Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176214,
        author = {Devi. D and Hemalatha S and Kaviyapriya R and Malaiyammal T and Abinaya S},
        title = {Secure Knowledge and Cluster based Intrusion Detection Mechanism for Smart Wireless Sensor Network},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {7238-7245},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176214},
        abstract = {Wireless Sensor Networks (WSNs) are deployed frequently across applications, including environmental monitoring, military surveillance, and health care systems. The constrained resources and open network channels in WSNs require robust IDS development because they create exposed security threats. WSN security relies heavily on IDS systems that detect harmful network events to protect network reliability and integrity. Trusted Intrusion Detection Systems operate with weak attack identifications, elevated system power usage, and restricted capabilities when detecting changing attack types. This paper introduces a secure knowledge and cluster-based Intrusion Detection System that combines Artificial Bee Colony-Long Short-Term Memory (ABC-LSTM) methodology to solve existing challenges. The outlined strategy is comprised of three fundamental steps; the first step is the formation of clusters utilizing the Low-Energy Adaptive Clustering Hierarchy (LEACH) method, which utilizes cluster forming to improve the energy consumption and scalability of the network; then follows feature selection with the Ant Colony Optimization (ACO) algorithm, which selects the most suitable cluster features intending to attain the highest detection accuracy with the lowest possible computational burden; and finally, intrusion detection ABC-LSTM, wherein hyperparameters of LSTM networks are tuned with the Artificial Bee Colony (ABC) method to enhance the efficiency of anomaly detection. The proposed method provides WSNs with adaptive intrusion detection systems that deliver energy efficiency with high accuracy. Simulation outcomes show that our solution delivers better IDS performance than standard IDS systems regarding detection capabilities, energy efficiency, and false alarm reduction, establishing it as an effective defensive measure for WSN security.},
        keywords = {WSN, IDS, threats, malicious activities, cluster, LEACH, ACO, ABC-LSTM, anomaly detection},
        month = {April},
        }