期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2014
卷号：11
期号：2
出版社：IJCSI Press
摘要：The comparative genomics is the comparative study of the structure and function of genomes of different species. It allows to identifying, classifying and understanding the effects of selection on the organization and evolution of genomes. This new research benefits from the increasing number of sequenced genomes. Genomic sequences allow to classify organisms into different categories and classes which have significant biological knowledge and can justify the evolution and identification of unknown organisms. Our system consists in three phases. The first phase is called transformation which is composed of three steps; binary codification of DNA sequence, Fourier Transform and Power Spectrum Signal Processing. The second phase is called approximation. This phase is empowered by the use of Multi Library Wavelet Neural Networks (MLWNN).The third phase is called classification which is realized by applying the algorithm of hierarchical classification. The results of this contribution are more interesting in comparison with some others works, in terms of rate classification using Eukaryotic organisms database. This method permits to avoid the complexity problem of form and structure in different classes of organisms.
关键词：Classification; DNA sequence; Beta wavelet networks; Power Spectrum; Fourier Transform; Multi Library Wavelet Neural Networks.
