Fast memory efficient local outlier detection in data streams (extended abstract)

Mahsa Salehi; Christopher Leckie; James C. Bezdek; Tharshan Vaithianathan; Xuyun Zhang

doi:10.1109/ICDE.2017.32

Fast memory efficient local outlier detection in data streams (extended abstract)

Mahsa Salehi^*, Christopher Leckie, James C. Bezdek, Tharshan Vaithianathan, Xuyun Zhang

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference abstract › peer-review

6 Citations (Scopus)

Abstract

Outlier detection is an important task in data mining. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the well-known Local Outlier Factor (LOF) algorithm has an incremental version (called iLOF), it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF_F), both have an accuracy close to iLOF but within a fixed memory bound. In addition MiLOF_F is robust to changes in the number of data points, underlying clusters and dimensions in the data stream.

Original language	English
Title of host publication	2017 IEEE 33rd International Conference on Data Engineering (ICDE 2017)
Place of Publication	Los Alamitos, CA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	51-52
Number of pages	2
ISBN (Electronic)	9781509065431
DOIs	https://doi.org/10.1109/ICDE.2017.32
Publication status	Published - 2017
Externally published	Yes
Event	IEEE 33rd International Conference on Data Engineering (ICDE) - San Diego, Canada Duration: 19 Apr 2017 → 22 Apr 2017

Publication series

Name	IEEE International Conference on Data Engineering
Publisher	IEEE
ISSN (Print)	1084-4627

Conference

Conference	IEEE 33rd International Conference on Data Engineering (ICDE)
Country/Territory	Canada
City	San Diego
Period	19/04/17 → 22/04/17

Access to Document

10.1109/ICDE.2017.32

Cite this

Salehi, M., Leckie, C., Bezdek, J. C., Vaithianathan, T., & Zhang, X. (2017). Fast memory efficient local outlier detection in data streams (extended abstract). In 2017 IEEE 33rd International Conference on Data Engineering (ICDE 2017) (pp. 51-52). (IEEE International Conference on Data Engineering). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICDE.2017.32

@inbook{1096190c477f49708cff3f6dd0d61be9,

title = "Fast memory efficient local outlier detection in data streams (extended abstract)",

abstract = "Outlier detection is an important task in data mining. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the well-known Local Outlier Factor (LOF) algorithm has an incremental version (called iLOF), it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF_F), both have an accuracy close to iLOF but within a fixed memory bound. In addition MiLOF_F is robust to changes in the number of data points, underlying clusters and dimensions in the data stream.",

author = "Mahsa Salehi and Christopher Leckie and Bezdek, {James C.} and Tharshan Vaithianathan and Xuyun Zhang",

year = "2017",

doi = "10.1109/ICDE.2017.32",

language = "English",

series = "IEEE International Conference on Data Engineering",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "51--52",

booktitle = "2017 IEEE 33rd International Conference on Data Engineering (ICDE 2017)",

address = "United States",

note = "IEEE 33rd International Conference on Data Engineering (ICDE) ; Conference date: 19-04-2017 Through 22-04-2017",

}

Salehi, M, Leckie, C, Bezdek, JC, Vaithianathan, T & Zhang, X 2017, Fast memory efficient local outlier detection in data streams (extended abstract). in 2017 IEEE 33rd International Conference on Data Engineering (ICDE 2017). IEEE International Conference on Data Engineering, Institute of Electrical and Electronics Engineers (IEEE), Los Alamitos, CA, pp. 51-52, IEEE 33rd International Conference on Data Engineering (ICDE), San Diego, Canada, 19/04/17. https://doi.org/10.1109/ICDE.2017.32

Fast memory efficient local outlier detection in data streams (extended abstract). / Salehi, Mahsa; Leckie, Christopher; Bezdek, James C. et al.
2017 IEEE 33rd International Conference on Data Engineering (ICDE 2017). Los Alamitos, CA: Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 51-52 (IEEE International Conference on Data Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference abstract › peer-review

TY - CHAP

T1 - Fast memory efficient local outlier detection in data streams (extended abstract)

AU - Salehi, Mahsa

AU - Leckie, Christopher

AU - Bezdek, James C.

AU - Vaithianathan, Tharshan

AU - Zhang, Xuyun

PY - 2017

Y1 - 2017

N2 - Outlier detection is an important task in data mining. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the well-known Local Outlier Factor (LOF) algorithm has an incremental version (called iLOF), it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF_F), both have an accuracy close to iLOF but within a fixed memory bound. In addition MiLOF_F is robust to changes in the number of data points, underlying clusters and dimensions in the data stream.

AB - Outlier detection is an important task in data mining. With the growing need to analyze high speed data streams, the task of outlier detection becomes even more challenging as traditional outlier detection techniques can no longer assume that all the data can be stored for processing. While the well-known Local Outlier Factor (LOF) algorithm has an incremental version (called iLOF), it assumes unbounded memory to keep all previous data points. In this paper, we propose a memory efficient incremental local outlier (MiLOF) detection algorithm for data streams, and a more flexible version (MiLOF_F), both have an accuracy close to iLOF but within a fixed memory bound. In addition MiLOF_F is robust to changes in the number of data points, underlying clusters and dimensions in the data stream.

UR - http://www.scopus.com/inward/record.url?scp=85021238905&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2017.32

DO - 10.1109/ICDE.2017.32

M3 - Conference abstract

T3 - IEEE International Conference on Data Engineering

SP - 51

EP - 52

BT - 2017 IEEE 33rd International Conference on Data Engineering (ICDE 2017)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Los Alamitos, CA

T2 - IEEE 33rd International Conference on Data Engineering (ICDE)

Y2 - 19 April 2017 through 22 April 2017

ER -

Salehi M, Leckie C, Bezdek JC, Vaithianathan T, Zhang X. Fast memory efficient local outlier detection in data streams (extended abstract). In 2017 IEEE 33rd International Conference on Data Engineering (ICDE 2017). Los Alamitos, CA: Institute of Electrical and Electronics Engineers (IEEE). 2017. p. 51-52. (IEEE International Conference on Data Engineering). doi: 10.1109/ICDE.2017.32

Fast memory efficient local outlier detection in data streams (extended abstract)

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this