An Optimized Computational Framework for Isolation Forest
Isolation Forest or iForest is one of the outstanding outlier detectors proposed in recent years. Yet, in the model setting, it is mainly based on the technique of randomization and, as a result, it is not clear how to select a proper attribute and how to locate an optimized split point on a given a...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2018-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2018/2318763 |
id |
doaj-e3acfbf273674234a661467fb2e6b54f |
---|---|
record_format |
Article |
spelling |
doaj-e3acfbf273674234a661467fb2e6b54f2020-11-24T23:18:30ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472018-01-01201810.1155/2018/23187632318763An Optimized Computational Framework for Isolation ForestZhen Liu0Xin Liu1Jin Ma2Hui Gao3Web Sciences Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaWeb Sciences Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaWeb Sciences Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaWeb Sciences Center, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaIsolation Forest or iForest is one of the outstanding outlier detectors proposed in recent years. Yet, in the model setting, it is mainly based on the technique of randomization and, as a result, it is not clear how to select a proper attribute and how to locate an optimized split point on a given attribute while building the isolation tree. Aiming to the two issues, we propose an improved computational framework which allows us to seek the most separable attributes and spot corresponding optimized split points effectively. According to the experimental results, the proposed model is able to achieve overall better performance in the accuracy of outlier detection compared with the original model and its related variants.http://dx.doi.org/10.1155/2018/2318763 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhen Liu Xin Liu Jin Ma Hui Gao |
spellingShingle |
Zhen Liu Xin Liu Jin Ma Hui Gao An Optimized Computational Framework for Isolation Forest Mathematical Problems in Engineering |
author_facet |
Zhen Liu Xin Liu Jin Ma Hui Gao |
author_sort |
Zhen Liu |
title |
An Optimized Computational Framework for Isolation Forest |
title_short |
An Optimized Computational Framework for Isolation Forest |
title_full |
An Optimized Computational Framework for Isolation Forest |
title_fullStr |
An Optimized Computational Framework for Isolation Forest |
title_full_unstemmed |
An Optimized Computational Framework for Isolation Forest |
title_sort |
optimized computational framework for isolation forest |
publisher |
Hindawi Limited |
series |
Mathematical Problems in Engineering |
issn |
1024-123X 1563-5147 |
publishDate |
2018-01-01 |
description |
Isolation Forest or iForest is one of the outstanding outlier detectors proposed in recent years. Yet, in the model setting, it is mainly based on the technique of randomization and, as a result, it is not clear how to select a proper attribute and how to locate an optimized split point on a given attribute while building the isolation tree. Aiming to the two issues, we propose an improved computational framework which allows us to seek the most separable attributes and spot corresponding optimized split points effectively. According to the experimental results, the proposed model is able to achieve overall better performance in the accuracy of outlier detection compared with the original model and its related variants. |
url |
http://dx.doi.org/10.1155/2018/2318763 |
work_keys_str_mv |
AT zhenliu anoptimizedcomputationalframeworkforisolationforest AT xinliu anoptimizedcomputationalframeworkforisolationforest AT jinma anoptimizedcomputationalframeworkforisolationforest AT huigao anoptimizedcomputationalframeworkforisolationforest AT zhenliu optimizedcomputationalframeworkforisolationforest AT xinliu optimizedcomputationalframeworkforisolationforest AT jinma optimizedcomputationalframeworkforisolationforest AT huigao optimizedcomputationalframeworkforisolationforest |
_version_ |
1725581270533013504 |