Affiliation:
1. Avinashilingam Institute for Home Science and Higher Education for Women, India
Abstract
Wireless sensor networks (WSNs) are important in various applications, including environmental monitoring, healthcare, and industrial automation. However, the energy constraints of sensor nodes present significant challenges in deploying robust security mechanisms, such as intrusion detection systems (IDS). The method involves using data aggregation, node selection, and energy harvesting techniques to reduce energy consumption while maintaining the accuracy of the IDS. The effectiveness of the proposed approach is evaluated using simulation experiments. This chapter offers a promising solution for providing effective and energy-efficient intrusion detection in ZigBee-based WSNs. The study found that applying machine learning techniques, specifically SFA, can significantly improve the energy efficiency of Zigbee protocol in wireless sensor networks. Results indicate that using these techniques energy consumption is up to 95.42% and 190 μW / node, IDS prediction ratio is 98.5%, and accuracy is 99.5% while maintaining network performance.