LOCATION-BASED AI-ASSISTED FILATION SOFTWARE FOR ISOLATION OF EPIDEMIC DISEASES

Abstract

Filiation is a technique used to find the first source of the disease in epidemics. As a result of filiation studies, basic and very important information such as the causes of the disease and transmission routes can be obtained. Health units can take preventive measures or plan some health services with the data they have obtained as a result of these studies. The purpose of this study is to follow the spatial movements of people with smartphones in daily life and to isolate the person in case of possible pandemic danger. In this context, it is aimed to determine the locations of infected people in coronavirus and other epidemic diseases, to map the filiation, and to help ensure social isolation. In this context, a tracking software that works on Android and IOS systems with flutter technology has been developed to retrieve user locations. The tracking software transfers the user location information to the central server. When there is a temporal deficiency or possible GPS differences in the received location information, the missing data in the server is estimated by the developed LSTM deep learning model. The model can make accurate predictions over 99%. In the last step of the study, the main tracking and mapping software was developed with C#. In an inquiry made with a positive patient's phone number, positional matches are extracted at the same time as the person. In this way, filiation scanning is performed on the map. As a result, with the widespread use of the study, it is aimed to take faster and more accurate measures to prevent the epidemic from infecting more people. In this context, it is aimed to determine the locations of infected people in coronavirus and other epidemic diseases, to map the filiation, and to help ensure social isolation.

Keywords

• Filiation
• Location-Based Service
• LSTM
• Epidemic

References

1. [1] Vaishya, R., Javaid, M., Khan, I. H., Vaish, A., & Iyengar, K. P. (2021). Significant Role of Modern Technologies for COVID-19 Pandemic. Journal of Industrial Integration and Management, 6(2), 147-159.
2. [2] Anglada-Tort, M., & Vidal-Alaball, J. (2020). Combining contact tracing and mobile health technologies to manage COVID-19 transmission: a narrative review. JMIR mHealth and uHealth, 8(9), e19818. doi: 10.2196/19818
3. [3] Kwok, K. O., & Wei, W. I. (2020). Social distancing during the COVID-19 pandemic: stay connected with family and friends. Head & neck, 42(6), 1205-1206. doi: 10.1002/hed.26191
4. [4] Anglada-Tort, M., & Vidal-Alaball, J. (2020). Combining contact tracing and mobile health technologies to manage COVID-19 transmission: a narrative review. JMIR mHealth and uHealth, 8(9), e19818. doi: 10.2196/19818
5. [5] Kwok, K. O., & Wei, W. I. (2020). Social distancing during the COVID-19 pandemic: stay connected with family and friends. Head & neck, 42(6), 1205-1206. doi: 10.1002/hed.26191
6. [6] Bayıroğlu, H., & Ayan, K. (2014). Android üzerinde web tabanlı çocuk takip sistemi. Sakarya University Journal of Science, 18(2), 87-91.
7. [7] Han, M., Li, L., Xie, Y., Wang, J., Duan, Z., Li, J., & Yan, M. (2018). Cognitive approach for location privacy protection. IEEE Access, 6, 13466-13477.
8. [8] Bayıroğlu, H., & Ayan, K. (2014). Android üzerinde web tabanlı çocuk takip sistemi. Sakarya University Journal of Science, 18(2), 87-91.

9. [9] Ministry of Health, (2021), Access Date: 12.02.2021, Access Link: https://covid19.saglik.gov.tr/TR-66393/covid-19-salgin-yonetimi-ve-calisma-rehberi.html
10. [10] Gülcüoğlu, E., Ustun, A. B., & Seyhan, N. (2021). Comparison of Flutter and React Native Platforms. Journal of Internet Applications and Management, 12(2), 129-143.
11. [11] Cao, J., Li, Z., & Li, J. (2019). Financial time series forecasting model based on CEEMDAN and LSTM. Physica A: Statistical mechanics and its applications, 519, 127-139.
12. [12] Chimmula, V. K. R., & Zhang, L. (2020). Time series forecasting of COVID-19 transmission in Canada using LSTM networks. Chaos, solitons & fractals, 135, 109864.
13. [13] Shastri, S., Singh, K., Kumar, S., Kour, P., & Mansotra, V. (2020). Time series forecasting of Covid-19 using deep learning models: India-USA comparative case study. Chaos, Solitons & Fractals, 140, 110227