Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/79024
Title: Innovative techniques to improve frequent pattern mining in data streams
Researcher: Mala, A
Guide(s): Ramesh Dhanaseelan, F
Keywords: Computer Science and Engineering
University: Noorul Islam Centre for Higher Education
Completed Date: 20/02/2015
Abstract: iii newlineABSTRACT newline Informational Society is the most proper and fitting term to describe newlinethe present day world. An astounding and ever expanding amount of information is newlinepouring in every day which is used for organizing the economy and the society itself. newlineThis has paved the way for the collection of such information with the aid of newlinesophisticated technologies and tools such as computers, satellites, remote sensors, newlineand many more. At the outset, much more importance was given to the collection newlineand storage of information as it is an established fact that information leads to power newlineand power in turn leads to success. Unfortunately, these massive collections of data newlinefrom heterogeneous sources, stored on disparate structures very rapidly became newlineoverwhelming. Nowadays even simple transactions such as using a credit card, a newlinephone or browsing the web have become ubiquitous and mammoth. In such newlinescenarios, analysis of the collected information becomes more essential than newlinecollection and storage. Thus automatically summarizing the data, extracting the core newlineinformation and discovering interesting patterns from the vast and ever growing raw newlinedata streams has become the need of the hour. newlineThe extraction of hidden predictive information from such large streams newlineof data is commonly referred to as data stream mining. It is a new kind of technology newlinethat blends traditional data analysis methods with sophisticated algorithms for newlineprocessing large volumes of dynamic data. Traditional data analysis tools and newlinetechniques cannot be used in such cases because of the massive size of data streams. newlineAlso the transactions arrive on the data streams continuously and so they cannot be newlinestored permanently even though memory devices are cheap and readily available. newlineHence there is an urgent need to develop new schemes for storing and mining these newlinedata streams. newlineThe objective of this thesis is to apply data mining techniques to discover newlinefrequent patterns from data streams in order to understand and serve better the needs newlineof the society. In this thesis, more eff
Pagination: -
URI: http://hdl.handle.net/10603/79024
Appears in Departments:Department of Computer Science and Engineering

Files in This Item:
File Description SizeFormat 
1_cover_page.pdfAttached File11.28 kBAdobe PDFView/Open
2_bonafide_certificate.pdf229.92 kBAdobe PDFView/Open
3_abstract.pdf177.19 kBAdobe PDFView/Open
4_acknowledgement.pdf165.75 kBAdobe PDFView/Open
5_table_of_contents.pdf92.52 kBAdobe PDFView/Open
6_list_of__tables__figures__abbreviations_and_symbols.pdf521.78 kBAdobe PDFView/Open
7_references.pdf266.63 kBAdobe PDFView/Open
8_publications.pdf181.64 kBAdobe PDFView/Open
chapter_1.pdf417.12 kBAdobe PDFView/Open
chapter_2.pdf641.31 kBAdobe PDFView/Open
chapter_3.pdf769.93 kBAdobe PDFView/Open
chapter_4.pdf601.04 kBAdobe PDFView/Open
chapter_5.pdf801.92 kBAdobe PDFView/Open
chapter_6.pdf788.68 kBAdobe PDFView/Open
chapter_7.pdf194.14 kBAdobe PDFView/Open
Show full item record


Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).

Altmetric Badge: