.png){kind=icon}
返回
Event log anomaly detection method based on auto-encoder and control flow
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-023-01199-3.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Anomaly detection is widely used in the field of business process management, and researchers have proposed various anomaly detection algorithms to detect anomalies in event logs. However, existing research focuses on detecting anomalies in event logs at the data level, ignoring the problem of anomalies caused by event log control flow, especially behavioral relationships, and identifying behavioral anomalies as normal, leading to an increase in the false-negative rate of anomaly detection results, which negatively affects the performance of process mining. To solve the above problems, this article proposes an auto-encoder-based anomaly detection approach to achieve the detection of behavioral relationship anomalies in event logs through the reconstruction error between images. The approach first considers event logs containing behavioral relationships, converts the logs into images as input to the auto-encoder, and analyses the reconstruction error between images to propose a reconstruction error threshold for anomaly detection. The algorithm is able to achieve anomaly detection of behavioral relationships in event logs and reduce the false-negative rate of anomaly detection results. Experiments on synthetic datasets and real datasets show that the proposed approach can improve the recall rate and F1-score of event log anomaly detection effectively.
Keyword:
Control flow
Anomaly detection
Auto-encoder
Business process
Reconstruction error
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
暂无机构信息
引用论文
Low Noise Nanopore Platforms Optimised for the Synchronised Optical and Electrical Detection of Biomolecules.png)
Nanofluidics
NanofluidicsIF0
PREAI
分享收藏分享收藏A new 3D three-interpenetration metal–organic framework and its photocatalytic property: A combined experimental and theoretical investigation一种新的3D三互穿金属有机框架及其光催化性能: 实验和理论的结合研究
PREAI
分享收藏Anomaly detection in business processes using process mining and fuzzy association rule learningJOURNAL OF BIG DATA
OAAI
JOURNAL OF BIG DATAIF6.4
OAAI分享收藏QTL analyses for tolerance to abiotic stresses in a common bean (Phaseolus vulgaris L.) populationPLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏分享收藏
查看更多内容