No abstract

Cloud computing offers a technological revolution to the end-users need less infrastructure costs with virtualizes resources, and storage remains the insecure to delivers the scalability. The most common type of Distributed Denial of Service DDoS attack, (denial of service), is a serious damage measure that affects virtual cloud users and Internet Service Providers (ISPs) are predominantly affects ongoing service attacks. I'm the recipient. These legacy of machine learning approach used to detect vulnerabilities to the attacker's leading network traffic intervention opening the door. By concentrating feature selection and classification approach with optimized neural network model to detect the DDoS type monitoring. This presents a deep neural network based DDoS detection system using Subset Feature Selection based Cascade Correlation Optimal Neural Network (SFS-C2ONN). The proposed approach is based on assumptions based on flow rate which is collected as dataset previously extracted from a model for network traffic. The test results shows that the sensitivity and specify based calcification approach which is suitable for the detection of neural network architecture and hyper parameters, and the optimizer DDoS attack. The results are obtained by calculating the accuracy of the attack detection.

No abstract

No abstract

In Data Mining, the Association rule mining is used to retrieve the recurrent item sets. Apriori algorithm is mainly used to mine association rules. In that, rule reduction is required for efficient decision-making system. Knowledge based rule reduction schemes are used to filter the interested rules. In the existing system rule validation is not provided. Quantitative attributes are not considered in the post-mining scheme. Weighted rule mining scheme is not supported. This paper proposes Weighted Rule mining approach to perform post mining on derived rules with ontology support.Post mining schemes are used to filter consequent rules. Based on the Support and confidence values, the interested rules are selected rules and the same is used for the decision making process. Here, rule-mining scheme is improved to handle quantitative attributes. The WARM method is improved with validation methods. Then weighted rule mining and filtering process can be incorporated with the ARIPSO scheme. And also the rank based concept relationship analysis can be provided to improve the post mining process. Ontology based Association rule mining and Ontology based weighted Rule mining comparative analysis are focused.