Comparative Analysis of Deep Learning and Machine Learning Techniques for Obesity Classification

DOI

10.2991/978-94-6463-716-8_27How to use a DOI?

Keywords

Machine learning; Obesity classification; Decision Tree; Deep learning; Logistic Regression; Support Vector Machine (SVM); Random Forest; XGBoost; Recurrent Neural Network (RNN); Neural Network; Overfitting

Abstract

The number of obese individuals has risen to alarming levels throughout the world and today obesity can be considered an illness that causes numerous diseases such as diabetes, cancer and heart disease. Effective Obesity classification can help in early detection of the disease and better planning of preventive measures for lifestyle diseases. The study aims to compare Machine Learning (ML) techniques: Logistic Regression, Decision Tree, Random Forest, XGBoost and Support Vector Machine (SVM) with Deep Learning models: Recurrent neural network (RNN) and Neural network for obesity classification using anthropometric data and lifestyle. The dataset which is used here has features of age, gender, weight, height, body mass index (BMI) and physical activity level. Pre-processed the data (scaling, missing value treatment), to deal with them before model training. We determine the performance of each model through accuracy, precision, recall and F1-score with respect to three obesity categories: normal weight, overweight, and obese. Although models like Decision Tree, Random Forest and XGBoost reached an accuracy of 1.0000 which indicates they are overfitting to the data at hand hence their poor generalization capability. Deep learning models, especially the RNN (which captures long-term non-linear dependencies in time), generally outperformed traditional machine-learning techniques thanks to their ability to make more general conclusions without overfitting. The current research unveils the promise in those techniques, with future work required to mitigate overfitting and mixed hybrid models for additional reliability during practical healthcare deployments.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Prince Chauhan
AU  - Shilpee Srivastava
PY  - 2025
DA  - 2025/05/26
TI  - Comparative Analysis of Deep Learning and Machine Learning Techniques for Obesity Classification
BT  - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025)
PB  - Atlantis Press
SP  - 335
EP  - 348
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-716-8_27
DO  - 10.2991/978-94-6463-716-8_27
ID  - Chauhan2025
ER  -