Article: Feature interpreted convolutional neural networks for real time implementation of respiratory data Journal: International Journal of System of Systems Engineering (IJSSE) 2026 Vol.16 No.1 pp.1 - 16 Abstract: Automatic detection of respiratory diseases is important to prevent any sudden death in patients. At present, respiratory diseases are detected by a physician who normally consumes more time to detect. In this work, the respiratory data from the persons are classified into either normal or abnormal using the proposed deep learning architecture. The proposed work consists of two subsequent phases namely training and testing. In training phase of the respiratory classification system (RCS), the respiratory data from both normal and both abnormal cases are individually data augmented in order to eliminate the overfitting issues in deep learning architecture. This data augmented respiratory data from both normal and abnormal case is used to construct data augmented matrix (DAM) which is trained by the proposed feature interpreted convolutional neural networks (FICNN) to produce the trained data. The proposed FICNN work obtained a 99.9% respiratory detection rate (RDR) with 0.05 ms as computational time. Inderscience Publishers - linking academia, business and industry through research

Title: Feature interpreted convolutional neural networks for real time implementation of respiratory data

Authors: R. Rampriya; N. Suguna; P. Sudhakar

Addresses: Department of CSE (AI), Madanapalle Institute of Technology and Science, Madanapalle, India ' Faculty of Engineering and Technology, Department of Computer Science and Engineering, Annamalai University, Annamalainagar, Tamilnadu, 608002, India ' Faculty of Engineering and Technology, Department of Computer Science and Engineering, Annamalai University, Annamalainagar, Tamilnadu, 608002, India

Abstract: Automatic detection of respiratory diseases is important to prevent any sudden death in patients. At present, respiratory diseases are detected by a physician who normally consumes more time to detect. In this work, the respiratory data from the persons are classified into either normal or abnormal using the proposed deep learning architecture. The proposed work consists of two subsequent phases namely training and testing. In training phase of the respiratory classification system (RCS), the respiratory data from both normal and both abnormal cases are individually data augmented in order to eliminate the overfitting issues in deep learning architecture. This data augmented respiratory data from both normal and abnormal case is used to construct data augmented matrix (DAM) which is trained by the proposed feature interpreted convolutional neural networks (FICNN) to produce the trained data. The proposed FICNN work obtained a 99.9% respiratory detection rate (RDR) with 0.05 ms as computational time.

Keywords: FICNN; feature interpreted convolutional neural networks; over fitting; data augmentation; deep learning; RCS; respiratory classification system; RDR; respiratory detection rate.

DOI: 10.1504/IJSSE.2026.152419

International Journal of System of Systems Engineering, 2026 Vol.16 No.1, pp.1 - 16

Received: 11 Aug 2023
Accepted: 26 Sep 2023
Published online: 19 Mar 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Feature interpreted convolutional neural networks for real time implementation of respiratory data

Keep up-to-date