• Annu Kumari Singh

In this paper, a deep Convolutional Neural Network (CNN) model is presented for the purpose of identifying and categorizing network intrusions in near real time from an unbalanced cloud environment. In order to choose the most appropriate characteristics to feed into the CNN model, the random forest model is also provided and used. The CSE-CIC-IDS2018 datasets were used in the experiments. The outcomes demonstrate that the suggested CNN model has a testing accuracy of 97.07% and an error rate of 2.93%. The accuracy, recall, and f1-score of the suggested model were also evaluated, with results of 98.11, 96.93, and 97.52%, respectively. The outcomes are more exact, accurate, and promising. They can be successfully applied in real-time Industry 4.0 systems and are capable of detecting network anomalies with the.

CSE-CICIDS2018 datasets; random forest; feature selection; deep convolutional neural network; network intrusion detection

"Network anomaly detection and categorization using deep learning in an unbalanced cloud environment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 5, page no.g330-g337, May-2024, Available :http://www.jetir.org/papers/JETIR2405641.pdf

"Network anomaly detection and categorization using deep learning in an unbalanced cloud environment", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 5, page no. ppg330-g337, May-2024, Available at : http://www.jetir.org/papers/JETIR2405641.pdf