An Effective Big Data-Driven IoT Intrusion Detection Model using BAOA-IESNN

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 7

Year of Publication : 2025

Authors : S. Ravishankar, P. Kanmani

10.14445/23488379/IJEEE-V12I7P116

How to Cite?

S. Ravishankar, P. Kanmani, "An Effective Big Data-Driven IoT Intrusion Detection Model using BAOA-IESNN," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 7, pp. 221-237, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I7P116

Abstract:

The rapid development of technological advances has saturated communications with network data traffic. Considering the multitude of sensor nodes within the Internet of Things (IoT) network, the analysis of network traffic data using conventional approaches could be difficult. It is essential to analyze this network traffic within a Big Data (BD) environment. BD refers to an enormous volume of complex data essential for analyzing patterns in networks and comprehending past occurrences within the network. Hence, this research proposes a BD-based intrusion detection model using the Deep Learning (DL) algorithm with Apache Spark (APS) for attack detection and classification. The developed intrusion detection model includes multiple processes such as data collection, data preprocessing, feature selection and classification. For this research, the BoT-IoT dataset is collected and applied to train and evaluate the model. The collected dataset is processed in the preprocessing stage with multiple preprocessing methods like data cleaning, label encoding, oversampling, and min-max normalization. The Binary Archimedes Optimization Algorithm (BAOA) technique is applied to select the optimal features from the dataset. Based on the selected optimal features, the Improved Elman Spiking Neural Network (IESNN) model performs attack detection and classification. The BAOA-IESNN model attained 99.39% accuracy, 99.24% detection rate, 99.30% precision, and 99.26% f1-score in binary classification, and 98.85% accuracy, 98.79% detection rate, 98.87% precision, and 98.83% f1-score in binary classification. This BAOA-IESNN model outperformed the current models compared in this research by demonstrating an effective performance in detecting and classifying attacks.

Keywords:

Big Data, IoT, Intrusion detection, Deep Learning, BAOA, IESNN, Apache spark, BoT-IoT.

References:

[1] Claudia Cavallaro et al., “Discovering Anomalies in Big Data: A Review Focused on the Applications of Metaheuristic and Machine Learning Techniques,” Frontiers in Big Data, vol. 6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Joffrey L. Leevy, and Taghi M. Khoshgoftaar, “A Survey and Analysis of Intrusions Detections Model based on CSE-CIC-IDS 2018 Big Data,” Journal of Big Data, vol. 7, no. 1, pp. 1-19, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Luis Filipe Dias, and Miguel Coreia, “Big Data Analytic for Intrusions Detections: An Overview,” Handbooks of Research on Machine and Deep Learning Application for Cyber Security, pp. 292-316, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Xiao Chu et al., “Big Data and its V’s with IoTs to Develop Sustainability,” Scientific Programming, vol. 2021, no. 1, pp. 1-16, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Noshina Tariq et al., “The Security of Big Data in Fog-Enabled IoTs Application Including Blockchains: A Survey,” Sensors, vol. 19, no. 8, pp. 1-33, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[6] KamtaNath Mishra et al., “Cloud and Big Data Security System Reviews Principle: A Decisive Investigation,” Wireless Personal Communication, vol. 126, no. 2, pp. 1013-1050, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Bijender Bansal et al., “Big Data Architectures for Networks Security,” Cyber Security and Networks Security, pp. 233-267, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Nnamdi Johnson Ogbuke et al., “Big Data Supply Chains Analytic: Ethical, Privacy and Security Challenges Posed to Business, Industries and Society,” Productions Planning & Controls, vol. 33, no. 2-3, pp. 123-137, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Prerna Agrawal, and Savita Gandhi, “Big Data Cyber Security Analytics,” Advanced Cyber Security Technique for Data, Blockchain, IoTs, and Network Protections, pp. 21-48, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[10] S. Kumar Reddy Mallidi, and Rajeswara Rao Ramisetty, “Optimizing Intrusions Detections for IoTs: A Systematic Review of Machine Learning and Deep Learning Approach with Feature Selections and Data Balancing,” Wiley Interdisciplinary Review: Data Mining and Knowledge Discovery, vol. 15, no. 2, pp. 1-41, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Isuru Udayangani Hewapathirana, “A Comparative Study of Two-Stage Intrusion Detection Using Modern Machine Learning Approach on the CSE-CIC-IDS 2018 Datasets,” Knowledge, vol. 5, no. 1, pp. 1-19, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Sankaramoorthy Muthubalaji et al., “An Intelligent Big Data Security Framework based on AEFS-KENN Algorithm for the Detection of Cyber-Attack from Smart Grids System,” Big Data Mining and Analytics, vol. 7, no. 2, pp. 399-418, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Abdulnaser A. Hagar, and Bharti W. Gawali, “Apache Sparks and Deep Learning Model for High-Performance Network Intrusion Detection using CSE‐CIC‐IDS 2018,” Computational Intelligences and Neurosciences, vol. 2022, no. 1, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Otmane Azeroual, and Anastasija Nikiforova, “Apache Spark and MLLIB-Based Intrusion Detection Systems or How the Big Data Technologies Can Secure The Data,” Information, vol. 13, no. 2, pp. 1-18, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Wei Zhong, Ning Yu, and Chunyu Ai, “Applying Big Data-Based Deep Learning Systems to Intrusion Detection,” Big Data Mining and Analytics, vol. 3, no. 3, pp. 181-195, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Mahzad Mahdavisharif, Shahram Jamali, and Reza Fotohi, “Big Data-Aware Intrusion Detection Systems in Communications Network: A Deep Learning Approach,” Journal of Grids Computing, vol. 19, no. 4, pp. 1-28, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Abdulrahman A. Alshdadi et al., “Big Data-Driven Deep Learning Ensemble for DDoS Attack Detection,” Future Internet, vol. 16, no. 12, pp. 1-26, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Md Abdur Rahman, and Hossain Shahriar, “Clustering Enable Robust Intrusions Detections Systems for Big Data Using Hadoop - PySpark,” 2023 IEEE 20th International Conferences on Smart Communities: Improving Quality of Life using AI, Robotic and IoTs (HONET), Boca Raton, FL, USA, pp. 249-254, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Rubayyi Alghamdi, and Martine Bellaiche, “Evaluations and Selections Model for Ensembled Intrusions Detections System in IoTs,” IoT, vol. 3, no. 2, pp. 285-314, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Brunel Elvire Bouya-Moko, Edward Kwadwo Boahen, and Changda Wang, “Fuzzy Local Information and Bhattacharya-Based C-Mean Clustering and Optimized Deep Learning in Spark Frameworks for Intrusion Detection,” Electronics, vol. 11, no. 11, pp. 1-16, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Abhijit Dnyaneshwar Jadhav, and Vidyullatha Pellakuri, “Highly Accurate and Efficient Two Phase-Intrusion Detection System (TP-IDS) using Distributed Processing of HADOOP and Machine Learning Techniques,” Journal of Big Data, vol. 8, no. 1, pp. 1-22, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Suad Mohammed Othman et al., “Intrusions Detections Models using Machine Learning Algorithms on Big Data Environments,” Journal of Big Data, vol. 5, no. 1, pp. 1-12, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Sami Yaras, and Murat Dener, “IoTs-Based Intrusion Detection Systems using New Hybrid Deep Learning Algorithms,” Electronics, vol. 13, no. 6, pp. 1-28, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Siriporn Chimphlee, and Witcha Chimphlee, “Machine Learning to Improve the Performances of Anomaly-Based Networks Intrusions Detections in Big Data,” Indonesian Journal of Electrical Engineering and Computer Sciences, vol. 30, no. 2, pp. 1106-1119, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Md. Alamin Talukder et al., “Machine Learning-Based Networks Intrusions Detections for Big and Imbalanced Data using Oversampling, Stacking Features Embedding and Feature Extraction,” Journal of Big Data, vol. 11, no. 1, pp. 1-44, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Anita Shiravani, Mohammad Hadi Sadreddini, and Hassan Nosrati Nahook, “Networks Intrusions Detections using Data Dimension Reductions Technique,” Journal of Big Data, vol. 10, no. 1, pp. 1-25, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Xiangyu Liu, and Yanhui Du, “Toward Effective Features Selections for IoTs Botnet Attacks Detections using a Genetic Algorithm,” Electronics, vol. 12, no. 5, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Abdelaziz Al Dawi et al., “An Approach to Botnet Attack in the Fog Computing Layers and Apache Spark for Smart Cities,” The Journal of Supercomputing, vol. 81, no. 4, pp. 1-30, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Yujie Zhang, and Zebin Wang, “Feature Engineering and Model Optimizations-Based Classifications Methods for Network Intrusion Detection,” Applied Sciences, vol. 13, no. 16, pp. 1-25, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Qinglei Yao, and Xiaoqiang Zhao, “An Intrusions Detections Imbalanced Data Classifications Algorithm based on CWGAN-GP Oversampling,” Peer-to-Peer Networking and Applications, vol. 18, no. 3, pp. 1-16, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Aya G. Ayad, Nehal A. Sakr, and Noha A. Hikal, “A Hybrid Approach for Efficient Features Selections in Anomaly Intrusion Detection for IoTs Networks,” The Journal of Supercomputing, vol. 80, no. 19, pp. 26942-26984, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Imène Neggaz, and Hadria Fizazi, “An Intelligent Handcrafted Features Selections using Archimedes Optimizations Algorithms for Facial Analysis,” Soft Computing, vol. 26, no. 19, pp. 10435-10464, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Lingling Fang, Yutong Yao, and Xiyue Liang, “New Binary Archimedes Optimizations Algorithms and its Applications,” Expert Systems with Applications, vol. 230, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[34] B. Meenakshi, and D. Karunkulali, “Enhanced Elman Spikes Neural Networks for Clusters Heads-Based Energy Aware Routing in WSNs,” Transaction on Emerging Telecommunication Technologies, vol. 34, no. 3, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[35] M. Deepanayaki, and Vidyaatulasiraman, “Enhanced Elman Spikes Neural Networks Optimized with Red Fox Optimizations Algorithms for Sugarcanes Yield Grades Predictions,” Smart Science, vol. 11, no. 3, pp. 568-582, 2023.
[CrossRef] [Google Scholar] [Publisher Link]