Indonesian Journal of Electrical Engineering and Computer Science
Vol 26, No 1: April 2022

Rapid bacterial colony classification using deep learning

Son Ali Akbar (Universitas Ahmad Dahlan)
Kawarul Hawari Ghazali (Unknown)
Habsah Hasan (Universiti Sains Malaysia, Kelantan)
Zeehaida Mohamed (Unknown)
Wahyu Sapto Aji (Universitas Ahmad Dahlan)
Anton Yudhana (Universitas Ahmad Dahlan)



Article Info

Publish Date
01 Apr 2022

Abstract

Bacterial colonies infection is one of the causes of bloodstream disease, and it can be a fatality. Therefore, medical diagnoses require fast identification and classification of organisms. Artificial Intelligence with deep learning (DL) can now be developed as a rapid bacterial classification. The research aims to combine deep learning and support vector machines (SVM). The ResNet-101 model of the DL algorithm extracted the image’s features using transfer learning then classified by the SVM classifier. According to the experimental results, this model had 99.61% accuracy, 99.58% recall, 99.58% precision, and 99.97% specificity. The technique presented might enhance clinical decision-making.

Copyrights © 2022