Research Article AMetaheuristicAutoencoderDeepLearningModelforIntrusion Detector System JayKumarPandey , 1 Sumit Kumar , 2 Madonna Lamin , 3 Suneet Gupta , 4 Rajesh Kumar Dubey , 5 andF.Sammy 6 1 Department of Electronics and Communication Engineering, Shri Ramswaroop Memorial University, Dewa Road, Barabanki, Uttar Pradesh, India 2 Indian Institute of Management, Kozhikode, India 3 Department of Computer Science and Engineering, ITM SLS Baroda University, Vadodara, Gujarat 391510, India 4 Department of CSE, School of Engineering and Technology, Mody University, Lakshmangarh, Rajasthan, India 5 Department of Electrical Engineering, School of Engineering and Technology, Central University of Haryana, Mahendragarh, India 6 Department of Information Technology, Dambi Dollo University, Dembi Dolo, Welega, Ethiopia Correspondence should be addressed to F. Sammy; sammy@dadu.edu.et Received 23 January 2022; Revised 9 February 2022; Accepted 11 February 2022; Published 4 March 2022 Academic Editor: Vijay Kumar Copyright © 2022 Jay Kumar Pandey et al. is 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. A multichannel autoencoder deep learning approach is developed to address the present intrusion detection systems’ detection accuracy and false alarm rate. First, two separate autoencoders are trained with average traffic and assault traffic. e original samples and the two additional feature vectors comprise a multichannel feature vector. Next, a one-dimensional convolution neural network (CNN) learns probable relationships across channels to better discriminate between ordinary and attack traffic. Unaided multichannel characteristic learning and supervised cross-channel characteristic dependency are used to develop an effective intrusion detection model. e scope of this research is that the method described in this study may significantly minimize false positives while also improving the detection accuracy of unknown attacks, which is the focus of this paper. is research was done in order to improve intrusion detection prediction performance. e autoencoder can successfully reduce the number of features while also allowing for easy integration with different neural networks; it can reduce the time it takes to train a model while also improving its detection accuracy. An evolutionary algorithm is utilized to discover the ideal topology set of the CNN model to maximize the hyperparameters and improve the network’s capacity to recognize interchannel dependencies. is paper is based on the multichannel autoencoder’s effectiveness; the fourth experiment is a comparative analysis, which proves the benefits of the approach in this article by correlating it to the findings of various different intrusion detection methods. is technique outperforms previous intrusion detection algorithms in several datasets and has superior forecast accuracy. 1.Introduction With the rise of the Internet, artificial intelligence, and big data, network security is facing new and complicated threats. At the moment, people need a more powerful and robust network intrusion detection system (NIDS) because network intrusions are becoming more diverse and complex [1]. Detecting network intrusions is the goal of network intru- sion detection systems. ey look at the network traffic to see if there is any malicious activity that could be bad. To do this, it needs to build a model that can tell the difference between an attack and normal network traffic. en, NIDS can turn intrusion detection into pattern recognition and classifica- tion, use the same kinds of algorithms to get data, clean it, model it, and classify different network behaviors [2]. After years of research, the current NIDS methods can be broken down into two groups: practises based on feature detection and techniques based on anomaly detection based Hindawi Mathematical Problems in Engineering Volume 2022, Article ID 3859155, 11 pages https://doi.org/10.1155/2022/3859155