Version 1
: Received: 17 October 2024 / Approved: 18 October 2024 / Online: 18 October 2024 (10:48:37 CEST)
How to cite:
Samreen, S. Autoencoder and Harris Hawk Optimization Based Timely and Accurate Prediction of Diabetes Using a Minimal-Sized Feature Set. Preprints2024, 2024101458. https://doi.org/10.20944/preprints202410.1458.v1
Samreen, S. Autoencoder and Harris Hawk Optimization Based Timely and Accurate Prediction of Diabetes Using a Minimal-Sized Feature Set. Preprints 2024, 2024101458. https://doi.org/10.20944/preprints202410.1458.v1
Samreen, S. Autoencoder and Harris Hawk Optimization Based Timely and Accurate Prediction of Diabetes Using a Minimal-Sized Feature Set. Preprints2024, 2024101458. https://doi.org/10.20944/preprints202410.1458.v1
APA Style
Samreen, S. (2024). Autoencoder and Harris Hawk Optimization Based Timely and Accurate Prediction of Diabetes Using a Minimal-Sized Feature Set. Preprints. https://doi.org/10.20944/preprints202410.1458.v1
Chicago/Turabian Style
Samreen, S. 2024 "Autoencoder and Harris Hawk Optimization Based Timely and Accurate Prediction of Diabetes Using a Minimal-Sized Feature Set" Preprints. https://doi.org/10.20944/preprints202410.1458.v1
Abstract
Timely diagnosis of diabetes helps in avoiding the major risks associated with the disorder. The proposed research involves the prediction of the disorder using a minimal sized and most representative feature set generated using automatic feature extraction through an autoencoder followed by a meta-heuristic feature selection of minimal size using Harris Hawk Optimization that predicts the onset of Diabetes with best accuracy. Specifically, the proposed method uses various classifiers like Support Vector Classifier, Logistic Regression, Decision Trees and Random Forest along with a stacking ensemble classifier upon the new feature set generated by the feature engineering pipeline. The usefulness of the proposed method is evaluated through metrics like accuracy, area under ROC (Receiver Operating Characteristic) curve, precision, recall and F1-score. The predictive ability of the models is affirmed under the presence of any statistical anomalies through the tests for statistical significance.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.