An intelligent computational model in adaptability evaluation

In this study, a modify approach based on neural network and fuzzy logic technologies (MFNN) was presented for adaptability evaluation to allow for the incorporation of both heuristics and deep knowledge to exploit the best characteristics of each. The model is front-network which comprised with five layers architecture which composed of dynamic inference of fuzzy rules where the consequent sub-models are implemented by recurrent neural networks with internal feedback paths and dynamic neuron synapses. The detail excitated function and dynamic inference fuzzy membership function for MFNN model are suggested. Training of the LF-DFNN models is achieved using an optimal on-line learning scheme with the evaluation guide line which error data are embed. Extensive experiment results demonstrate that our models exhibit superior performance exhibits some interesting features such as enhanced representation power, local modeling characteristics, model parsimony, and stable learning compared to other adaptability evaluation models.