International Journal of Electrical and Computer Engineering (IJECE) Vol. 14, No. 3, June 2024, pp. 3094~3105 ISSN: 2088-8708, DOI: 10.11591/ijece.v14i3.pp3094-3105  3094 Journal homepage: http://ijece.iaescore.com An advanced approach for accurate pneumonia detection using combined deep convolutional neural networks Ola M. El Zein 1 , Naglaa E. Ghannam 1,2 1 Department of Mathematics, Faculty of Science, Al-Azhar University (Girls’ Branch), Cairo, Egypt 2 Department of Computer Engineering and Information, College of Engineering in Wadi Alddawasir, Prince Sattam Bin Abdulaziz University, Wadi Alddawasir, Saudi Arabia Article Info ABSTRACT Article history: Received Jan 20, 2024 Revised Feb 15, 2024 Accepted Mar 5, 2024 Pneumonia, a lung infection caused by viral or bacterial agents, poses a significant health risk by affecting one or both lungs in humans. Accurate diagnosis, particularly in pediatric cases, is crucial for timely intervention. chest X-rays (CXRs) are a common and non-invasive diagnostic tool to detect pneumonia-related abnormalities. Nonetheless, the minimal radiation exposure suitable for pediatric diagnosis poses a challenge in accurately detecting pneumonia in children. This work proposes a concatenation model that combines two pre-trained convolutional neural networks (CNNs) depending on the transfer learning (TL) technique and optimizes the training parameters to build a highly accurate model for detecting pediatric pneumonia from CXR images. The concatenated extracted features from the two pre-trained CNNs are passed through a convolutional layer to select more valuable semantic features to reduce the extracted features, which helps reduce the model parameters and execution time. Experimental results demonstrate that the feature concatenation technique, along with optimization of training parameters, surpasses the performance of individual CNNs and several state-of-the-art methods. The proposed method achieves a classification accuracy of 98.5%, precision of 99.5%, sensitivity of 98.4%, and F1 score of 99.1%. The primary objective of the proposed approach is to aid radiologists in achieving accurate pneumonia diagnosis in real-time. Keywords: Chest X-rays Concatenation technique Deep feature extraction Pediatric pneumonia Transfer learning This is an open access article under the CC BY-SA license. Corresponding Author: Ola M. El Zein Department of Mathematics, Faculty of Science, Al-Azhar University (Girls’ Branch) Cairo, Egypt Email: olaelzin@azhar.edu.eg 1. INTRODUCTION In recent years, the worldwide spread of various infections and diseases has become a significant concern. Pneumonia is a respiratory infection resulting from viruses or bacteria affecting the lungs [1], [2]. The World Health Organization (WHO) has recognized pneumonia as the primary cause of death worldwide among children under the age of five, constituting approximately 12.8% of annual child deaths [3]. Tragically, in 2016, over 800,000 children succumbed to pneumonia, with the majority being under two years old. This death toll surpassed the combined fatalities from malaria, acquired immunodeficiency syndrome (AIDS), and measles [4], [5]. The gravity of the situation persisted in 2019, with pneumonia claiming the lives of 740,180 children, accounting for 14% of all deaths in child under 5 years old and 22% in child deaths aged 1-5 years [6]. These alarming statistics underscore the urgent need for improved strategies in pneumonia detection, treatment, and prevention to mitigate its devastating impact on global child mortality rates. The chest X-ray (CXR) proves to be a time and cost-efficient method for pneumonia diagnosis