Cardiovascular Risk Detection Using Cr-Hom Hybrid Optimization Algorithm And Machine Learning Techniques
Main Article Content
Abstract
Cardiovascular Disease Deaths Are Increasing Day By Day And Causes Very Serious Issues Among Human Rise. Recent Survey Report Demonstrates That The Death Rates Are Rapidly Increasing With Bases Of Many Health Issues. The Patients Who Are Effected With Kidney Disease Have Nearly 50 Percentage Of Chance To Cause Cardiovascular Problems. Most Of The Research Work Focuses Only On Predicting Risk Factors Of Kidney Diseases, Were This Papers Also Focuses On Factors Which Are Responsible For Cardiovascular Deaths. Early Prediction Of Such Problems May Solve Death Ratio Problems. A Proposed Hybrid Algorithmic Technique (Cr-Hom) Which Is Used For Predicting The Disease In Early Stage. Initial Stage Of Feature Extraction Process Is Carried Out With Modified Tug Of War (Mtw) Algorithm. The Process Not Only Selects The Necessary Features It Also Helps In Improving The Accuracy Of Proposed Algorithm. The Step Followed After Selecting The Necessary Feature Is Ruzzo Tompa Memetic Based Deep Neural Network (Rtm-Dnn), Which Is Very Useful In Classifying The Cardiovascular Risk Factors. The Proposed Cr-Hom Technique Can Analyze With Different Standard Datasets And Compare The Performance With Existing State-Of-Art Techniques In Terms Of Accuracy, Precision, F-Measure And Recall. The Proposed Algorithm’s Performance Is Best Compared To That Of Other Existing Algorithms.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.