Please use this identifier to cite or link to this item:
https://rda.sliit.lk/handle/123456789/1122
Title: | InCOV Chamber: An IoT based Intelligent Chamber to monitor and identify potential COVID-19 positive patients |
Authors: | Liyanarachchi, R.K. Premathilaka, M. Samarawickrama, H. Thilakasiri, N. Wellalage, S. Wijekoon, J.L. |
Keywords: | Coronavirus COVID-19 Screening Artificial Intelligence IoT |
Issue Date: | 9-Dec-2021 |
Publisher: | 2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT |
Abstract: | COVID-19, the infectious disease with common symptoms such as tiredness, fever, cough, and severe symptoms such as shortness of breath has become a global pandemic that has an enormous negative impact on society. Because of the disease’s negative influence o n o r ganizational operations, the entire world is concerned about its spread within their organization. Despite the fact that fever is currently the only symptom used to identify COVID-19 suspects, there may be COVID-19 patients who may not show any signs of fever. The goal of this study is to use an IoT-based chamber to detect potential COVID-19 suspects by taking into account the aforementioned symptoms. When a person enters the chamber, our system employs Neural Networks and Artificial Intelligence (AI) to detect COVID-19 symptoms like Fever, Anosmia, Cough, and Shortness of Breath. The proposed system yields accuracies of 95% for fever detection, 96% for Anosmia detection, and 94% for cough analysis. |
URI: | http://rda.sliit.lk/handle/123456789/1122 |
ISSN: | 978-1-6654-0862-2/21 |
Appears in Collections: | 3rd International Conference on Advancements in Computing (ICAC) | 2021 Research Papers - Dept of Computer Systems Engineering Research Papers - IEEE |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
InCOV_Chamber_An_IoT_based_Intelligent_Chamber_to_monitor_and_identify_potential_COVID-19_positive_patients.pdf Until 2050-12-31 | 2.49 MB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.