Obesity Risk Prediction using Machine Learning

IEEE BASE PAPER TITLE:

DeepHealthNet: Adolescent Obesity Prediction System Based on a Deep Learning Framework

IEEE BASE PAPER ABSTRACT:

The global prevalence of childhood and adolescent obesity is a major concern due to its association with chronic diseases and long-term health risks. Artificial intelligence technology has been identified as a potential solution to accurately predict obesity rates and provide personalized feedback to adolescents. This study highlights the importance of early identification and prevention of obesity-related health issues. To develop effective algorithms for the prediction of obesity rates and provide personalized feedback, factors such as height, weight, waist circumference, calorie intake, physical activity levels, and other relevant health information must be taken into account. Therefore, by collecting health datasets from 321 adolescents who participated in Would You Do It! application, we proposed an adolescent obesity prediction system that provides personalized predictions and assists individuals in making informed health decisions. Our proposed deep learning framework, DeepHealthNet, effectively trains the model using data augmentation techniques, even when daily health data are limited, resulting in improved prediction accuracy (acc: 0.8842). Additionally, the study revealed variations in the prediction of the obesity rate between boys (acc: 0.9320) and girls (acc: 0.9163), allowing the identification of disparities and the determination of the optimal time to provide feedback. Statistical analysis revealed that the performance of the proposed deep learning framework was more statistically significant (p<0.001) compared to the other general models. The proposed system has the potential to effectively address childhood and adolescent obesity.

PROJECT OUTPUT VIDEO:

ALGORITHM/ MODEL USED:

XGBoost Classifier, Stacking Classifier

OUR PROPOSED ABSTRACT:

Obesity has become one of the leading public health concerns globally, contributing to various chronic conditions like diabetes, cardiovascular diseases, and certain cancers. Early identification of obesity risk is crucial for implementing preventive measures and personalized health interventions. This project presents a machine learning-based approach to predict obesity risk using two advanced classification models: XGBoost Classifier and Stacking Classifier. The system uses Python as the coding language, with Flask as the web framework, and an intuitive front-end built using HTML, CSS, and JavaScript.

Two powerful machine learning models, XGBoost Classifier and Stacking Classifier, were employed in the system to enhance the accuracy of predictions. The XGBoost Classifier, known for its gradient boosting capabilities and efficient handling of large datasets, achieved a perfect training accuracy of 100% and a test accuracy of 98%. Similarly, the Stacking Classifier, which combines multiple base models to improve predictive performance, also achieved 100% training accuracy and 98% test accuracy. These results demonstrate the robustness and reliability of the proposed system in predicting obesity risk with high precision.

The dataset used in the project contains 2,111 instances and 17 attributes, representing various physical, lifestyle, and demographic factors that contribute to obesity. These attributes include variables such as body mass index (BMI), physical activity levels, eating habits, and age, among others. The models were trained to classify individuals into the aforementioned seven obesity categories, allowing for a comprehensive assessment of obesity risk. This predictive tool aims to assist healthcare providers in early diagnosis and prevention, offering a data-driven approach to combating the global obesity epidemic.

By integrating advanced machine learning techniques with a user-friendly web interface, this project provides a valuable resource for both healthcare professionals and individuals seeking to monitor and manage their obesity risk. The combination of high accuracy in predictions and ease of access makes this system an effective tool for public health initiatives, enabling timely interventions and personalized recommendations based on individual risk profiles.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED.
Input Devices : Keyboard, Mouse.
Ram : 8 GB.

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.12.0.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

Ji-Hoon Jeong, Associate Member, IEEE, In-Gyu Lee , Sung-Kyung Kim , Tae-Eui Kam, Seong-Whan Lee , Fellow, IEEE, and Euijong Lee, “DeepHealthNet: Adolescent Obesity Prediction System Based on a Deep Learning Framework”, IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, VOL. 28, NO. 4, APRIL 2024.

Python IEEE Projects

Obesity Risk Prediction using Machine Learning