Comparison and Combination of Leaky ReLU and ReLU Activation Function and Three Optimizers on Deep CNN for Covid-19 Detection

Mujhid, Almuzhidul and Surono, Sugiyarto and Irsalinda, Nursyiva and Thobirin, Aris (2022) Comparison and Combination of Leaky ReLU and ReLU Activation Function and Three Optimizers on Deep CNN for Covid-19 Detection. In: Fuzzy Systems and Data Mining VIII. IOS Press Ebooks, pp. 50-57.

Text (HASIL CEK SIMILARITY) 9781643683478 (3)_1.pdf - Published Version Download (622kB)

Abstract

COVID-19 detection is an interesting field of study in the medical world and the commonly used method is classification. In determining the best detection model, several classification architectures, such as SVM, KNN, and CNN were utilized. The CNN is a changeable architecture due to having combinations of varying numbers of hidden layers or different activation and optimizer functions. Therefore, this study uses a deep CNN architecture with a combination of Leaky ReLU activation functions and 3 different optimizers, which include Adagrad, Adadelta, and Adamax. The results showed that the combination of the Leaky ReLU activation function and the Adamax optimizer produced good and stable accuracy in the CRX and CT datasets.

Item Type:	Book Section
Keyword:	COVID-19, Image classification, Deep CNN, Leaky ReLU activation function, Optimizers
Subjects:	Q Science > QA Mathematics
Divisi / Prodi:	Faculty of Teacher Training and Education (Fakultas Keguruan dan Ilmu Pendidikan) > S1-Mathematics Education (S1-Pendidikan Matematika)
Depositing User:	Dr Sugiyarto Surono
Date Deposited:	22 Nov 2022 07:09
Last Modified:	22 Nov 2022 07:09
URI:	http://eprints.uad.ac.id/id/eprint/37575

Actions (login required)

View Item