A Comparison of Deep Learning CNN Architecture Models for Classifying Bacteria

Poomrittigul, Suvit; Chomkwah, Wanwalee; Tanpatanan, Tananan; Sakorntanant, Sakda; Treebupachatsakul, Treesukon

doi:10.1109/ITC-CSCC55581.2022.9894986

A Comparison of Deep Learning CNN Architecture Models for Classifying Bacteria

Author(s)

Poomrittigul, Suvit

Chomkwah, Wanwalee

Tanpatanan, Tananan

Sakorntanant, Sakda

Treebupachatsakul, Treesukon

Date Issued

January 1, 2022

Type

Conference Paper

DOI

10.1109/ITC-CSCC55581.2022.9894986

Abstract

Since identifying bacteria from a patient's sample for medical diagnosis purposes by the traditional approach is time-consuming and requires the pathologist's expertise to do the bacteria identification procedure. Thus, involving the deep learning model reported the capability of multi-class image classification allows us to reduce the time and increase the prediction accuracy of the bacteria identification process. This research includes 35 different bacteria species and 6 different Convolutional Neural Network (CNN) architectures. Convolutional Neural Network (CNN) architectures are LeNet-5, AlexNet, VGG-16, VGG-19, ResNet-18, and ResNet-34. The results confirmed the perceptional performance by applying Stratified K-fold cross validation with VGG-16 and observing the multi-class performance with the AUC-ROC score.

Citation

Itc Cscc 2022 37th International Technical Conference on Circuits Systems Computers and Communications, 290-293, 2022

Subjects

Bacteria

Classification

CNN

Deep Learning