Firefly algorithm based WSN-IoT security enhancement with machine learning for intrusion detection

Abstract

A Wireless Sensor Network (WSN) aided by the Internet of Things (IoT) is a collaborative system of WSN systems and IoT networks are work to exchange, gather, and handle data. The primary objective of this collaboration is to enhance data analysis and automation to facilitate improved decision-making. Securing IoT with the assistance of WSN necessitates the implementation of protective measures to confirm the safety and reliability of the interconnected WSN and IoT components. This research significantly advances the current state of the art in IoT and WSN security by synergistically harnessing the potential of machine learning and the Firefly Algorithm. The contributions of this work are twofold: firstly, the proposed FA-ML technique exhibits an exceptional capability to enhance intrusion detection accuracy within the WSN-IoT landscape. Secondly, the amalgamation of the Firefly Algorithm and machine learning introduces a novel dimension to the domain of security-oriented optimization techniques. The implications of this research resonate across various sectors, ranging from critical infrastructure protection to industrial automation and beyond, where safeguarding the integrity of interconnected systems are of paramount importance. The amalgamation of cutting-edge machine learning and bio-inspired algorithms marks a pivotal step forward in crafting robust and intelligent security measures for the evolving landscape of IoT-driven technologies. For intrusion detection in the WSN-IoT, the FA-ML method employs a support vector machine (SVM) machine model for classification with parameter tuning accomplished using a Grey Wolf Optimizer (GWO) algorithm. The experimental evaluation is simulated using NSL-KDD Dataset, revealing the remarkable enhancement of the FA-ML technique, achieving a maximum accuracy of 99.34%. In comparison, the KNN-PSO and XGBoost models achieved lower accuracies of 96.42% and 95.36%, respectively. The findings validate the potential of the FA-ML technique as an active security solution for WSN-IoT systems, harnessing the power of machine learning and the Firefly Algorithm to bolster intrusion detection capabilities.

Text Mining Algorithm Naive Bayes Classifier to Improve Quality Sentiment Analysis Passport Mobile Application

“…The process of data mining or data mining at the KDD stage can also be called text mining or text mining, because the data that researchers use is in the form of text, then at this stage, the Naive Bayes classifier algorithm is implemented for sentiment analysis of Mobile Passport application reviews (Karthikeyan et al, 2024). This stage is carried out after the data has passed the sentiment class labeling, this process is carried out by classification analysis, namely by making training data and testing data, then classifying with the Naive Bayes classifier algorithm and visualizing barplots and word clouds of the positive and negative words produced.…”

Network Information Security Monitoring Under Artificial Intelligence Environment

“…Network attack detection is one of the important means to ensure NIS, aiming to timely detect, identify, and respond to various network attack behaviors, ensuring the normal operation of network systems and the security of user data (Karthikeyan et al, 2024). With the rapid development of the internet and the continuous evolution of hacker attacks, network attacks have become more and more complex and hidden, posing a huge threat to network security.…”