<![CDATA[Introduction: Wheezing is one of the most common manifestations of airway obstruction. The use of a stethoscope in the wheezing examination has several disadvantages such as subjective results and depends on the auditor's hearing sensitivity. So an easy device is needed that helps determine the wheezing sound precisely. This study assembled a single tool to detect wheezing sounds based on the internet of things.Method: This tool is designed with a microprocessor hardware connected to an electric stethoscope so that it can be attached to the patient's chest wall. Collection of chest breathing voice data accessed on kaggle.com. The creation of algorithms with Convolutional Neural Networks (CNN) was later changed to Mel Frequency Cepstral Coefficients (MFCC). This model will be implanted in a microprocessor and use python language to be able to record the sound of chest wall vibrations. The recorded sound is converted into MFCC to make it easier to perform wheezing sound detection. MFCC image results and detection results are sent to the database via the firebase database feature which stores MFCC photos in real-time as they are detected. Designing android application software using Flutter builds communication between android applications and firebase databases that allows applications to retrieve MFCC images as the final result. Result: The results of the tool trial on five volunteers, three exacerbation asthma patients and two healthy people showed the device can detect wheezing sounds at a frequency of 400Hz with 80% accuracy through CNN and MFCC algorithms Internet of things based.Conclusion: This tool can help health workers to accurately determine wheezing sounds, enforce the diagnosis faster, the prognosis of the disease to be better, so as to reduce the number morbidity and mortality of diseases with airway abnormalities in Indonesia ]]>
Copyrights © 2022
