Preprocessing Solutions for Telecommunication Specific Big Data Use Cases

Thumbnail Image
Files
master_Jony_Rabiul_2014.pdf (4.92 MB)
Journal Title
Journal ISSN
Volume Title
Sähkötekniikan korkeakoulu | Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Author
Date
2014-02-10
Department
Major/Subject
Radio Communications
Mcode
S3019
Degree programme
TLT - Master’s Programme in Communications Engineering
Language
en
Pages
65+35
Series
Abstract
Big data is becoming important in mobile data analytics. The increase of networked devices and applications means that more data is being collected than ever before. All this has led to an explosion of data which is providing new opportunities to business and science. Data analysis can be divided in two steps, namely preprocessing and actual processing. Successful analysis requires advanced preprocessing capabilities. Functional needs for preprocessing include support of many data types and integration to many systems, fit for both off-line and on-line data analysis, filtering out unnecessary information, handling missing data, anonymization, and merging multiple data sets together. As a part of the thesis, 20 experts were interviewed to shed understanding on big data, its use cases, data preprocessing, feature requirements and available tools. This thesis investigates on what is big data, and how the organizations, especially telecommunications industry can gain benefit out of it. Furthermore, preprocessing as a part of value chain is presented and the preprocessing requirements are sorted. Finally, The available data analysis tools are surveyed and tested to find out the most suitable preprocessing solution. This study presents two findings as results. Firstly, it identifies the potential big data use cases and corresponding functional requirements for telecom industry based on literature review and conducted interviews. Secondly, this study distinguishes two most promising tools for big data preprocessing based on the functional requirements, preliminary testing and hands-on testing.
Description
Supervisor
Hämmäinen, Heikki
Thesis advisor
Kekolahti, Pekka
Keywords
Big data, Data preprocesing, Data value chain, Big data in telecom industry, Preprocessig tools.
Other note
Citation
Permanent link to this item
https://urn.fi/URN:NBN:fi:aalto-201403061515
Collections
[dipl] Sähkötekniikan korkeakoulu / ELEC