Research on Method and it’s Evaluation for User Focused Frequent Itemset Mining

DOI

10.2991/iiicec-15.2015.222How to use a DOI?

Keywords

Frequent Itemsets; Attention; Association Rule; Log File

Abstract

High frequent network request pattern in office automation system (OAS) is one kind of important network behaviors which can affect the performance of OAS, especially OAS in intelligent building. High frequent network request patterns in one OAS can be mined from network access log file of the OAS. To mine high frequent network request concerned by user, user focused frequent itemset is used to describe high frequent network request concerned by user. According to early selection model of attention on information filter mechanism, attention based user focused high frequent itemset mining method is presented in this paper. To evaluate performance of algorithm for user focused high frequent itemset mining, precision ratio and recall ration are defined. Experimental results show that the performance of our proposed method is better.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhenya Zhang
AU  - Weili Wang
AU  - Hongmei Cheng
PY  - 2015/03
DA  - 2015/03
TI  - Research on Method and it’s Evaluation for User Focused Frequent Itemset Mining
BT  - Proceedings of the 2015 International Industrial Informatics and Computer Engineering Conference
PB  - Atlantis Press
SP  - 995
EP  - 998
SN  - 2352-538X
UR  - https://doi.org/10.2991/iiicec-15.2015.222
DO  - 10.2991/iiicec-15.2015.222
ID  - Zhang2015/03
ER  -