JP Journal of Heat and Mass Transfer
Special Volume, Issue III, Advances in Mechanical System and ICT-convergence, Pages 341 - 346
(August 2018) http://dx.doi.org/10.17654/HMSI318341 |
|
A NOVEL SIMILARITY MEASURE FOR TRACE CLUSTERING BASED ON NORMALIZED GOOGLE DISTANCE
Hong-Nhung Bui, Quang-Thuy Ha and Tri-Thanh Nguyen
|
Abstract: In trace clustering, a problem of process mining, traditional distance measures only focus on the local relationship between trace pairs. In this paper, we propose a new method to measure the global relationship of the traces based on the Normalized Google Distance. Experimental results show that our method not only outperforms alternatives but also helps to speed up the trace clustering. |
Keywords and phrases: process mining, process discovery, trace clustering, Normalized Google Distance, similarity measure. |
|
Number of Downloads: 574 | Number of Views: 3588 |
|