- Subject
- Components, Circuits, Devices and Systems
Computing and Processing
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Predictive models
Computational modeling
Firing
Artificial neural networks
Prediction algorithms
Training
Chaotic Series Prediction
Neuro-Fuzzy Systems
Extreme Learning
- Language
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.