Performance Evaluation of Density-Based Outlier Detection on High Dimensional Data
Journal Title: International Journal on Computer Science and Engineering - Year 2013, Vol 5, Issue 2
Abstract
Outlier detection is a task that finds objects that are considerably dissimilar, exceptional or inconsistent with respect to the remaining data. Outlier detection has wide applications which include data analysis, financial fraud detection, network intrusion detection and clinical diagnosis of diseases. In data analysis applications, outliers are often considered as error or noise and are removed once detected. Approaches to detect and remove outliers have been studied by several researchers. Density based approaches have been proved to be effective in detecting outliers successfully, but usually requires huge amount of computations. In this paper, two approaches that enhance the traditional density based method for removing outliers are analyzed. The first method uses data partitioning method and use speed up strategies to avoid large computations. The second method presents a unified clustering and outlier detection using Neighbourhood based Local Density Factor (NLDF). The aim of both the models is to improve the performance of outlier detection, clustering and to speed up the whole process. In this paper, the working of these two papers is studied and a performance evaluation based on clustering efficiency and outlier detection efficiency is presented.
Authors and Affiliations
P. Murugavel , Dr. M. Punithavalli
Keywords
Related Articles
- EP ID EP87237
- DOI -
- Views 145
- Downloads 0
Performance of TCP/IP/ UDP adaptive header compression algorithm for wireless network
The convergence of mobile technologies will haracterize the future telecommunication systems based on TCP/IP protocols. These Protocols can be used to build both wired and wireless parts on same platform. But TCP/IP hea...
Adaption of Proactive Measure for Improving Performance Throughput Of TCP-Vegas
TCP (Transmission Control Protocol) throughput considered to be one of the most important aspects for analyzing the performance of TCP. This article represents a novel proactive technique based Acknowledge Delay which ai...
Comparative and Analysis of Biometric Systems
Biometric as the science of recognizing an individual based on his or her physical or behavioral traits, it is beginning to gain acceptance as a legitimate method for determining an individual identity. Biometric have no...
An Exact Algorithm for Multi – Product Bulk Transportation Problem
The paper investigates an NP-Hard nature Problem, where several commodities are produced in several plant sites with capacity constraints, and distributed to several destination sites according to demands and transportat...
QoS- unbroken traffic lane streaming in Road network
At present situation travel becomes the biggest hassle for everyone. In this proposed research paper I have used GPS system to find out the shortest path to make your travel at ease. Through this navigation process it is...