An efficient closed frequent item sets mining algorithm-for mining closed frequent item sets from data streams

Venu Madhav Kuthadi, Rajalakshmi Selvaraj

Research output: Contribution to journalArticle

Abstract

A data stream is a continuous sequence of data elements generated from a specified source. Mining frequent item sets in dynamic databases and data streams encounters some challenges that make the mining task harder than static databases. Many research works were developed in the frequent itemset mining, but these methods have the familiar problem of memory usage and processing time. Because, in data streams data elements are arrive at a rapid rate. The incoming data is unbounded and probably infinite. Due to high speed and large amount of incoming data, frequent item set mining algorithm must require a limited memory and processing time. To reduce this drawback in the existing method, a new algorithm is proposed in this paper. Here, a new algorithm is named as CFIM is developed for mining closed frequent item sets from the data streams based on their utility and consistency. During the closed frequent item sets mining, a hash table is maintained to check whether the given item set is closed or not. The computation of closed frequent item sets from the data stream will minimize the memory usage and processing time. Thus our proposed technique performance is analyzed by using the synthetic data set and compared with the exiting mining techniques.

Original languageEnglish
Pages (from-to)7467-7474
Number of pages8
JournalJournal of Computational and Theoretical Nanoscience
Volume13
Issue number10
DOIs
Publication statusPublished - Jan 1 2016

Fingerprint

Frequent Itemsets
Data Streams
Mining
Closed
Data storage equipment
Processing
Synthetic Data
encounters
Table
High Speed
high speed
Minimise

All Science Journal Classification (ASJC) codes

  • Chemistry(all)
  • Materials Science(all)
  • Condensed Matter Physics
  • Computational Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{018a32dce74846cdb428cd08dd59174f,
title = "An efficient closed frequent item sets mining algorithm-for mining closed frequent item sets from data streams",
abstract = "A data stream is a continuous sequence of data elements generated from a specified source. Mining frequent item sets in dynamic databases and data streams encounters some challenges that make the mining task harder than static databases. Many research works were developed in the frequent itemset mining, but these methods have the familiar problem of memory usage and processing time. Because, in data streams data elements are arrive at a rapid rate. The incoming data is unbounded and probably infinite. Due to high speed and large amount of incoming data, frequent item set mining algorithm must require a limited memory and processing time. To reduce this drawback in the existing method, a new algorithm is proposed in this paper. Here, a new algorithm is named as CFIM is developed for mining closed frequent item sets from the data streams based on their utility and consistency. During the closed frequent item sets mining, a hash table is maintained to check whether the given item set is closed or not. The computation of closed frequent item sets from the data stream will minimize the memory usage and processing time. Thus our proposed technique performance is analyzed by using the synthetic data set and compared with the exiting mining techniques.",
author = "Kuthadi, {Venu Madhav} and Rajalakshmi Selvaraj",
year = "2016",
month = "1",
day = "1",
doi = "10.1166/jctn.2016.5741",
language = "English",
volume = "13",
pages = "7467--7474",
journal = "Journal of Computational and Theoretical Nanoscience",
issn = "1546-1955",
publisher = "American Scientific Publishers",
number = "10",

}

An efficient closed frequent item sets mining algorithm-for mining closed frequent item sets from data streams. / Kuthadi, Venu Madhav; Selvaraj, Rajalakshmi.

In: Journal of Computational and Theoretical Nanoscience, Vol. 13, No. 10, 01.01.2016, p. 7467-7474.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An efficient closed frequent item sets mining algorithm-for mining closed frequent item sets from data streams

AU - Kuthadi, Venu Madhav

AU - Selvaraj, Rajalakshmi

PY - 2016/1/1

Y1 - 2016/1/1

N2 - A data stream is a continuous sequence of data elements generated from a specified source. Mining frequent item sets in dynamic databases and data streams encounters some challenges that make the mining task harder than static databases. Many research works were developed in the frequent itemset mining, but these methods have the familiar problem of memory usage and processing time. Because, in data streams data elements are arrive at a rapid rate. The incoming data is unbounded and probably infinite. Due to high speed and large amount of incoming data, frequent item set mining algorithm must require a limited memory and processing time. To reduce this drawback in the existing method, a new algorithm is proposed in this paper. Here, a new algorithm is named as CFIM is developed for mining closed frequent item sets from the data streams based on their utility and consistency. During the closed frequent item sets mining, a hash table is maintained to check whether the given item set is closed or not. The computation of closed frequent item sets from the data stream will minimize the memory usage and processing time. Thus our proposed technique performance is analyzed by using the synthetic data set and compared with the exiting mining techniques.

AB - A data stream is a continuous sequence of data elements generated from a specified source. Mining frequent item sets in dynamic databases and data streams encounters some challenges that make the mining task harder than static databases. Many research works were developed in the frequent itemset mining, but these methods have the familiar problem of memory usage and processing time. Because, in data streams data elements are arrive at a rapid rate. The incoming data is unbounded and probably infinite. Due to high speed and large amount of incoming data, frequent item set mining algorithm must require a limited memory and processing time. To reduce this drawback in the existing method, a new algorithm is proposed in this paper. Here, a new algorithm is named as CFIM is developed for mining closed frequent item sets from the data streams based on their utility and consistency. During the closed frequent item sets mining, a hash table is maintained to check whether the given item set is closed or not. The computation of closed frequent item sets from the data stream will minimize the memory usage and processing time. Thus our proposed technique performance is analyzed by using the synthetic data set and compared with the exiting mining techniques.

UR - http://www.scopus.com/inward/record.url?scp=85013637402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013637402&partnerID=8YFLogxK

U2 - 10.1166/jctn.2016.5741

DO - 10.1166/jctn.2016.5741

M3 - Article

AN - SCOPUS:85013637402

VL - 13

SP - 7467

EP - 7474

JO - Journal of Computational and Theoretical Nanoscience

JF - Journal of Computational and Theoretical Nanoscience

SN - 1546-1955

IS - 10

ER -