An Evolutionary-Based Approach for Low-Complexity Intrusion Detection in Wireless Sensor Networks

As security threats are increasingly diversified, a critical problem in Wireless Sensor Network environments (WSNs) is detecting anomalies. WSNs affected by several limitations, such as limited energy, insufficient memory, weak computation power, and short communication range. Hence, it necessary to improve the detection accuracy convergence speed of intrusion environments. In this article, we propose an model based on Time-Varying Parameter Improved Particle Swarm Optimization (TVP-IPSO) with Principal Component Analysis (PCA) Support Vector Machine (SVM). The PCA applied aimed at data dimension reduction compressing reduce energy consumption, algorithm SVM considered ensure high accuracy. To optimize identify its optimal parameters, TVP-IPSO used algorithm's precision speed. Experimental results show that TVP-IPSO-SVM higher than GA-SVM IPSO-SVM, demonstrating proposed research has better adaptability, accuracy, faster when compared other works presented.