Rashidian Mohsen, Malek Mohammad Reza, Sadeghi-Niaraki Abolghasem, Choi Soo-Mi
Ubiquitous and Mobile GIS Research Lab., Faculty of Geodesy and Geomatics Engineering, K.N. Toosi University of Technology, Tehran Iran.
Department of Computer Science & Engineering and Convergence Engineering for Intelligent Drone, XR Research Center, Sejong University, Seoul, Republic of Korea.
Digit Health. 2024 Jul 21;10:20552076241261929. doi: 10.1177/20552076241261929. eCollection 2024 Jan-Dec.
Bluetooth low energy (BLE)-based contact-tracing applications were widely used during the COVID-19 pandemic. However, the use of only the received signal strength feature for proximity calculations may not be adaptable to different virus variants or scalable for other potential epidemic diseases.
This study presents a novel framework in regard to evaluating and classifying personal exposure risk that considers both contact features, which include distance and length of contact, and environment features, which include crowd size and the number of recently infected cases in the environment. The framework utilizes a fuzzy expert system that is adaptable to different virus variants.
The proposed method was tested on two viruses with different close contact features, which used four membership functions and 256 fuzzy rule sets.
The proposed framework classified personal exposure risks into four classes, which include low, medium, high, and too high risk. The empirical results showed that the fuzzy logic-based approach reduced the number of false positive cases and demonstrated better accuracy and precision than the current BLE-only approaches.
The proposed framework provides a more practical and adaptable method in regard to assessing exposure risks in real-world scenarios. It has the potential to be scalable and adaptable to different virus variants and other potential epidemic diseases by considering both contact and environment features. These findings may be useful in order to develop more effective digital contact-tracing applications and policies.
基于低功耗蓝牙（BLE）的接触者追踪应用在新冠疫情期间被广泛使用。然而，仅使用接收信号强度特征进行接近度计算可能无法适应不同的病毒变种，也无法扩展用于其他潜在的流行病。
本研究提出了一个关于评估和分类个人暴露风险的新颖框架，该框架同时考虑了接触特征（包括距离和接触时长）和环境特征（包括人群规模和环境中近期感染病例数）。该框架利用了一个适用于不同病毒变种的模糊专家系统。
所提出的方法在两种具有不同密切接触特征的病毒上进行了测试，使用了四个隶属函数和256个模糊规则集。
所提出的框架将个人暴露风险分为四类，包括低、中、高和极高风险。实证结果表明，基于模糊逻辑的方法减少了误报病例的数量，并且比当前仅基于BLE的方法具有更高的准确性和精确性。
所提出的框架为评估现实场景中的暴露风险提供了一种更实用、更具适应性的方法。通过同时考虑接触和环境特征，它有可能扩展并适应不同的病毒变种和其他潜在的流行病。这些发现可能有助于开发更有效的数字接触者追踪应用和政策。
