A DSP technique for prediction of cancer cell

Abstract

At present cancer is an alarmed disease. According to medical research, central cause of cancer is due to the genetic abnormality. Most cancers are generated due to permanent change in the deoxyribonucleic acid (DNA). For the past two decades, genomic signal processing (GSP) is a vital area of research. It has engrossed the consideration of digital signal processing (DSP) researchers for the massive amount of data accessible in the public data base. By finding out the DNA sequence for cancer cells & normal cells of human beings & applying some digital signal processing (DSP) approaches on both, difference between them can be found. Previously, discrete Fourier transform (DFT) power spectrum was used to predict cancer cells of a DNA sequence. In this paper, discrete cosine transform (DCT) and discrete sine transform (DST) approaches are presented as an alternative to analyze the spectral characteristics of cancer cells and normal cells. Further, post-processing is done using digital IIR low pass filter to improve the discrepancy between cancer and normal cells. The proposed method is tested for a number of data sets available in Gene Bank.