Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 8 (2022) > Article

DOI: 10.14704/nq.2022.20.8.NQ44428

Decision Support for Recommendation system at Different Levels of Obesity Classification

A.Ramya, Dr.K.Rohini

Abstract

In recent days we are facing various health problems and getting affected to diseases due to environmental conditions and food habits. Earlier stage disease prediction helps the medical people to take quick actions to rectify the complications of getting into worse condition. Datamining is one of the technologies that provides decision support in medical prognosis. Datamining processes the data from patient datasets and yield new knowledgeable information out of it. This research work deals with Body Mass Index, which can be used to identify the intensity of obesity at its various levels. Many supervised machine learning algorithms such as Naïve Bayes, K-Neighbors, Extreme Gradient Boost, and Decision Tree classifiers. Effective implementation of the Algorithms with the Obesity dataset is done in Python. About 6000 patient data are applied to these algorithms and comparative charts of their accuracies are obtained. The proposed Modified Decision Tree Algorithm gives better Accuracy Result compared with the existing ones.

Keywords

ML – machine learning, BMI – Body mass index, Datamining, Obesity.

Full Text

PDF

References

?>