Anomaly detection is an important task in many fields such as eHealth and online fraud. In this paper, we propose a new technique for anomaly detection based on a graph that connects transactions with the same attribute values and searches for dense clusters indicative of an anomalous pattern. The experimental evaluation shows that the graph-based approach outperforms two other approaches in the considered dataset. The extension of this approach to the eHealth domain is reserved as future work.
Description
A Graph-Based Approach to Detect Anomalies Based on Shared Attribute Values | SpringerLink
%0 Conference Paper
%1 10.1007/978-3-031-24801-6_36
%A Brauer, Steffen
%A Fisichella, Marco
%A Lax, Gianluca
%A Romeo, Carlo
%A Russo, Antonia
%B Applied Intelligence and Informatics
%C Cham
%D 2022
%E Mahmud, Mufti
%E Ieracitano, Cosimo
%E Kaiser, M. Shamim
%E Mammone, Nadia
%E Morabito, Francesco Carlo
%I Springer Nature Switzerland
%K myown from:mfisichella
%P 511--522
%T A Graph-Based Approach to Detect Anomalies Based on Shared Attribute Values
%X Anomaly detection is an important task in many fields such as eHealth and online fraud. In this paper, we propose a new technique for anomaly detection based on a graph that connects transactions with the same attribute values and searches for dense clusters indicative of an anomalous pattern. The experimental evaluation shows that the graph-based approach outperforms two other approaches in the considered dataset. The extension of this approach to the eHealth domain is reserved as future work.
%@ 978-3-031-24801-6
@inproceedings{10.1007/978-3-031-24801-6_36,
abstract = {Anomaly detection is an important task in many fields such as eHealth and online fraud. In this paper, we propose a new technique for anomaly detection based on a graph that connects transactions with the same attribute values and searches for dense clusters indicative of an anomalous pattern. The experimental evaluation shows that the graph-based approach outperforms two other approaches in the considered dataset. The extension of this approach to the eHealth domain is reserved as future work.},
added-at = {2024-02-07T10:24:36.000+0100},
address = {Cham},
author = {Brauer, Steffen and Fisichella, Marco and Lax, Gianluca and Romeo, Carlo and Russo, Antonia},
biburl = {https://www.bibsonomy.org/bibtex/260ff0faf9b119502b50060b8217dcd16/l3s},
booktitle = {Applied Intelligence and Informatics},
description = {A Graph-Based Approach to Detect Anomalies Based on Shared Attribute Values | SpringerLink},
editor = {Mahmud, Mufti and Ieracitano, Cosimo and Kaiser, M. Shamim and Mammone, Nadia and Morabito, Francesco Carlo},
interhash = {5062dfafa5d66ee6f1a88f5541b3693b},
intrahash = {60ff0faf9b119502b50060b8217dcd16},
isbn = {978-3-031-24801-6},
keywords = {myown from:mfisichella},
pages = {511--522},
publisher = {Springer Nature Switzerland},
timestamp = {2024-02-07T10:24:36.000+0100},
title = {A Graph-Based Approach to Detect Anomalies Based on Shared Attribute Values},
year = 2022
}