Comparison of prediction of obesity status based on different machine learning approaches with different factor quantities

Guanlan Shao

doi:10.1117/12.2660726

6 December 2022 Comparison of prediction of obesity status based on different machine learning approaches with different factor quantities

Guanlan Shao

Author Affiliations +

Proceedings Volume 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022); 124583U (2022) https://doi.org/10.1117/12.2660726
Event: International Conference on Biomedical and Intelligent Systems, 2022, Chengdu, China

Abstract

Contemporarily, obesity, as a chronic disease, has seriously affected the quality of daily life and attracted the attention of scholars. This research will investigate 2111 observations on eating habits and behaviour patterns of obesity based on five machine learning approaches (Decision Tree (DT), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Random Forest (RF) and Extremely Randomized Trees (ERT) models). By adding 16 factors in the data into five models successively according to their correlation with obesity level from strong to weak, one explores the impact of different factor quantities on the prediction of obesity status. According to the three metrics of accuracy score, Kappa score and Matthews correlation coefficient, the classification effect of the five models tended to be stable and saturated when the quantity of factors reached a certain value. Additionally, the accuracy of the model classification will be greatly improved when the correlation coefficients between the new factor and the added factors are small. Meanwhile, among the five models, XGBoost model has the best classification effect under 14 factors, with an accuracy of 97.16%. The research of this paper further explores the classification effects of different models on obesity status under different factor quantities. Overall, these results shed light on guiding the related research of the internal relationship between different factor quantities and the classification effect of different machine learning approaches.

Citation Download Citation

Guanlan Shao "Comparison of prediction of obesity status based on different machine learning approaches with different factor quantities", Proc. SPIE 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022), 124583U (6 December 2022); https://doi.org/10.1117/12.2660726

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Machine learning

Analytical research

Performance modeling

Statistical modeling

Computer programming languages

Data analysis

Show All Keywords

Keywords/Phrases

Search In:

Publication Years