Cascaded PFLANN Model for Intelligent Health Informatics in Detection of Respiratory Diseases from Speech Using Bio-inspired Computation

Abstract

Due to the recent developments in communications technology, cognitive computations have been used in smart healthcare techniques that can combine massive medical data, artificial intelligence, federated learning, bio-inspired computation, and the Internet of Medical Things. It has helped in knowledge sharing and scaling ability between patients, doctors, and clinics for effective treatment of patients. Speech-based respiratory disease detection and monitoring are crucial in this direction and have shown several promising results. Since the subject’s speech can be remotely recorded and submitted for further examination, it offers a quick, economical, dependable, and noninvasive prospective alternative detection approach. However, the two main requirements of this are higher accuracy and lower computational complexity and, in many cases, these two requirements do not correlate with each other. This problem has been taken up in this paper to develop a low computational complexity-based neural network with higher accuracy. A cascaded perceptual functional link artificial neural network (PFLANN) is used to capture the nonlinearity in the data for better classification performance with low computational complexity. The proposed model is being tested for multiple respiratory diseases, and the analysis of various performance matrices demonstrates the superior performance of the proposed model both in terms of accuracy and complexity.