Skip to content

MarinYoung4596/OutlierDetection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

OutlierDetection

##Overview This is an program for outlier Detection.

This project consist of 4 sub-projects, named,

  1. Generate Random Databse
  2. Outlier Detection Algorithm
  3. Outlier Analysis
  4. Python Implementation

We generate a random database for unit test to get the performance of these algorithms, Angle-Based Outlier Detection (ABOD), Density-Based Outlier Detection (LOF), and Distance-Based Outlier Detection (DBOD).

We implement all these algorithms in Visual Studio 2013 based on C# programming language. And use Outlier Analysis project to analyze the result.

##Techniques Details

  1. Distance Based Approach

DBOD

  1. Density Based Method

LOF_1 LOF_2

  1. Angle Based Algorithm

ABOD_1 ABOD_2 ABOF

##Statistical Results

  1. Precision

FastABOD_Precision_Dimension LBABOD_Precision_Dimension Precision_Dimension_N500 Precision_Dimension_N1000

  1. Dimension

Time_D_ABOD_LBABOD Time_D_FastABOD Time_D_LOF

  1. CPU Time

LBABOD_Time_D

References

To better understand the program in folder [OutlierDetection], please read the following papers:

  1. Angle-based Outlier Detection in High-Dimensional Data
  2. Outlier Detection Techniques(p.s. You may find this documents is helpful to you. enjoy :-) )

Notes

Any more questions, please feel free to contact me :-). marinyoung(at)163.com

About

An Outlier Detection Project for High Dimensional Data

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages