Efficient elastic burst detection in data streams

Yunyue Zhu; Dennis Shasha

doi:10.1145/956750.956789

Efficient elastic burst detection in data streams

Yunyue Zhu, Dennis Shasha

Computer Science

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

Abstract

Burst detection is the activity of finding abnormal aggregates in data streams. Such aggregates are based on sliding windows over data streams. In some applications, we want to monitor many sliding window sizes simultaneously and to report those windows with aggregates significantly different from other periods. We will present a general data structure for detecting interesting aggregates over such elastic windows in near linear time. We present applications of the algorithm for detecting Gamma Ray Bursts in large-scale astrophysical data. Detection of periods with high volumes of trading activities and high stock price volatility is also demonstrated using real time Trade and Quote (TAQ) data from the New York Stock Exchange (NYSE). Our algorithm beats the direct computation approach by several orders of magnitude.

Original language	English (US)
Title of host publication	Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '03
Pages	336-345
Number of pages	10
DOIs	https://doi.org/10.1145/956750.956789
State	Published - 2003
Event	9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '03 - Washington, DC, United States Duration: Aug 24 2003 → Aug 27 2003

Other

Other	9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '03
Country/Territory	United States
City	Washington, DC
Period	8/24/03 → 8/27/03

Keywords

Data stream
Elastic burst

ASJC Scopus subject areas

Software
Information Systems

Access to Document

10.1145/956750.956789

Cite this

@inproceedings{a2f66917873b45b5bfb0b9823d1179cf,

title = "Efficient elastic burst detection in data streams",

abstract = "Burst detection is the activity of finding abnormal aggregates in data streams. Such aggregates are based on sliding windows over data streams. In some applications, we want to monitor many sliding window sizes simultaneously and to report those windows with aggregates significantly different from other periods. We will present a general data structure for detecting interesting aggregates over such elastic windows in near linear time. We present applications of the algorithm for detecting Gamma Ray Bursts in large-scale astrophysical data. Detection of periods with high volumes of trading activities and high stock price volatility is also demonstrated using real time Trade and Quote (TAQ) data from the New York Stock Exchange (NYSE). Our algorithm beats the direct computation approach by several orders of magnitude.",

keywords = "Data stream, Elastic burst",

author = "Yunyue Zhu and Dennis Shasha",

year = "2003",

doi = "10.1145/956750.956789",

language = "English (US)",

pages = "336--345",

booktitle = "Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '03",

note = "9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '03 ; Conference date: 24-08-2003 Through 27-08-2003",

}

TY - GEN

T1 - Efficient elastic burst detection in data streams

AU - Zhu, Yunyue

AU - Shasha, Dennis

PY - 2003

Y1 - 2003

N2 - Burst detection is the activity of finding abnormal aggregates in data streams. Such aggregates are based on sliding windows over data streams. In some applications, we want to monitor many sliding window sizes simultaneously and to report those windows with aggregates significantly different from other periods. We will present a general data structure for detecting interesting aggregates over such elastic windows in near linear time. We present applications of the algorithm for detecting Gamma Ray Bursts in large-scale astrophysical data. Detection of periods with high volumes of trading activities and high stock price volatility is also demonstrated using real time Trade and Quote (TAQ) data from the New York Stock Exchange (NYSE). Our algorithm beats the direct computation approach by several orders of magnitude.

AB - Burst detection is the activity of finding abnormal aggregates in data streams. Such aggregates are based on sliding windows over data streams. In some applications, we want to monitor many sliding window sizes simultaneously and to report those windows with aggregates significantly different from other periods. We will present a general data structure for detecting interesting aggregates over such elastic windows in near linear time. We present applications of the algorithm for detecting Gamma Ray Bursts in large-scale astrophysical data. Detection of periods with high volumes of trading activities and high stock price volatility is also demonstrated using real time Trade and Quote (TAQ) data from the New York Stock Exchange (NYSE). Our algorithm beats the direct computation approach by several orders of magnitude.

KW - Data stream

KW - Elastic burst

UR - http://www.scopus.com/inward/record.url?scp=77952383186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77952383186&partnerID=8YFLogxK

U2 - 10.1145/956750.956789

DO - 10.1145/956750.956789

M3 - Conference contribution

AN - SCOPUS:77952383186

SP - 336

EP - 345

BT - Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '03

T2 - 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD '03

Y2 - 24 August 2003 through 27 August 2003

ER -

Efficient elastic burst detection in data streams

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this