TY  - CHAP
ID  - SisLab3159
UR  - https://link.springer.com/chapter/10.1007%2F978-3-319-99368-3_50
A1  - Bui, Hong Nhung
A1  - Nguyen, Tri Thanh
A1  - Nguyen, Thi Cham
A1  - Ha, Quang Thuy
Y1  - 2018/08//
N2  - In process mining, trace clustering is an important technique that at-tracts the attention of researchers to solve the large and complex volume of event logs. Traditional trace clustering often uses available data mining algorithms which do not exploit the characteristic of processes. In this study, we propose a new trace clustering algorithm, especially for the process mining, based on the using trace context. The proposed clustering algorithm can automatic detects the number of clusters, and it does not need a convergence iteration like traditional ones like K-means. The algorithm takes two loops over the input to generate the clusters, thus the complexity is greatly reduced. Experimental results show that our method also has good results when compared to traditional methods.
PB  - Springer
T3  - Lecture Notes in Computer Science
SN  - ISBN 978-3-319-76080-3
ED  - Nguyen, Hung Son
ED  - Ha, Quang Thuy
ED  - li, Tianrui
ED  - Ma?gorzata, Przyby?a-Kasperek
TI  - A New Trace Clustering Algorithm Based on Context in Process Mining
SP  - 644
AV  - public
EP  - 657
T2  - International Joint Conference on Rough Sets (IJCRS 2018)
ER  -