APPLICATION OF MULTIPLE MACHINE LEARNING TECHNIQUES IN CLASSIFYING OBESITY LEVEL USING MULTIVARIATE DATASET

Main Article Content

Jayvee Ryan Banal
Kenneth Dynielle Lawas
Laurice M. Mariquina

Abstract

People's health is important. It must be preserved. There are a variety of issues that might contribute to a person's health, including their lifestyle. One of the most prominent concerns during this pandemic is a person's body weight, which is particularly significant these days. Obesity is one of those body diseases about which it is important to be aware of the reasons. This study intends to create different machine learning models to define what causes obesity, select the most appropriate model that did the best, and discuss how accurate it performed. It can also be used in determining the how the obesity impact in our daily lives. Through the use of different machine learning models such as KNN, Random Forest, Gradient Boosting and Ada Boost, the study be able to obtain the appropriate model. Despite being trained on unbalanced data, the classifiers utilized were able to predict the properties of the presented datasets that Random Forest has an accuracy of 83.6%.


Keywords—Obesity, Datasets, Machine Learning, Random Forest, Gradient Boosting, KNN

Downloads

Download data is not yet available.

Article Details

Section
Articles
Author Biographies

Jayvee Ryan Banal

Batangas State University

Alangilan, Batangas, Philippines

Kenneth Dynielle Lawas

Laguna State Polytechnics University

San Pablo, Laguna, Philippines

Laurice M. Mariquina

City College of Calamba

Calamba City, Laguna, Philippines