Effective Identification and Prediction of Breast Cancer Gene Using Volterra Based LMS/F Adaptive Filter

摘要

Cancer is a widespread hereditary disease in human beings and accounts for lots of deaths in the world. Early identification of the disease plays a significant role in picking the best treatment. Present work proposes a model which is based on the concept of Least Mean Square/Fourth (LMS/F) adaptive filtering algorithm along with the Volterra expansions of the input sequence. We have incorporated Trigonometric mapping along with (VLMS/F) filter to improve the prediction properties of breast cancer genes. Based on the value of MSE the decision is taken whether the anonymous target input sequence is cancer or healthy one. The proposed VLMS/F filter is tested on 10 breast cancers and 10 breast healthy benchmark genes available in GenBank. The MSE values for cancer and for all healthy case, the value is found to be >0.1 and <0.1, respectively. Thus the algorithm gives a satisfactory result.