An IOT-Based COVID-19 Detector Using K-Nearest Neighbor

T. M. Okediran (), O. R. Vincent, A. A. Abayomi-Alli and O. J. Adeniran ()
Additional contact information
T. M. Okediran: Federal University of Agriculture
O. R. Vincent: Federal University of Agriculture
A. A. Abayomi-Alli: Federal University of Agriculture
O. J. Adeniran: Federal University of Agriculture

Chapter Chapter 2 in Decision Sciences for COVID-19, 2022, pp 27-43 from Springer

Abstract: Abstract COVID-19 is rampaging the world, increasing medical emergencies, imposing a high cost on every Nation’s expenditure without minding the budget, and causing a continuous rise in the death rate. It has come to stay and live with people in the world. The cure is no longer the case, but how to manage it is now the fact. It is essential to save time, cost of running tests and test kits, cost of purchasing vaccine, create awareness in public places, decongest the isolation centers, save time to get test results, and provide mobility advantage for testing people anywhere and everywhere. This model will quickly detect and report COVID-19 symptoms on patients with cost-effectiveness to bring down the rising curve. It presents an Internet of Things (IOT) based COVID-19 detector that lowers the cost of testing by using machine learning techniques for easy and timely detection of Covid-19 symptoms in a patient. The device integrates an Infrared (IR) camera, Infrared skin thermometer, IR stethoscope, IR sphygmomanometer for blood pressure, a liquid crystal display screen to show the result, a Buzz alarm and its database, hosted in the cloud and connected via the wireless network. The training and test data gives an accuracy of 0.995 and 0.996, respectively, by using the k-nearest neighbor’s classifier. It shows that the model performs well on training and test data without overfitting. Nine patients were further tested with the model, four were reported positive by this model, five returned negative, and the maximum time taken to complete the check was 28 s, while the minimum time was 20.5 s, which shows that the device is time-efficient and can be used where large numbers of people are expected.

Keywords: Internet of things; Cost; IR; Corona virus; Symptoms; k-nearest neighbor (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:isochp:978-3-030-87019-5_2

Ordering information: This item can be ordered from
http://www.springer.com/9783030870195

DOI: 10.1007/978-3-030-87019-5_2

Access Statistics for this chapter

More chapters in International Series in Operations Research & Management Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().