Efficient Analysis of the Big Data IDS Over Proposed Model
1B. Priyanka, Indivar Shaik
In the last ten years, the Internet has grown quickly. As a result, computer and network device interconnection has become so complicated to monitor, that even security experts do not fully understand their deepest internal functions. Every year, personal computers have become very quick. It is not unusual for a very ordinary individual to connect via or faster than 20 Mbs to the Internet. The security of the network has become very important for data monitoring with this enormous network data. Big data in the intrusion detection system are a major challenge to develop. In this article, the framework for pre-processing functionality was used to create sub-sets of features related to template creation. The algorithm Random Forest was used to categorize data for the network. The knowledge benefit approach was used to improve the accuracy of the Random Forest Algorithm. To check the performance of the model proposed, the NSL-KDD standard data was used. Several assessment metrics have been suggested to assess the model proposed. The empirical results of the model proposed show that performance measures are better. The results of the proposed model and various existing algorithms are comparatively analyzed. The results show that the performance of the proposed model was higher than that of existing systems.
Big data ids proposed model.