A feature clustering-based adaptive modular neural network for nonlinear system modeling. (May 2020)

• Record Type: Journal Article
• Authors: Li, Wenjing; Li, Meng; Qiao, Junfei; Guo, Xin
• Is Part Of: ISA transactions. Volume 100(2020)
• Page Start: 185
• Page End: 197
• Publication Date: 2020-05
• Subjects: Modular neural network -- Feature clustering -- Nonlinear system modeling -- RBF neural network -- Bayesian method; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2019.11.015
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: To improve the performance of nonlinear system modeling, this study proposes a feature clustering-based adaptive modular neural network (FC-AMNN) by simulating information processing mechanism of human brains in the way that different information is processed by different modules in parallel. Firstly, features are clustered using an adaptive feature clustering algorithm, and the number of modules in FC-AMNN is determined by the number of feature clusters automatically. The features in each cluster are then allocated to the corresponding module in FC-AMNN. Then, a self-constructive RBF neural network based on Error Correction algorithm is adopted as the subnetwork to study the allocated features. All modules work in parallel and are finally integrated using a Bayesian method to obtain the output. To demonstrate the effectiveness of the proposed model, FC-AMNN is tested on several UCI benchmark problems as well as a practical problem in wastewater treatment process. The experimental results show that the FC-AMNN can achieve a better generalization performance and an accurate result for nonlinear system modeling compared with other modular neural networks. Highlights: All modules in FC-AMNN work in parallel to complete a complicated task. Input matrix is decomposed along the dimension of features in FC-AMNN. The structure of FC-AMNN is adaptively determined without predefinition. FC-AMNN improves the generalization ability and prediction accuracy.