The Data Mining Forum 
IMPORTANT: This is the old Data Mining forum.
I keep it online so that you can read the old messages.
Please post your new messages in the new forum: https://forum2.philippe-fournier-viger.com/index.php
HUIM-HC and HUIM-SA: very efficient algorithms for approximate high utility itemset mining
Posted by:
webmasterphilfv
Date: May 05, 2021 08:31AM
Hi all,
This is to let you know that we have just proposed two new algorithms for approximate high utility itemset mining:
- HUIM-HC : using Hill-Climbing
- HUIM-SA : using Simulated Annealing
If you want to read the paper will appear in the ACM TMIS journal. The PDF is here.
In the paper we show that HUIM-SA is generally faster than previous approximate algorithms (HUIM-GA, HUIM-PSO, HUIF-BA, HUIF-GA, HUIM-BPSO) while finding about the same number of high utility itemsets.
I will add the source code and datasets to SPMF next week so that they can be used in your studies or to compare with them. If you need them earlier, you can also send me a message.
Best regards,
Philippe
Edited 1 time(s). Last edit at 05/05/2021 08:31AM by webmasterphilfv.
This is to let you know that we have just proposed two new algorithms for approximate high utility itemset mining:
- HUIM-HC : using Hill-Climbing
- HUIM-SA : using Simulated Annealing
If you want to read the paper will appear in the ACM TMIS journal. The PDF is here.
In the paper we show that HUIM-SA is generally faster than previous approximate algorithms (HUIM-GA, HUIM-PSO, HUIF-BA, HUIF-GA, HUIM-BPSO) while finding about the same number of high utility itemsets.
I will add the source code and datasets to SPMF next week so that they can be used in your studies or to compare with them. If you need them earlier, you can also send me a message.
Best regards,
Philippe
Edited 1 time(s). Last edit at 05/05/2021 08:31AM by webmasterphilfv.