Stacked Generalization Ensemble-Based Hybrid Gradient Boosted Model for Predicting Diabetes

DOI

10.2991/978-94-6463-529-4_23How to use a DOI?

Keywords

Light Gradient Boosting Machine (LGBM); data balancing; Staking approach; Ensemble; Extreme Gradient Boosting machine (XGB)

Abstract

In the modern world, diabetes is a very scary problem. It is a long-term condition that can lead to a number of health problems. It is a grouping of illnesses that cause blood sugar to be too high. Machine learning is being used more and more in the field of health care because of how quickly it is improving. The goal of this study is to find the most accurate way to predict how likely it is that a patient will get diabetes.

This article shows how to make the A Hybrid Stacked Generalization LGBM-XGB Model Based on Ensembles for Diabetes Prediction work well with computers. The suggested method predicts the start of diabetes early on by using a strategy based on stacking generalisation. This method uses the LGBM -Light Gradient Boosting Machine and the EGBM- Extreme Gradient Boosting Machine together (XGB). The Hybrid XGB-LGBM model works by making meta-data from the XGB and LGBM models so that the SMOTE technique for balancing data can be used to figure out the final predictions. Using two datasets from PIDD, the Stacked XGB-LGBM-SMOTE model is tested to see how well it works. The most important things that this study findings are: 1) An enhanced new hybrid ensemble-based approach is made; 2) The data balancing method is used successfully; and 3) A comparison of how well PIDD datasets work with and without data balancing models is done. Case studies have been done to show that the proposed enhanced model works superior to both the current benchmark methods and the hybrid stacked models.

Copyright

© 2024 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  - Priyabrata Sahu
AU  - Jibendu Kumar Mantri
PY  - 2024
DA  - 2024/10/04
TI  - Stacked Generalization Ensemble-Based Hybrid Gradient Boosted Model for Predicting Diabetes
BT  - Proceedings of the International Conference on Signal Processing and Computer Vision (SIPCOV-2023)
PB  - Atlantis Press
SP  - 253
EP  - 265
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-529-4_23
DO  - 10.2991/978-94-6463-529-4_23
ID  - Sahu2024
ER  -