LOCATE: Locally Anomalous Behavior Change Detection in Behavior Information Sequence

Dingshan Cui, Lei Duan, Xinao Wang, Jyrki Nummenmaa, Ruiqi Qin, Shan Xiao

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


With the availability of diverse data reflecting people’s behavior, behavior analysis has been studied extensively. Detecting anom-alies can improve the monitoring and understanding of the objects’ (e.g., people’s) behavior. This work considers the situation where objects behave significantly differently from their previous (past) similar objects. We call this locally anomalous behavior change. Locally anomalous behavior change detection is relevant to various practical applications, e.g., detecting elderly people with abnormal behavior. In this paper, making use of objects, behavior and their associated attributes as well as the relations between them, we propose a behavior information sequence (BIS) constructed from behavior data, and design a novel graph information propagation autoencoder framework called LOCATE (locally anomalous behavior change detection), to detect the anomalies involving the locally anomalous behavior change in the BIS. Two real-world datasets were used to assess the performance of LOCATE. Experimental results demonstrated that LOCATE is effective in detecting locally anomalous behavior change.

Original languageEnglish
Title of host publicationWeb and Big Data - 4th International Joint Conference, APWeb-WAIM 2020, Proceedings
EditorsXin Wang, Rui Zhang, Young-Koo Lee, Le Sun, Yang-Sae Moon
Number of pages16
ISBN (Print)9783030602895
Publication statusPublished - 2020
Publication typeA4 Article in conference proceedings
EventAsia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint Conference -
Duration: 1 Jan 2017 → …

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceAsia-Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint Conference
Period1/01/17 → …


  • Anomaly detection
  • Behavior analysis
  • Network embedding

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)


Dive into the research topics of 'LOCATE: Locally Anomalous Behavior Change Detection in Behavior Information Sequence'. Together they form a unique fingerprint.

Cite this