DocumentCode
538851
Title
Busy Line Analysis with Improved Association Rules Mining Algorithm for Hangzhou Public Free-Bicycle System
Author
Zhang, Wanjun ; Ge, Yinglong ; Yuan, Baolan ; Xu, Haitao
Author_Institution
Sch. of Software Eng., Hangzhou Dianzi Univ., Hangzhou, China
Volume
1
fYear
2010
fDate
16-17 Dec. 2010
Firstpage
139
Lastpage
142
Abstract
In China, Hangzhou is the first city to set up the Public Free-Bicycle System. There are many and many technology problems in the decision of intelligent dispatch. In this paper, we investigate the busy line of Hangzhou Public Free-Bicycle System with association rules mining algorithm. Actually, finding association rules is an important data mining problem and can be derived based on mining large frequent candidate sets. In this paper, a new procedure is proposed for efficient generating busy lines candidate set. At first, by passing over the cruel database only once, a rent-return database with entries 1 or 0 are set up. Then, the busy locations and busy lines candidate sets are obtained from the rent-return database. Finally, busy lines are mined from the busy lines candidate sets. Practice examples and comparison with the Apriori Algorithm are made on 4 rent-return databases with small, middle and large sizes from, the West Lake Scenic Zone. It is observed from the experiments that the proposed algorithm is efficient and robust.
Keywords
bicycles; data mining; public administration; rental; very large databases; Hangzhou public free-bicycle system; West lake scenic zone; apriori algorithm; association rules mining; busy line analysis; cruel database; data mining; intelligent dispatch; rent-return database; Artificial intelligence; Association rules; Bicycles; Integrated circuits; Itemsets; Apriori algorithma; Apriori algorithmssociation rules; Public Free-Bicycle System; PublicFree-Bicycle System; busy line; data mining; ssociation rules;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Systems (GCIS), 2010 Second WRI Global Congress on
Conference_Location
Wuhan
Print_ISBN
978-1-4244-9247-3
Type
conf
DOI
10.1109/GCIS.2010.159
Filename
5708730
Link To Document