Particle Swarm Optimization of MLP for the identification of factors related to Common Mental Disorders

• Published in: Expert systems with applications Vol. 40; no. 11; pp. 4648 - 4652
• Main Authors: Ludermir, Teresa B., de Oliveira, Wilson R.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Ltd 01-09-2013; Elsevier
• Subjects: Applied sciences; Architecture; Artificial intelligence; Common Mental Disorder; Computational efficiency; Computer science; control theory; systems; Connectionism. Neural networks; Culture; Exact sciences and technology; Flows in networks. Combinatorial problems; Learning theory; Mental disorders; Networks; Neural Network Optimization; Neural networks; Operational research and scientific management; Operational research. Management science; Optimization; Particle Swarm Optimization; Particle Swarm Optimization; Common Mental Disorder; Neural Network Optimization; Costs; Social class; Network management; Neural network; Economic development; Particle swarm optimization; Weighted graph; Classification; Mental disorder; Swarm intelligence; Early stopping; Culture; Optimal flow
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2013.02.003

► We introduce a method, called PSO-PSO:WD. ► PSO-PSO:WD optimizes architecture and weights of ANNs using PSO with early stopping. ► PSO-PSO:WD identifies factors related to Common Mental Disorder. ► PSO-PSO:WD obtained good experimental results. ► The correct classification of the individuals with positive diagnose for the CMDs was of 90.59%.
Social class differences in the prevalence of Common Mental Disorder (CMD) are likely to vary according to time, culture and stage of economic development. The present study aimed to investigate the use of optimization of architecture and weights of Artificial Neural Network (ANN) for identification of the factors related to CMDs. The identification of the factors was possible by optimizing the architecture and weights of the network. The optimization of architecture and weights of ANNs is based on Particle Swarm Optimization with early stopping criteria. This approach achieved a good generalization control, as well as similar or better results than other techniques, but with a lower computational cost, with the ability to generate small networks and with the advantage of the automated architecture selection, which simplify the training process. This paper presents the results obtained in the experiments with ANNs in which it was observed an average percentage of correct classification of individuals with positive diagnostic for the CMDs of 90.59%.