Obtaining Rough Set Approximation using MapReduce Technique in Data Mining

  Varda Dhande,  Dr. B. K. Sarkar

Nowadays data growing at tremendous rate, which creates a many challenges in immense data mining and knowledge discovery. Rough set theory is one of the tool for data mining in which lower and upper approximations are basic concepts. By using Rough Set theory with Map-Reduce technique parallelization of approximation is possible. This paper proposes a parallel method for rough set approximation for handling unstructured data, with the help of Hadoop technology. Related algorithms for parallel method based on map-reduce technique are put forward to deal with unstructured data. The time efficiency in calculating Rough Set approximation using parallel method can be increased by using attribute selection option, for avoiding redundant attributes which are responsible for time consummation and for degrading quality of decision rules, which will discovered from lower and upper rough set approximation.

Keywords- Data Mining, Map-Reduce, Rough Set, Approximations, Hadoop, HDFS

Unique Identification Number - IJEDR1604127
Page Number(s) - 851-855
Pubished in - Volume 4 | Issue 4 | December 2016
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Varda Dhande,  Dr. B. K. Sarkar,   "Obtaining Rough Set Approximation using MapReduce Technique in Data Mining", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.4, Issue 4, pp.851-855, December 2016, Available at :http://www.ijedr.org/papers/IJEDR1604127.pdf