Paper Info
Title
Visual Pattern Discovery In Timed Event Data
Abstract
Business processes have tremendously changed the way large companies conduct their business: The integration of information systems into the workflows of their employees ensures a high service level and thus high customer satisfaction. One core aspect of business process engineering are events that steer the workflows and trigger internal processes. Strict requirements on interval-scaled temporal patterns, which are common in time series, are thereby released through the ordinal character of such events. It is this additional degree of freedom that opens unexplored possibilities for visualizing event data.In this paper, we present a flexible and novel system to find significant events, event clusters and event patterns. Each event is represented as a small rectangle, which is colored according to categorical, ordinal or interval-scaled metadata. Depending on the analysis task, different layout functions are used to highlight either the ordinal character of the data or temporal correlations. The system has built-in features for ordering customers or event groups according to the similarity of their event sequences, temporal gap alignment and stacking of co-occurring events. Two characteristically different case studies dealing with business process events and news articles demonstrate the capabilities of our system to explore event data.
Year
DOI
Venue
2011
10.1117/12.871870
VISUALIZATION AND DATA ANALYSIS 2011
Keywords
Field
DocType
Event Data, Visual Analytics, Information Visualization
Data integration,Information system,Similitude,Metadata,Data mining,Information visualization,Ordinal number,Computer science,Visual analytics,Workflow
Conference
Volume
ISSN
Citations 
7868
0277-786X
6
PageRank 
References 
Authors
0.69
19
7
Name
Order
Citations
PageRank
Matthias Schäfer1164.74
Franz Wanner2533.65
Florian Mansmann358935.91
christian scheible460.69
verity stennett560.69
anders t hasselrot660.69
Daniel A. Keim777041141.60