LDA and SVM performance evaluation for diabetes prediction.
In: AIP Conference Proceedings; 2024, Vol. 3070 Issue 1, p1-7, 7p; Jg. 3070 (2024-04-06) 1, S. 1-7
Konferenz
Zugriff:
Diabetes mellitus has no remedy at the moment. Diabetes mellitus is a fatal condition that can lead to heart failure, kidney disease, unhealed wounds, and other consequences. Precautions are one option that can be used to combat this condition. Using artificial intelligence, this project aims to develop an early detection system for diabetes mellitus. In this article, researchers employ a combination of two machine learning algorithms to diagnose diabetes: Linear Discriminant Analysis (LDA) as the model to extract the important information from the dataset and Support Vector Machines (SVM) as a classifier model. The main target of this study is to find the best classification model for identifying diabetes. The LDA-SVM approach for identifying diabetes is also described in this work, as well as its implementation and performance. The PIMA Indian Diabetes dataset was used to conduct the experiment in this case. In addition, to find the optimum parameters and develop the best model, we employ a cross-validation approach as many as 10 fold. The conclusion of this study is that LDA-SVM successfully detected diabetes using sigma = -4.5 with a result of accuracy value of 77.34%, a result of sensitivity of 73.507%, and a result of specificity of 79.60%. [ABSTRACT FROM AUTHOR]
Copyright of AIP Conference Proceedings is the property of American Institute of Physics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Titel: |
LDA and SVM performance evaluation for diabetes prediction.
|
---|---|
Autor/in / Beteiligte Person: | Abdillah, Abdul Azis ; Azwardi, Azwardi ; Wahyudi, Imam ; Arifin, Samsul ; Ibrahim, Muhammad Amien ; Mauritsus, Tuga |
Quelle: | AIP Conference Proceedings; 2024, Vol. 3070 Issue 1, p1-7, 7p; Jg. 3070 (2024-04-06) 1, S. 1-7 |
Veröffentlichung: | 2024 |
Medientyp: | Konferenz |
ISSN: | 0094-243X (print) |
DOI: | 10.1063/5.0198841 |
Schlagwort: |
|
Sonstiges: |
|