Radial Basis Function Networks With Linear Interval Regression Weights for Symbolic Interval Data

• Published in: IEEE transactions on cybernetics 2012-02, Vol.42 (1), p.69-80
• Main Authors: Shun-Feng Su, Chen-Chia Chuang, Tao, C. W., Jin-Tsong Jeng, Chih-Ching Hsiao
• Format: Article
• Language: English
• Subjects: Algorithms; Argon; Clustering algorithms; Computer Simulation; Data models; Intervals; Learning; Linear interval regression weights; Linear regression; Mathematical models; Mean square errors; Models, Theoretical; Monte Carlo methods; Networks; Neural Networks (Computer); Partitioning algorithms; Radial basis function; Radial basis function networks; radial basis function networks and interval competitive agglomeration clustering algorithm; Regression; Regression Analysis; Signal Processing, Computer-Assisted; Studies; symbolic interval-valued data; Upper bound
• ISSN: 1083-4419; 2168-2267; 1941-0492; 2168-2275
• DOI: 10.1109/TSMCB.2011.2161468

This paper introduces a new structure of radial basis function networks (RBFNs) that can successfully model symbolic interval-valued data. In the proposed structure, to handle symbolic interval data, the Gaussian functions required in the RBFNs are modified to consider interval distance measure, and the synaptic weights of the RBFNs are replaced by linear interval regression weights. In the linear interval regression weights, the lower and upper bounds of the interval-valued data as well as the center and range of the interval-valued data are considered. In addition, in the proposed approach, two stages of learning mechanisms are proposed. In stage 1, an initial structure (i.e., the number of hidden nodes and the adjustable parameters of radial basis functions) of the proposed structure is obtained by the interval competitive agglomeration clustering algorithm. In stage 2, a gradient-descent kind of learning algorithm is applied to fine-tune the parameters of the radial basis function and the coefficients of the linear interval regression weights. Various experiments are conducted, and the average behavior of the root mean square error and the square of the correlation coefficient in the framework of a Monte Carlo experiment are considered as the performance index. The results clearly show the effectiveness of the proposed structure.