Narrow Results

Audio-based healthcare technologies are among the most significant applications of pattern recognition and Artificial Intelligence. Lately, a major chunk of the World population has been infected with serious respiratory diseases such as COVID-19. Early recognition of lung health abnormalities can facilitate early intervention, and decrease the mortality rate of the infected population. Research has shown that it is possible to automatically monitor lung health abnormalities through respiratory sounds. In this paper, we propose an approach that employs filter bank energy-based features and Random Forests to classify lung problem types from respiratory sounds. The adventitious sounds, crackles and wheezes appear distinct to the human ear. Moreover, different sounds are characterized by different frequency ranges that are dominant. The proposed approach attempts to distinguish the adventitious sounds (crackles and wheezes) by modeling the human auditory perception of these sounds. Specifically, we propose a respiratory sounds representation technique capable of modeling the dominant frequency range present in such sounds. On a publicly available dataset (ICBHI) of size 6898 cycles spanning over 5h, our results can be compared with the state-of-the-art results, in distinguishing two different types of adventitious sounds: crackles and wheezes.

Background: The world is transitioning to Industry 4.0, representing the transition to digital, fully machine-driven environments and cyberphysical systems. Industry 4.0 comprises various technologies and innovations that enable development in multiple perspectives, which are implemented in many different sectors. Problem: The major challenges are the high cost, high rate of failure, security and privacy issues, and there is a need for highly skilled labor for applying healthcare data analysis. Aim: To resolve these issues, we employ the proposed system of Industry 4.0 smart manufacturing for IoT-enabled healthcare data analysis in virtual hospital systems with machine learning (ML) techniques. Methods: The proposed system contains five alternative solutions under smart manufacturing. First, the healthcare data analysis is applied for Weber’s syndrome. That is, this will be used to analyze Weber’s syndrome during its consistent treatment. Second, the IoT-enabled healthcare data handling system works based on edge-assisted edge computing that is used to apply IoT to the healthcare data handling system. The healthcare data analysis in virtual hospital systems uses machine learning for driving data synthesis. Finally, the Industry 4.0 smart manufacturing is applied to the IoT-enabled healthcare data analysis to realize efficient data digitization, especially in smart hospitals with smart sensors for virtual IoT-enabled devices surveillance of Weber’s syndrome. Result: The data digitization based on Industry 4.0 smart manufacturing analysis is considered for data processing, storage and transmission. The proposed system is 62% more efficient than the other analyzed methods. The identification of Weber’s syndrome is 69.8% more efficient than the existing midbrain stroke syndrome identification. The processing and storage of data results are 45.78% more efficient than the current encryption method. Finally, the priority-aware healthcare data analysis based on ML provides 63.4% efficient, faster and more accurate diagnoses in the personalized treatment.