Ashraf Osman Ibrahim

Multiobjective Differential Evolutionary Neural Network for Multi Class Pattern Classification

In this paper, a Differential Evolution (DE) algorithm for solving multiobjective optimization problems to solve the problem of tuning Artificial Neural Network (ANN) parameters is presented. The multiobjective evolutionary used in this study is a Differential Evolution algorithm while ANN used is Three-Term Backpropagation network (TBP). The proposed algorithm, named (MODETBP) utilizes the advantages of multi objective differential evolution to design the network architecture in order to find an appropriate number of hidden nodes in the hidden layer along with the network error rate. For performance evaluation, indicators, such as accuracy, sensitivity, specificity and 10-fold cross validation are used to evaluate the outcome of the proposed method. The results show that our proposed method is viable in multi class pattern classification problems when compared with TBP Network Based on Elitist Multiobjective Genetic Algorithm (MOGATBP) and some other methods found in literature. In addition, the empirical analysis of the numerical results shows the efficiency of the proposed algorithm.

Hybrid NSGA-II of Three-Term Backpropagation network for multiclass classification problems

Hybridization has become one of the current focuses of new research areas of the evolutionary algorithms over the past few years. Hybridization offers better speed of convergence to the evolutionary approach and better accuracy of the final solutions. This paper presents a hybrid non-dominated sorting genetic algorithm-II (NSGA-II) to optimize Three-Term Backpropagation (TBP) network in terms of two objectives which are: accuracy and complexity of the network. Backpropagation algorithm (BP) is often used as a local search algorithm and when combined with NSGA-II, the performance of NSGA II is enhanced due to the improvement of the individuals in the population. The experimental results show that the proposed method is effective in multiclass classification problems. The results of the hybrid approach to the classification problems are compared with multiobjective genetic algorithm based TBP network (MOGATBP) and some methods found in the literature. Moreover, the results indicate that the proposed method is a potentially useful classifier for enhancing classification process ability.