An Effectual Polycystic Ovarian Syndrome Detection Model Using SVM Optimization with Tabu Search

Dr.A. Kavitha and Neetha Thomas

Data mining is a field that uncover patterns from huge repositories has many applications like generating predictive models which is very advantageous with respect to medical industries. In specific, this research field concentrates on Polycystic Ovarian Syndrome which is a hormonal disorder which largely identified for women with reproductive age. To assist in the earlier prediction of PCOS, classification techniques like improved support vector machine and Tabu search can be utilized to categorize real time data of PCOS based on the training set established. In this investigation, a try has been made to contrast the performance metrics and accuracy of prior determined data mining techniques to predict whether an individual is likely to possess PCOS or not. The simulation will be carried out in MATLAB environment. The outcomes show that the proposed method is superior when compared to the prevailing methods.

Volume 12 | 04-Special Issue

Pages: 509-521

DOI: 10.5373/JARDCS/V12SP4/20201516