Journal
IEEE TRANSACTIONS ON FUZZY SYSTEMS
Volume 19, Issue 5, Pages 983-988Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TFUZZ.2011.2130529
Keywords
Adaptive neurofuzzy inference system (ANFIS); prediction interval (PI); uncertainty
Funding
- Centre for Intelligent Systems Research at Deakin University
Ask authors/readers for more resources
The performance of an adaptive neurofuzzy inference system (ANFIS) significantly drops when uncertainty exists in the data or system operation. Prediction intervals (PIs) can quantify the uncertainty associated with ANFIS point predictions. This paper first presents a methodology to adapt the delta technique for the construction of PIs for outcomes of the ANFIS models. As the ANFIS models are linear in their consequent part, the ANFIS-based PIs are computationally less expensive than neural network (NN)-based PIs. Second, this paper proposes a method to optimize ANFIS-based PIs. Anew PI-based cost function is developed for the training of the ANFIS models. A simulated annealing-based algorithm is applied to minimize the new nonlinear cost function and adjust the premise and consequent parameters of the ANFIS model. Using three real-world case studies, it is shown that ANFIS-based PIs are computationally less expensive than NN-based PIs. The application of the proposed optimization algorithm leads to better quality PIs than optimized NN-based PIs.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available