Improve the performance of cancer and diabetes detection using novel technique of machine learning

EasyChair Preprint 2332

Abstract

These system allow the user to make a use of algorithms to predict the risk of diabetes in human body. The various classification models such as Decision Tree, artificial Neural Networks, Logistic Regression, Association rules and Naive Bayes are used in this system. Then the Random Forest technique is used to find the accuracy of each model in the project. The dataset used is the Pima Indians Diabetes Data Set, which has the information of patients, some of them have developing diabetes therefore, this project is aimed to create a mobile application for predicting a person’s class whether present in of the diabetes and cancer risk or not. In this study, we have analyzed medical data using several classification algorithms in order to optimize classifier performance for cancer and diabetes prediction. For this project we have guidance letter from “Max Care Hospital” under support of medical oncologist Dr. Satish Sonawane (oncologist ) to study the medical history of patients and their medical reports.

Keyphrases: ANN, Decision Tree, ELM, health care

@booklet{EasyChair:2332,
  author    = {Samrudhi R. Kaware and Vinod S. Wadne},
  title     = {Improve the performance of cancer and diabetes detection using novel technique of machine learning},
  howpublished = {EasyChair Preprint 2332},
  year      = {EasyChair, 2020}}