Diversifying big data in parallel (Master thesis)

Νούλης, Κωνσταντίνος


A characteristic that makes a query result distinctive is apparently quality. One way of enhancing the quality of a query result is diversification. Many ways have been already proposed in order to diversify a query result. In this study we utilize the algorithm of Dissimilarity and Coverage as well as the Max Cover algorithm in an attempt to diversify a query result, which is substituted by several sets of data. The novelty that is introduced in this study is the perspective through which we approach those algorithms. Diversification is conducted with the use of parallel implementations of the aforementioned algorithms in a distributed environment. With this thesis, we intend to propose a new way of diversifying Big Data efficiently, taking at the same time advantage of new distributed platforms.
Institution and School/Department of submitter: Πανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Η/Υ & Πληροφορικής
Subject classification: Algorithms
Keywords: Κατανεμημένα συστήματα,Παράλληλη υλοποίηση αλγορίθμων,Ποικιλομορφία,Hadoap,Map-reduce,Diversification,Disc
URI: http://olympias.lib.uoi.gr/jspui/handle/123456789/27893
Appears in Collections:Διατριβές Μεταπτυχιακής Έρευνας (Masters)

Files in This Item:
File Description SizeFormat 
Μ.Ε. ΝΟΥΛΗΣ ΚΩΝΣΤΑΝΤΙΝΟΣ 2017.pdf8.76 MBAdobe PDFView/Open



 Please use this identifier to cite or link to this item:
http://olympias.lib.uoi.gr/jspui/handle/123456789/27893
  This item is a favorite for 0 people.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.