TRUM Version 1.0 =========== Maintaining frequent equivalence classes when transactions are removed. First use ecgen to generate frequent equivalence classes and the tid tree. For example, usage: ecgen input ms output ecgen t10i4d100k.dat 100 t10_100 Then use the output of ecgen as the input of trum. For trum, one need to specify the number of transactions to be removed, and the position of the first removing transaction. usage: trum input ms output #transactions startingPoint trum t10_100 100 t10_trum 1000 1234 Credits: This program was written by FENG Mengling. The project was partially supported by the I2R-SOC Joint Lab in Knowledge Discovery and FRC grant "R-252-040-238-101 & R-252-060-238-133: Pattern Spaces: Theory, Algorithms, and Applications". If you use this program, please cite: Mengling Feng, Guozhu Dong, Jinyan Li, Yap-Peng Tan, Limsoon Wong. Evolution and Maintenance of Frequent Pattern Space when Transactions are Removed. Proceedings of 11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pages ???--???, Nanjing, China, May 2007.