Issue |
ITM Web Conf.
Volume 56, 2023
First International Conference on Data Science and Advanced Computing (ICDSAC 2023)
|
|
---|---|---|
Article Number | 05015 | |
Number of page(s) | 5 | |
Section | Machine Learning & Neural Networks | |
DOI | https://doi.org/10.1051/itmconf/20235605015 | |
Published online | 09 August 2023 |
Diabetes Mellitus Prediction Using Ensemble Machine Learning Techniques
Department of Information Technology, Vignan’s Foundation for Science Technology and Research, Guntur, India
madhudontha@gmail.com
sridhathri.1021@gmail.com
Diabetes Mellitus most called has Diabetes is a type of acute endocrine chronic disease which is the major problem in many individuals either through hereditary or from the trends of the human life style. It elevates the blood sugars in the body due to endocrine issues. This increase in blood sugar does not only affect its levels but even causes many health issues related to kidney, liver functions, blood pressure and eye damage etc. This is most common in the smaller age group, and for the age group above 45 years. Almost 68 percent people in our country suffer from these diabetics. This can be avoided or eradicated when it is predicted near to the levels. With the scenario it is considered has the severe problem and it needs to be controlled at any cost. Combining the technology of Computer Science, we use Machine Learning techniques to predict the diabetes at early stage with a greater accuracy. Here we use different classifiers namely K-Nearest, Naive Bayes (NB), XG Boost, Decision Tree (DT) and Random Forest (RF) from the provided data sets and detect its accuracy. Among those we found Random Forest to be more suitable for higher precision calculation in comparison with other different techniques.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.