Publisher

LAMINTANGLAMINTANG

Journal Journal of Engineering, Technology, and Applied Science (JETAS)Journal of Engineering, Technology, and Applied Science (JETAS) Abstract

The ongoing global pandemic, which has now become an endemic, has had a significant impact on the educational sector. Despite advancements in technology, there is no real-time prevention of COVID-19 transmission, especially for UiTM Tapah students who must go through crowds to reach the health unit and have a high possibility of spreading the disease. This research aims to develop a mobile application utilizing machine learning for UiTM Tapah students to classify their COVID-19 status. The research adopted the Mobile Application Development Life Cycle (MADLC) methodology. The applications core functionality lies in the implementation of an Artificial Neural Network (ANN), trained on 5,434 samples of data previously classified in studies analyzing student data to identify potential cases. The ANN achieved 98% accuracy. Feedback from 32 respondents identified student difficulties during the pandemic, with most agreeing that the MCO affected their adaptation to online learning and access to healthcare. Usability testing using the System Usability Scale (SUS) indicated a high level of user-friendliness, with scores of 88.3 from UiTM Tapah students and 76.25 from lecturers. This system is usable for classifying infection risk among undiagnosed students, with room for improvement. The systems ability to identify infected individuals promptly and accurately aided in controlling the spread of the virus, protecting students and staff. Thus, the classification system using ANN is a valuable tool for public health organizations in combating the COVID-19 pandemic.

Conclusion

This research successfully developed a mobile application utilizing an Artificial Neural Network (ANN) to classify COVID-19 status among UiTM Tapah students.The system demonstrated high accuracy in identifying potential cases, contributing to the control of virus spread within the campus community.The usability testing results indicated a positive user experience, suggesting the systems potential for widespread adoption and integration into public health initiatives.

Future Research

Further research could explore the integration of real-time data streams, such as temperature readings from wearable devices, to enhance the accuracy and responsiveness of the classification system. Additionally, investigating the application of more advanced machine learning models, like deep learning architectures, could potentially improve the systems ability to detect subtle patterns indicative of COVID-19 infection. Finally, a longitudinal study is needed to assess the long-term impact of this system on student health behaviors and the overall effectiveness of pandemic response strategies within the university setting, considering factors like user adherence and evolving virus variants. These investigations will contribute to a more robust and adaptable system for managing future health crises and promoting proactive health management among students.

References

1. Covid Classification System for Covid Detection | Journal of Engineering, Technology, and Applied Science... lamintang.org/journal/index.php/jetas/article/view/610Covid Classification System for Covid Detection Journal of Engineering Technology and Applied Science lamintang journal index php jetas article view 610

Metadata

File size	1000.42 KB
Pages	7
DMCA	Report