Application Of Wavelets To Improve Cancer Diagnosis Model In High Dimensional Linguistic DNA Microarray Datasets

DNA microarray datasets suffer scaling and uncertainty problems. This paper develops a model that manages DNA microarray datasets challenges more precisely by using the advantages of Wavelet decomposition and fuzzy numbers. For this aim, the proposed method is utilized to classify linguistic DNA microarray datasets set, where datasets can be given as linguistic genes. Linguistic genes are represented by using triangular fuzzy numbers provided as LR (left-right) fuzzy numbers. Then the WABL method is applied as the defuzzification method. Also, a set of orthogonal wavelet detail coefficients based on wavelet decomposition at different levels is extracted to specify the localized genes of DNA microarray datasets. Three DNA microarray datasets are used to evaluate this method. The experiments are shown that the proposed model has better diagnostic accuracy than other methods.