Life-threatening novel severe acute respiratory syndrome coronavirus (SARS-CoV-2), also known as COVID-19, has engulfed the world and caused health and economic challenges. To control the spread of COVID-19, a mechanism is required to enforce physical distancing between people. This paper proposes a Blockchain-based framework that preserves patients’ anonymity while tracing their contacts with the help of Bluetooth-enabled smartphones. We use a smartphone application to interact with the proposed blockchain framework for contact tracing of the general public using Bluetooth and to store the obtained data over the cloud, which is accessible to health departments and government agencies to perform necessary and timely actions (e.g., like quarantine the infected people moving around). Thus, the proposed framework helps people perform their regular business and day-to-day activities with a controlled mechanism that keeps them safe from infected and exposed people. The smartphone application is capable enough to check their COVID status after analyzing the symptoms quickly and observes (based on given symptoms) either this person is infected or not. As a result, the proposed Adaptive Neuro-Fuzzy Interference System (ANFIS) system predicts the COVID status, and K-Nearest Neighbor (KNN) enhances the accuracy rate to 95.9% compared to state-of-the-art results.

威胁生命的新型严重急性呼吸系统综合症冠状病毒 (SARS-CoV-2)，也称为 COVID-19，已席卷全球，并造成健康和经济挑战。为了控制 COVID-19 的传播，需要一种机制来加强人与人之间的身体距离。本文提出了一个基于区块链的框架，该框架可以在支持蓝牙的智能手机的帮助下跟踪患者的联系人的同时保持患者的匿名性。我们使用智能手机应用程序与提议的区块链框架进行交互，以使用蓝牙对公众进行接触者追踪，并将获得的数据存储在云端，卫生部门和政府机构可以访问这些数据以执行必要和及时的行动（例如，隔离四处走动的感染者）。因此，拟议的框架通过受控机制帮助人们开展日常业务和日常活动，以保护他们免受感染和暴露人员的伤害。智能手机应用程序能够在快速分析症状后检查他们的 COVID 状态，并观察（基于给定的症状）这个人是否被感染。因此，所提出的自适应神经模糊干扰系统 (ANFIS) 系统可以预测 COVID 状态，并且与最先进的结果相比，K-最近邻 (KNN) 将准确率提高到 95.9%。智能手机应用程序能够在快速分析症状后检查他们的 COVID 状态，并观察（基于给定的症状）这个人是否被感染。因此，所提出的自适应神经模糊干扰系统 (ANFIS) 系统可以预测 COVID 状态，与最先进的结果相比，K-最近邻 (KNN) 将准确率提高到 95.9%。智能手机应用程序能够在快速分析症状后检查他们的 COVID 状态，并观察（基于给定的症状）这个人是否被感染。因此，所提出的自适应神经模糊干扰系统 (ANFIS) 系统可以预测 COVID 状态，并且与最先进的结果相比，K-最近邻 (KNN) 将准确率提高到 95.9%。