An Evolutionary-Based Adaptive Neuro-Fuzzy Expert System as a Family Counselor before Marriage with the Aim of Divorce Rate Reduction

Abstract

Due to the growth of divorce rate in developed and developing countries, and with the aim of reducing this phenomenon, an evolutionary-based Adaptive Neuro-Fuzzy Expert System as a family counselor before marriage is developed. The main goal is to combine evolutionary algorithms with fuzzy logic, and inferring nature inspired results for this kind of natural event (divorce). For validating results, a dataset from a human expert (marriage counselor) has been received, which described thoroughly in section IV in details. This dataset has been trained and tested with different Meta-heuristic optimization algorithms like (ACO, DE, PSO and GA) and neural network training methods like (Hybrid and back-propagation). Error factors like (MSE, RMSE, Error Mean and Error STD) will be calculate for each one of these approaches as validation results. Also, classification results with MLP algorithm, made this paper more detailed. Validation processes returned promising results and opened a way to use this kind of counselor expert system in the absence of human expert conditions. Dream to day which all the children grow up with their original parents.