Detection of Severity of Chronic Cough in Elders and Children using Machine Learning
R, Velvizhi1, D. Jayapriya2, N. Priya3
1R. Velvizhi, Department of CSE, Bharath Institute of Higher Edccation and Research, Chennai, Tamilnadu, India.
2D. Jayapriya, Department of CSE, Bharath Institute of Higher Edccation and Research, Chennai, Tamilnadu, India.
3N. Priya, Department of CSE, Bharath Institute of Higher Edccation and Research, Chennai, Tamilnadu, India.
Manuscript received on 04 July 2019 | Revised Manuscript received on 17 July 2019 | Manuscript Published on 23 August 2019 | PP: 550-553 | Volume-8 Issue-9S3 August 2019 | Retrieval Number: I31070789S319/2019©BEIESP | DOI: 10.35940/ijitee.I3107.0789S319
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Cough is a prevalent symptom of many illnesses of the respiratory system. The assessment of its intensity and event frequency could provide useful clinical data in the assessment of chronic cough patients .The MEMS vibration sensor is placed in neck either as batches or robes. The band-like filter patch was put on the body of the patient. Sensor is driven by batteries that allow patient mobility and connect to a smartphone phone. Smartphone transmits information to a cloud-based health platform that provides additional information and alerts medical staff. 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 sent to one or more caretakers ‘ smartphones, alerting them to early indications of an assault by the client. If various caregivers are present, the first person to react may use the smartphone to give a response text message to all others, notifying them of being with or on the manner 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 patient’s doctor.
Keywords: IoT, Machine Learning, Bio patches, Classification and Regression Tree.
Scope of the Article: IoT