Welcome to IJSDR UGC CARE norms ugc approved journal norms IJRTI Research Journal | ISSN : 2455-2631
INTERNATIONAL JOURNAL OF SCIENTIFIC DEVELOPMENT AND RESEARCH International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.15 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Diabetes is a type of chronic disease that develops from lack of insulin in our body. In diabetes, this process is broken. The main forms of diabetes are type 1 and type 2, but there are other forms as well, including gestational diabetes, which develops during pregnancy. The use of various Machine Learning algorithms including K-Nearest Neighbors (KNN), random forests (RF), decision trees (DT), AdaBoost (AB), Naive Bayes classifier (NB), and XGBoost (XB), and preprocessing steps includes outlier rejection, filling in missing values, data standardization, and stratified K-fold validation to validate the results. To enhance the outcome, the weighted ensembling of various machine learning models are also suggested. For performance metric Area Under ROC Curve (AUC) is used. For further optimization in model's performance is done using GridSearch technique of hyperparameter tuning. In a publicly accessible Pima Indian Diabetes Dataset from Kaggle in which 768 female patients record is given and 268 are diabetic and 500 are non-diabetic.
"A Workflow Paper On Prediction of Type 2 Diabetes Using Ensemble Learning Method", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 5, page no.859 - 865, May-2023, Available :http://www.ijsdr.org/papers/IJSDR2305129.pdf
Downloads:
000222060
Publication Details:
Published Paper ID: IJSDR2305129
Registration ID:206230
Published In: Volume 8 Issue 5, May-2023
DOI (Digital Object Identifier):
Page No: 859 - 865
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631
Facebook Twitter Instagram LinkedIn