Performance Analysis of Enhanced Adaboost Framework in Multifacet medical dataset

Main Article Content

Dr. Sudharson D, P. Divya, DR.D.Palanivel Rajan, Ratheeshkumar A.M

Abstract

Predictions that are made based on features are performed through machine learning (ML) algorithms. Machine learning allows systems to learn and develop on their own by gaining experience. In the field of artificial intelligence, machine learning is a sub-discipline. Supervised and unsupervised learning are the two prevalent categories under machine learning. Supervised ML is used for classification whereas unsupervised ML is used for clustering. Currently, machine learning is being employed in a plethora of fields. Biometric recognition, handwriting recognition, and medical diagnosis are some of the use cases of ML. A significant role is played by machine learning in the medical field: identify diseases based on a patient's characteristics. Software applications based on ML algorithms are helping doctors in diagnosing various diseases like cancer, cardiac arrest, etc. We employed an ensemble learning strategy to predict heart problems in this paper. Through the comparison of different evaluation parameters namely ROC, F-measure, recall, precision and accuracy, our paper describes the performance of ML algorithms. The study used a mix of machine learning classifiers to predict heart problems, including Naive Bayes (NB), Decision Tree (DT), Random Forest (RF) and Support Vector Machine (SVM) algorithms. It was observed that implementing Paretto Distribution enabled adaboost resulted in 98.61% accuracy. NB, DT, RF and SVM models were also trained and tested separately.

Article Details

Section
Articles