vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff955e270000000f0d000001000400 The rapid growth in technologies and social media provides us the enormous amount of data, and it opens a wider window for researchers to work on such data. One of the critical analyses of the data is to check the changing trends in data. These days, massive volumes of data are being generated and processed using Hadoop and its ecosystem tools. These tools help in fast and efficient computing of a significant amount of data. In this paper, we collaborate few popular clustering algorithms with big data technologies to analyze the usage of mobile phones and networks in various locations. We loaded and processed this dataset in Apache Hive to examine the number of users and most prominent systems in given areas, based on their location codes. Further, we compared the time taken to build the clustered model on our framework to that on Weka tool. It was observed that Weka takes comparatively longer to process the dataset. This analysis would not only help in management and segregation of a considerable amount of data but would also help mobile service providers to understand the patterns of usage by customers and network problems, which may persist in some regions.
Shefali Arora, Ruchi Mittal, M.P.S Bhatia
Netaji Subhas Institute of Technology, India
Big Data, Clustering Methods, Machine Learning, Hive
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 8 , Issue: 4 , Pages: 1701-1705 )
Date of Publication :
July 2018
Page Views :
109
Full Text Views :
1
|