Modified Honey Bee Optimization for recurrent neuro-fuzzy system model

This paper presents a Mamdani recurrent neuro-fuzzy system model (MRNFS), using modified Honey Bee Optimization (HBO). In the basic version of HBO, the algorithm performs a kind of neighborhood search combined with random search; hence it has the capability of achieving global optimum. To improve the local search ability of HBO and help the algorithm to jump out from the local optimum, a modification is performed by applying three kinds of crossovers to the elite individuals. To verify the performance of the proposed method, this method is applied to some identification and prediction benchmarks and its performance compared with the basic HBO, Gradient descent (GD), Differential Evolution (DE) and Particle swarm optimization (PSO), in training the MRNFS model.