Cited 0 time in webofscience Cited 0 time in scopus

SSDMiner: A Scalable and Fast Disk-Based Frequent Pattern Miner

Title
SSDMiner: A Scalable and Fast Disk-Based Frequent Pattern Miner
Authors
Chon, Kang WookKim, Min Soo
DGIST Authors
Chon, Kang Wook; Kim, Min Soo
Issue Date
2018-08
Citation
7th International Conference on Emerging Databases: Technologies, Applications, and Theory, EDB 2017, 99-110
Type
Conference
ISSN
1876-1100
Abstract
Frequent itemset mining is widely used as a fundamental data mining technique. Recently, there have been proposed a number of disk-based methods. However, the existing methods still do not have a good scalability due to large-scale intermediate data and non-trivial disk I/Os. We propose SSDMiner, a new fast and scalable disk-based method for frequent itemset mining that is based on Apriori-like method and has no intermediate data and small disk I/O overheads by exploiting SSD. We propose a concept of bitmap chunks for storing transactional database in disks and a fast support counting based on bitmap chunks. Through experiments, we demonstrate that SSDMiner has the enhanced scalability and the good performance similar to that in memory-based methods with robustness. © 2018, Springer Nature Singapore Pte Ltd.
URI
http://hdl.handle.net/20.500.11750/4812
DOI
10.1007/978-981-10-6520-0_11
Publisher
Springer Verlag
Related Researcher
  • Author Kim, Min-Soo InfoLab
  • Research Interests Big Data Systems; Big Data Mining & Machine Learning; Big Data Bioinformatics; 데이터 마이닝 및 빅데이터 분석; 바이오인포메틱스 및 뉴로인포메틱스; 뇌-기계 인터페이스(BMI)
Files:
There are no files associated with this item.
Collection:
Department of Information and Communication EngineeringInfoLab2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE