Ensemble probability distribution for novelty detection

Xiaoshuang Qiao; Hui Wang; Gongde Guo; Yuanyuan Liu

doi:10.1051/matecconf/201818903008

Ensemble probability distribution for novelty detection

Xiaoshuang Qiao^*, Hui Wang, Gongde Guo, Yuanyuan Liu

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

3 Downloads (Pure)

Abstract

This paper explores a new ensemble approach called Ensemble Probability Distribution Novelty Detection (EPDND) for novelty detection. The proposed ensemble approach provides a metric to characterize different classes. Experimental results on 4 real-world datasets show that EPDND exhibits competitive overall performance to the other two common novelty detection approaches-Support Vector Domain Description and Gaussian Mixed Models in terms of accuracy, recall and F1 scores in many cases.

Original language	English
Title of host publication	MATEC Web of Conferences - 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018: proceedings
Number of pages	8
Volume	189
DOIs	https://doi.org/10.1051/matecconf/201818903008
Publication status	Published - 10 Aug 2018
Externally published	Yes
Event	2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018 - Beijing, China Duration: 25 May 2018 → 27 May 2018

Publication series

Name	MATEC Web of Conferences
Publisher	EDP Sciences
Volume	189
ISSN (Print)	2261-236X

Conference

Conference	2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018
Country/Territory	China
City	Beijing
Period	25/05/2018 → 27/05/2018

Bibliographical note

Publisher Copyright:
© 2018 The Authors, published by EDP Sciences.

ASJC Scopus subject areas

General Chemistry
General Materials Science
General Engineering

Access to Document

10.1051/matecconf/201818903008Licence: CC BY

Ensemble probability distribution for novelty detection
Copyright 2018 the authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final published version, 292 KBLicence: CC BY

Cite this

@inproceedings{397b87a183ed488292ea64099eb4d808,

title = "Ensemble probability distribution for novelty detection",

abstract = "This paper explores a new ensemble approach called Ensemble Probability Distribution Novelty Detection (EPDND) for novelty detection. The proposed ensemble approach provides a metric to characterize different classes. Experimental results on 4 real-world datasets show that EPDND exhibits competitive overall performance to the other two common novelty detection approaches-Support Vector Domain Description and Gaussian Mixed Models in terms of accuracy, recall and F1 scores in many cases.",

author = "Xiaoshuang Qiao and Hui Wang and Gongde Guo and Yuanyuan Liu",

note = "Publisher Copyright: {\textcopyright} 2018 The Authors, published by EDP Sciences.; 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018 ; Conference date: 25-05-2018 Through 27-05-2018",

year = "2018",

month = aug,

day = "10",

doi = "10.1051/matecconf/201818903008",

language = "English",

volume = "189",

series = "MATEC Web of Conferences",

publisher = "EDP Sciences",

booktitle = "MATEC Web of Conferences - 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018: proceedings",

}

Qiao, X, Wang, H, Guo, G & Liu, Y 2018, Ensemble probability distribution for novelty detection. in MATEC Web of Conferences - 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018: proceedings. vol. 189, 03008 (, MATEC Web of Conferences, vol. 189, 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018, Beijing, China, 25/05/2018. https://doi.org/10.1051/matecconf/201818903008

Ensemble probability distribution for novelty detection. / Qiao, Xiaoshuang; Wang, Hui; Guo, Gongde et al.
MATEC Web of Conferences - 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018: proceedings. Vol. 189 2018. 03008 ( (MATEC Web of Conferences; Vol. 189).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Ensemble probability distribution for novelty detection

AU - Qiao, Xiaoshuang

AU - Wang, Hui

AU - Guo, Gongde

AU - Liu, Yuanyuan

PY - 2018/8/10

Y1 - 2018/8/10

N2 - This paper explores a new ensemble approach called Ensemble Probability Distribution Novelty Detection (EPDND) for novelty detection. The proposed ensemble approach provides a metric to characterize different classes. Experimental results on 4 real-world datasets show that EPDND exhibits competitive overall performance to the other two common novelty detection approaches-Support Vector Domain Description and Gaussian Mixed Models in terms of accuracy, recall and F1 scores in many cases.

AB - This paper explores a new ensemble approach called Ensemble Probability Distribution Novelty Detection (EPDND) for novelty detection. The proposed ensemble approach provides a metric to characterize different classes. Experimental results on 4 real-world datasets show that EPDND exhibits competitive overall performance to the other two common novelty detection approaches-Support Vector Domain Description and Gaussian Mixed Models in terms of accuracy, recall and F1 scores in many cases.

U2 - 10.1051/matecconf/201818903008

DO - 10.1051/matecconf/201818903008

M3 - Conference contribution

AN - SCOPUS:85053164355

VL - 189

T3 - MATEC Web of Conferences

BT - MATEC Web of Conferences - 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018: proceedings

T2 - 2nd International Conference on Material Engineering and Advanced Manufacturing Technology, MEAMT 2018

Y2 - 25 May 2018 through 27 May 2018

ER -

Ensemble probability distribution for novelty detection

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this