Department of Mathematics, School of Science, Nanjing University of Science and Technology, Nanjing, China.
Department of Information Systems, Faculty of Management, Comenius University in Bratislava, Bratislava, Slovakia.
Front Public Health. 2021 Dec 3;9:788347. doi: 10.3389/fpubh.2021.788347. eCollection 2021.
In Internet of Things (IoT)-based network systems (IoT-net), intrusion detection systems (IDS) play a significant role to maintain patient health records (PHR) in e-healthcare. IoT-net is a massive technology with security threats on the network layer, as it is considered the most common source for communication and data storage platforms. The security of data servers in all sectors (mainly healthcare) has become one of the most crucial challenges for researchers. This paper proposes an approach for effective intrusion detection in the e-healthcare environment to maintain PHR in a safe IoT-net using an adaptive neuro-fuzzy inference system (ANFIS). In the proposed security model, the experiments present a security tool that helps to detect malicious network traffic. The practical implementation of the ANFIS model on the MATLAB framework with testing and training results compares the accuracy rate from the previous research in security.
在基于物联网（IoT）的网络系统（IoT-net）中，入侵检测系统（IDS）在电子医疗保健中维护患者健康记录（PHR）方面发挥着重要作用。IoT-net 是一项庞大的技术，存在网络层安全威胁，因为它被认为是最常见的通信和数据存储平台源。所有部门（主要是医疗保健）的数据服务器安全性已成为研究人员面临的最关键挑战之一。本文提出了一种在电子医疗保健环境中使用自适应神经模糊推理系统（ANFIS）进行有效入侵检测的方法，以在安全的 IoT-net 中维护 PHR。在所提出的安全模型中，实验提出了一种安全工具，可帮助检测恶意网络流量。将 ANFIS 模型在 MATLAB 框架上进行实际实现，并结合测试和训练结果，将准确率与之前的安全研究进行了比较。
