Association Measures in Network Outlier Detection Methods
Ch.Nagamani1, Suneetha Chittineni2
1Ch.Nagamani *, Research Scholar, Acharya Nagarjuna University, Guntur.
2Dr. Suneetha Chittineni, Associate Professor, Department of Computer Applications, RVR & JC College of Engg & Tech, Chowdavaram, Guntur.

Manuscript received on November 17., 2019. | Revised Manuscript received on November 24 2019. | Manuscript published on 30 November, 2019. | PP: 12218-12223 | Volume-8 Issue-4, November 2019. | Retrieval Number: D8545118419/2019©BEIESP | DOI: 10.35940/ijrte.D8545.118419

Open Access | Ethics and Policies | Cite  | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Detecting outliers before they cause any damage to the data in the network is a important constraint. Outlier detection methods need to be applied on various applications like fraud detection, network robustness analysis. This paper mainly focuses on detailed measures of both proposed intrusion and outlier detection methods with traditional methods. In the proposed work, KDD CUP data set is used. In this work, we initially divide the entire network into individual nodes for efficient monitoring. Later, the proposed methodology is applied on networks which can easily handle high / multidimensional data. While detection of outliers, the proposed method divides the entire network into sub-networks and each network is formed with density based strategy and then outlier detection is applied on them using a Efficient Crossover Design method which identifies the outliers more accurately. Finally ,the proposed method is evaluated and compared with traditional method will all possible parameters in network intrusion detection and the results prove that the performance levels of the proposed method is far better than the traditional methods.
Keywords: Comparative Analysis, Data Mining, Outlier Detections, Network Data, Processing, Clustering, Classification, Feature Extraction.
Scope of the Article: Data Mining.