International Journal of Research in Arts and Science

Impact Factor: 0.387 | International Scientific Indexing(ISI) calculate based on International Citation Report(ICR)


A Study on Chronic Cough Detection using IoT and Machine Learning

Ms. P. Hemalatha and Ms. R. Vidhyalakshmi


Abstract:

Cough is a common symptom of many respiratory diseases. The evaluation of its intensity and frequency of occurrence could provide valuable clinical information in the assessment of patients with chronic cough. The MEMS vibration sensor is placed in neck either as batches or robes. The band-like sensor patch placed on patients body. Sensor is powered by batteries which enables mobility of the patient and is connected to a smart phone device. Smartphone transmits data to a cloud-based health platform which further delivers data and alerts medical personnel. The machine learning algorithms collect and analyze the sound of the coughs to personalize it to the user based on its pitch and sound profile, which is unique to each person based on the size and capacity of his or her lungs. When coughing indicates an impending attack, the device transmits a message to the dedicated cloud-based software via the nearest cellular communications tower. A text message is then automatically dispatched to the smart phones of one or more caretakers, alerting them that the patient is showing early signs of an attack. If there are multiple caretakers present, the first to respond can use the smart phone to send a reply text message to all of the others, notifying them that he or she is with or on the way to the patient. The doctors could use recordings of coughing to help diagnose an illness. The device issues an alert only to caregivers because sending an audio file would consume a significant amount of battery power. However, when the wearable sensor batch is recharging, it could be provisioned to forward sound files to the patients doctor.

Keywords: IoT, Machine Learning, MEMS

Volume: 5 | Issue: Holistic Research Perspectives [Volume 4]

Pages: 151-160

Issue Date: August , 2019

DOI: 10.9756/BP2019.1002/14

Full Text

Email

Password

 


This Journal is an Open Access Journal to Facilitate the Research Community