A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree

碩士 === 國立中正大學 === 資訊管理所暨醫療資訊管理所 === 97 === In this paper, we proposed a novel algorithm which is implemented on the distributed system that can efficiently solve the problem of FP-tree. The algorithm uses divide and conquer to split big database into several sub-database. With data division, the alg...

Full description

Bibliographic Details
Main Authors:	Tz-ke Wu, 吳子科
Other Authors:	吳帆
Format:	Others
Language:	en_US
Published:	2009
Online Access:	http://ndltd.ncl.edu.tw/handle/14377152327481581455

id	ndltd-TW-097CCU05777015
record_format	oai_dc
spelling	ndltd-TW-097CCU057770152016-05-04T04:26:07Z http://ndltd.ncl.edu.tw/handle/14377152327481581455 A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree 一個根基於Frequent Pattern-Tree的理論分散式資料探勘演算法 Tz-ke Wu 吳子科碩士國立中正大學資訊管理所暨醫療資訊管理所 97 In this paper, we proposed a novel algorithm which is implemented on the distributed system that can efficiently solve the problem of FP-tree. The algorithm uses divide and conquer to split big database into several sub-database. With data division, the algorithm can reduce the total execution time of algorithm. The algorithm doesn’t construct the whole FP-tree. Instead, with intermittence, a time division mechanism, the algorithm can also efficiently reduce the execution time. We also compress the data into a one dimensional array while transmitting, which can reduce the communication cost. 吳帆胡雅涵 2009 學位論文 ; thesis 35 en_US
collection	NDLTD
language	en_US
format	Others
sources	NDLTD
description	碩士 === 國立中正大學 === 資訊管理所暨醫療資訊管理所 === 97 === In this paper, we proposed a novel algorithm which is implemented on the distributed system that can efficiently solve the problem of FP-tree. The algorithm uses divide and conquer to split big database into several sub-database. With data division, the algorithm can reduce the total execution time of algorithm. The algorithm doesn’t construct the whole FP-tree. Instead, with intermittence, a time division mechanism, the algorithm can also efficiently reduce the execution time. We also compress the data into a one dimensional array while transmitting, which can reduce the communication cost.
author2	吳帆
author_facet	吳帆 Tz-ke Wu 吳子科
author	Tz-ke Wu 吳子科
spellingShingle	Tz-ke Wu 吳子科 A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree
author_sort	Tz-ke Wu
title	A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree
title_short	A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree
title_full	A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree
title_fullStr	A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree
title_full_unstemmed	A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree
title_sort	novel and efficient distributed data mining algorithm based on frequent pattern-tree
publishDate	2009
url	http://ndltd.ncl.edu.tw/handle/14377152327481581455
work_keys_str_mv	AT tzkewu anovelandefficientdistributeddataminingalgorithmbasedonfrequentpatterntree AT wúzikē anovelandefficientdistributeddataminingalgorithmbasedonfrequentpatterntree AT tzkewu yīgègēnjīyúfrequentpatterntreedelǐlùnfēnsànshìzīliàotànkānyǎnsuànfǎ AT wúzikē yīgègēnjīyúfrequentpatterntreedelǐlùnfēnsànshìzīliàotànkānyǎnsuànfǎ AT tzkewu novelandefficientdistributeddataminingalgorithmbasedonfrequentpatterntree AT wúzikē novelandefficientdistributeddataminingalgorithmbasedonfrequentpatterntree
_version_	1718258451658833920

A Novel and Efficient Distributed Data Mining Algorithm Based on Frequent Pattern-Tree

Similar Items