TY - GEN
T1 - Modeling and mining optimal patterns using dynamic CSP
AU - Ugarte, Willy
AU - Boizumault, Patrice
AU - Crémilleux, Bruno
AU - Loudni, Samir
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/1/4
Y1 - 2016/1/4
N2 - We introduce the notion of Optimal Patterns (OPs), defined as the best patterns according to a given user preference, and show that OPs encompass many data mining problems. Then, we propose a generic method based on a Dynamic Constraint Satisfaction Problem to mine OPs, and we show that any OP is characterized by a basic constraint and a set of constraints to be dynamically added. Finally, we perform an experimental study comparing our approach vs adhoc methods on several types of OPs.
AB - We introduce the notion of Optimal Patterns (OPs), defined as the best patterns according to a given user preference, and show that OPs encompass many data mining problems. Then, we propose a generic method based on a Dynamic Constraint Satisfaction Problem to mine OPs, and we show that any OP is characterized by a basic constraint and a set of constraints to be dynamically added. Finally, we perform an experimental study comparing our approach vs adhoc methods on several types of OPs.
KW - Dynamic CSP
KW - Optimisation
KW - Pattern Mining
UR - https://www.scopus.com/pages/publications/84963579549
U2 - 10.1109/ICTAI.2015.19
DO - 10.1109/ICTAI.2015.19
M3 - Contribución a la conferencia
AN - SCOPUS:84963579549
T3 - Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
SP - 33
EP - 40
BT - Proceedings - 2015 IEEE 27th International Conference on Tools with Artificial Intelligence, ICTAI 2015
PB - IEEE Computer Society
T2 - 27th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2015
Y2 - 9 November 2015 through 11 November 2015
ER -