@ARTICLE{6834786,
author={J. Zhang and J. Wong and Y. Pan and T. Li},
journal={IEEE Transactions on Knowledge and Data Engineering},
title={A Parallel Matrix-Based Method for Computing Approximations in Incomplete Information Systems},
year={2015},
volume={27},
number={2},
pages={326-339},
abstract={As the volume of data grows at an unprecedented rate, large-scale data mining and knowledge discovery present a tremendous challenge. Rough set theory, which has been used successfully in solving problems in pattern recognition, machine learning, and data mining, centers around the idea that a set of distinct objects may be approximated via a lower and upper bound. In order to obtain the benefits that rough sets can provide for data mining and related tasks, efficient computation of these approximations is vital. The recently introduced cloud computing model, MapReduce, has gained a lot of attention from the scientific community for its applicability to large-scale data analysis. In previous research, we proposed a MapReduce-based method for computing approximations in parallel, which can efficiently process complete data but fails in the case of missing (incomplete) data. To address this shortcoming, three different parallel matrix-based methods are introduced to process large-scale, incomplete data. All of them are built on MapReduce and implemented on Twister that is a lightweight MapReduce runtime system. The proposed parallel methods are then experimentally shown to be efficient for processing large-scale data.},
keywords={approximation theory;cloud computing;data mining;matrix algebra;rough set theory;lightweight MapReduce runtime system;Twister;large-scale data analysis;cloud computing;rough set theory;knowledge discovery;large-scale data mining;incomplete information system;approximation method;parallel matrix-based method;Approximation methods;Vectors;Information systems;Data mining;Rough sets;Approximation algorithms;Computational modeling;Rough sets;data mining;MapReduce;matrix;incomplete information systems},
doi={10.1109/TKDE.2014.2330821},
ISSN={1041-4347},
month={Feb},}