تعداد نشریات | 31 |
تعداد شمارهها | 748 |
تعداد مقالات | 7,128 |
تعداد مشاهده مقاله | 10,280,328 |
تعداد دریافت فایل اصل مقاله | 6,912,199 |
Anomaly Detection System in the Industrial Internet of Things Network with Convolutional Neural Network | ||
Computational Sciences and Engineering | ||
مقالات آماده انتشار، پذیرفته شده، انتشار آنلاین از تاریخ 24 بهمن 1402 | ||
نوع مقاله: Original Article | ||
شناسه دیجیتال (DOI): 10.22124/cse.2024.26046.1069 | ||
نویسندگان | ||
Rahim Asghari* 1؛ Sajjad Ghasemzadeh2؛ Mohammad Allahyari3 | ||
1Department of mathematics, Technical and Vocational University, Tehran, Iran. | ||
2University of Tehran, College of Engineering, Tehran, Iran. | ||
3Urmia University of Technology, Urmia, Iran. | ||
چکیده | ||
Today, information security and preventing data theft are of great importance in the industrial Internet of Things. For this reason, in order to improve the network, it is necessary to use a suitable intrusion detection system to detect anomalies and improve the network. Machine learning is one of the powerful methods used for network modeling and diagnosis. In this article, with the help of convolutional neural network modeling, which is considered one of the powerful methods of machine learning, an intrusion detection system with optimal performance in abnormal traffic detection is presented. In this method, the proposed model is implemented and shown in several classes. Also, data processing to NSL-KDD datasets is applied in this paper to obtain appropriate results that indicate the appropriate quality of the proposed evaluation model; Therefore, according to the simulation results, the accuracy and true positive rate of the NSL-KDD data set, and the proposed neural network model, the accuracy and true positive rate on the NSL-KDD data set have reached 92.3% and 88.5%, respectively. | ||
کلیدواژهها | ||
Industrial Internet of Things؛ network security؛ intrusion detection system؛ deep learning؛ convolutional neural network | ||
آمار تعداد مشاهده مقاله: 160 |