Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Insyst : Journal of Intelligent System and Computation
Dina Zatusiva Haq
UIN Sunan Ampel, Surabaya
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Detecting Lung Disease Based on Chest X-ray Images Using a Hybrid CNN-KELM Approach Dian Candra Rini Novitasari; Musfiroh Musfiroh; Dina Zatusiva Haq
Intelligent System and Computation Vol 8 No 1 (2026): INSYST: Journal of Intelligent System and Computation
Publisher : Institut Sains dan Teknologi Terpadu Surabaya (d/h Sekolah Tinggi Teknik Surabaya)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52985/insyst.v8i1.479

Abstract

Tuberculosis (TB) is a disease caused by the Mycobacterium tuberculosis (M.tb) bacterium. TB ranks among the top 10 deadliest diseases worldwide and is the second most contagious disease after COVID-19. The World Health Organization (WHO) recommends using Chest X-ray (CXR) imaging techniques, given their high sensitivity and cost-effectiveness. This study proposes a hybrid CNN-KELM (CKELM) method for the classification of four lung disease categories based on chest X-ray (CXR) images: tuberculosis, pneumonia, COVID-19, and normal, all within a short computational time. This study experimented with several types of CNN architectures implemented for feature extraction, while KELM for classification used hyperparameters that tested various kernel types and regularization coefficients. The experimental results indicate that the best performance is achieved using the DenseNet201 architecture with a polynomial kernel and a regularization coefficient of 0.1. The polynomial kernel demonstrates superior performance across all CNN architectures. Furthermore, a regularization coefficient of 0.1 exhibits the highest accuracy in the kernel and CNN architecture experiments. The DenseNet201-KELM model attains an accuracy, sensitivity, specificity, precision, and F1-score of 99.57%, 99.57%, 99.86%, 99.57%, and 99.57%, which is 7% better than without under sampling and detection using the DenseNet201-KELM method requires a computational time of 309.19 seconds. The proposed method achieved good performance in multi-class classification, especially for balanced data, with fast computational time.
Co-Authors Musfiroh Musfiroh Sari, Dian Candra Rini Novita