SMO classification for cervical cancer dataset by applying various kernels
Ayyappan G., K. Sivakumar · Indian Journal of Computer Science and Engineering · 2019
This research work presents a decision making of healthcare operational system by using machine learning classifiers algorithm to predict the decision making in comparison to the actual decision making.This model may help to doctor for making the best decisions.This model helps us to prediction of indicators/diagnosis of cervical cancer.This study explains utilization of machine learning algorithms in determination of medical operation methods.This dataset focuses on the prediction of indicators/diagnosis of cervical cancer.The results show that SMO in RBF Kernel parameter for this case study generates highest accuracy level of 87.5%.I. INTRODUCTION Machine learning in today's healthcare is unavoidable.Optimists predict that machine learning and artificial intelligence will diagnose disease better and earlier, treat illness more precisely and engage patients more efficiently in future healthcare.In recent years instances in healthcare such as medical image processing and analyzing, predicting healthcare operational decisions, dosage trials for intravenous tumor treatment detection and management of prostate cancer.In this paper organizes section one has related works and brief introduction of this fields, section two presents Materials and Methods, the section three describes results and discussions and the section four presents conclusion. II. MATERIALS AND METHODSIn this section presents the materials and methods of this research work.Here the dataset borrowed from https://archive.ics.uci.edu/ml/datasets/Cervical+cancer+%28Risk+Factors%29# .In this dataset contains information about The dataset comprises demographic information, habits, and historic medical records of 858 patients.In this research work applied in weka 3.8.3version for SMO classification method by applying various kernels namely Polykernel, Normalized Polykernel, Puk, and RBF Kernel were applied to calculate for predicting caesarian section operational decisions