TOAD: Trace Ordering for Anomaly Detection

Richter, Florian; Lu, Yifeng; Zellner, Ludwig; Sontheim, Janina; Seidl, Thomas

doi:10.1109/icpm49681.2020.00033

Cited by 4 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For crowded scenes, Wang Q [14] fuses acceleration information with optical flow characteristics, the mixed optical flow histogram is constructed as the feature descriptor, and the abnormal behavior detection is realized by the sparse representation method. [15] The feature extraction method based on motion trajectory to construct features by acquiring the position, length, speed, and other information of the object in the process of moving. In this regard, some scholars have proposed the dense trajectory algorithm, which intensively samples the feature points, extracts their trajectory features and encodes them, and classifies them by support vector machine.…”

Section: Feature Extraction Methods Based On Human Appearance and Mov...mentioning

confidence: 99%

A review of abnormal behavior research based on motion characteristics

Liu

2023

International Conference on Electronic Information Engineering and Data Processing (EIEDP 2023)

View full text Add to dashboard Cite

Section: Feature Extraction Methods Based On Human Appearance and Mov...mentioning

confidence: 99%

A review of abnormal behavior research based on motion characteristics

Liu

2023

International Conference on Electronic Information Engineering and Data Processing (EIEDP 2023)

View full text Add to dashboard Cite

“…In [11], the authors identify such outliers of event pairs online by using hashing for event collecting and applying z-scoring to define an in-control area for unsuspicious event relations. In [10], this idea is leveraged on the trace level to detect collective trace anomalies using density-based clustering on temporal deviation signatures. We adapt the presented clustering technique for OTOSO.…”

Section: Related Workmentioning

confidence: 99%

OTOSO: Online Trace Ordering for Structural Overviews

Richter

Maldonado

Zellner

et al. 2021

Lecture Notes in Business Information Processing

Self Cite

View full text Add to dashboard Cite

Identifying structures in data is an essential step to enhance insights and understand applications. Clusters and anomalies are the basic building blocks for those structures and occur in various types. Clusters vary in shape and density, while anomalies occur as single-point outliers, contextual or collective anomalies. In online applications, clusters even have a higher complexity. Besides static clusters, which represent a persistent structure throughout the whole data stream, many clusters are dynamic, tend to drift and are only observable in certain time frames. Here, we propose OTOSO, a monitoring tool based on OPTICS. OTOSO is an anytime structure visualizer, that plots representations for density-based trace clusters in process event streams. It identifies temporal deviation clusters and visualizes them as a time-dependent graph. Each node represents a cluster of traces by size and density. Edges yield information about merging and splitting trace clusters. The aim is to provide an on-demand overview over the temporal deviation structure during the process execution. Not only for online applications, but also for static datasets, our approach yields insights about temporally limited occurrences of trace clusters, which are difficult to detect using a global clustering approach.

show abstract