The emergence of DNA microarray technologies leads to significant advances in molecular biology. Time-course gene expression data are often measured in order to study dynamic biological systems and gene regulatory networks. It is believed that genes demonstrating similar expression profiles over time might give an informative insight into how underlying biological mechanisms work. This importance leads that in microarray gene research, statistical and intelligent models have received considerable attention to analyze complex time-course gene expression data. Recently, various classification models have been applied in order to find genes which show similar periodic pattern expression. In this paper, we consider the classification of gene expression in temporal expression patterns; then propose an Intelligent hybrid classification model, in which an artificial neural network is combined with a multiple linear regression model to classify genes data. Empirical results show that the proposed model can yield more accurate results than other well-known statistical and intelligent classification models. Therefore, it can be applied as an appropriate approach for classification of gene expression data.