Search

Your search keyword '"Zina Z R Al-Shamaa"' showing total 2 results
Start Over Author "Zina Z R Al-Shamaa"
2 results on '"Zina Z R Al-Shamaa"'

1. The Use of Hellinger Distance Undersampling Model to Improve the Classification of Disease Class in Imbalanced Medical Datasets

Author

Zina Z. R. Al-Shamaa, Sefer Kurnaz, Adil Deniz Duru, Nadia Peppa, Alex H. Mirnezami, and Zaed Z. R. Hamady

Subjects
Biotechnology, TP248.13-248.65, Biology (General), QH301-705.5
Abstract

Imbalanced class distribution in the medical dataset is a challenging task that hinders classifying disease correctly. It emerges when the number of healthy class instances being much larger than the disease class instances. To solve this problem, we proposed undersampling the healthy class instances to improve disease class classification. This model is named Hellinger Distance Undersampling (HDUS). It employs the Hellinger Distance to measure the resemblance between majority class instance and its neighbouring minority class instances to separate classes effectively and boost the discrimination power for each class. An extensive experiment has been conducted on four imbalanced medical datasets using three classifiers to compare HDUS with a baseline model and three state-of-the-art undersampling models. The outcomes display that HDUS can perform better than other models in terms of sensitivity, F1 measure, and balanced accuracy.

Published
2020
Full Text
View/download PDF

2. The Use of Hellinger Distance Undersampling Model to Improve the Classification of Disease Class in Imbalanced Medical Datasets

Author

Zaed Hamady, Nadia Peppa, Sefer Kurnaz, Alex H. Mirnezami, Zina Z R Al-Shamaa, Adil Deniz Duru, Al-Shamaa, Zina Z. R., Kurnaz, Sefer, Duru, Adil Deniz, Peppa, Nadia, Mirnezami, Alex H., and Hamady, Zaed Z. R.

Subjects
SELECTION, Article Subject, QH301-705.5, Computer science, Biomedical Engineering, Medicine (miscellaneous), Bioengineering, 02 engineering and technology, Minority class, Machine learning, computer.software_genre, Measure (mathematics), 03 medical and health sciences, 0202 electrical engineering, electronic engineering, information engineering, Hellinger, Sensitivity (control systems), Biology (General), Hellinger distance, SMOTE, 030304 developmental biology, 0303 health sciences, business.industry, Medical Datasets, ALGORITHMS, Baseline model, Classification, Class (biology), Majority class, Undersampling, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer, TP248.13-248.65, Biotechnology, Research Article
Abstract

Mirnezami, Alexander/0000-0002-6199-8332 WOS:000594274800001 PubMed: 33204304 Imbalanced class distribution in the medical dataset is a challenging task that hinders classifying disease correctly. It emerges when the number of healthy class instances being much larger than the disease class instances. To solve this problem, we proposed undersampling the healthy class instances to improve disease class classification. This model is named Hellinger Distance Undersampling (HDUS). It employs the Hellinger Distance to measure the resemblance between majority class instance and its neighbouring minority class instances to separate classes effectively and boost the discrimination power for each class. An extensive experiment has been conducted on four imbalanced medical datasets using three classifiers to compare HDUS with a baseline model and three state-of-the-art undersampling models. The outcomes display that HDUS can perform better than other models in terms of sensitivity, F1 measure, and balanced accuracy.

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results