An Efficient Cancer Prediction Mechanism Using SA and SVM

Cancer is one of the deadly diseases that involve abnormal cell growth with the capability to spread to all the parts of the body. Due to the extremeness of the disease, it is important to predict cancer in advance. Prediction of Cancer is difficult to perform accurately, due to the existence of the abnormalities, noise, and outliers in the data set. One of the important methods that could improve the efficiency and also the accuracy of the classifier in the process of cancer prediction is the feature selection. In feature selection only, the attributes that are most relevant participate in the process of classification. Cancer Prediction based on Simulated Annealing and Support Vector Machine algorithm (CP-SASVM) is being used where feature selector based on the principle of Simulated Annealing is being used and Support Vector Machine is being used for the classification purpose. By this process, we reduce the data dimensionality, and this leads to less complication in the network structure and thus increases efficiency in the processing of the data. By removing the irrelevant data, the accuracy of the classifier can be improved appreciably. The performance of the CP-SASVM is being compared with the performance of Cancer prediction using Linear Regression classifier (CP-LR). On comparison, CP-SASVM performs more efficiently and accurately than that of CP-LR.