Abstract | ||
---|---|---|
Objective: To develop an algorithm for aligning process traces that considers activity duration during alignment and helps derive data-driven insights from workflow data.Methods: We developed a duration-aware trace alignment algorithm as part of a Java application that provides visualization of the alignment. The relative weight of the activity type vs. activity duration during the alignment is an adjustable parameter. We evaluated proportional and logarithmic weights for activity duration. Results: We used duration-aware trace alignment on two real-world medical datasets. Compared with existing context-based alignment algorithm, our results show that duration-aware alignment algorithm achieves higher alignment accuracy and provides more intuitive insights for deviation detection and data visualization. Conclusion: Duration-aware trace alignment improves upon an existing trace alignment |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-41561-1_28 | ADVANCES IN DATA MINING: APPLICATIONS AND THEORETICAL ASPECTS |
Field | DocType | Volume |
Data mining,Data visualization,Dynamic time warping,Visualization,Computer science,Logarithm,Workflow,Java | Conference | 9728 |
ISSN | Citations | PageRank |
0302-9743 | 4 | 0.46 |
References | Authors | |
7 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sen Yang | 1 | 10 | 3.98 |
Moliang Zhou | 2 | 16 | 3.55 |
Rachel Webman | 3 | 10 | 1.01 |
JaeWon Yang | 4 | 10 | 1.35 |
Aleksandra Sarcevic | 5 | 182 | 26.75 |
Ivan Marsic | 6 | 716 | 91.96 |
Randall S. Burd | 7 | 122 | 21.53 |