Implementation of Extreme Learning Model for Cyber Security in IoT Networks

Cybersecurity in IoT (Internet of Things) networks faces several significant challenges and problems, primarily due to the unique characteristics of IoT devices and their widespread deployment. Cybersecurity is a major problem for IoT networks. Addressing these cybersecurity challenges in IoT networks requires a multi-pronged approach involving manufacturers, users, policymakers, and cybersecurity experts. This approach should include robust device authentication, encryption, regular updates, intrusion detection systems, and user education. Extreme Learning Machines (ELMs) have gained significant attention in the machine learning community due to their efficiency and effectiveness across diverse applications. In this paper, a new algorithm called Fusion Extreme Learning Machine with enhanced multi-feature integration (FELM-EMFI) is specifically tailored for enhancing the security of communication channels in Internet of Things (IoT) networks. By incorporating multiple features into the learning process, FELM-EMFI aim to bolster the reliability and robustness of communication channels within IoT systems. The suggested technique achieves the highest accuracy of 96.5%, outperforming the ELM method with 94.2%, the AVM strategy with 94.7%, and the BP approach with 91.2%. Consequently, the proposed approach demonstrates superior performance when compared to the current methodologies.