Πλοήγηση ανά Συγγραφέας "Charalampakis, Evangelos"

Τώρα δείχνει 1 - 1 of 1
  • Μικρογραφία εικόνας
    Τεκμήριο
    Recommender systems and community detection in graphs.
    (Τ.Ε.Ι. Κρήτης, Σχολή Τεχνολογικών Εφαρμογών (Σ.Τ.Εφ), ΠΜΣ Πληροφορική και Πολυμέσα, 2018-09-12) Charalampakis, Evangelos; Χαραλαμπάκης, Ευάγγελος
    This thesis consists of two parts. The first part presents an overview of the literature and the proposals that exist in general, with which techniques work, what properties each one has, the pros and cons of each method, what problems they are facing and how these systems are evaluated. Each algorithm is presented along with examples from the real world. At the end of the first part of the thesis is an extensive description as well as results from an experiment based on the SCoR algorithm, an algorithm constructed to produce optimal recommendations based on the modified Vivaldi algorithm. The second part is about community detection systems in social media. This has to do with systems that, based on some “relationships” of the end-users of a social network, discover the "hidden" community of users hidden behind these explicit relationships. There is a description of how such a community can be formed at the graph level, depending on the logic of the algorithm that is required to discover this graph. We present the available techniques that are used by the various approaches. In addition, the best-known algorithms of the field are presented with results from experiments that have been performed and the advantages and disadvantages are presented for each case. At the end of the second part, we present the results of the experiment of the SCCD algorithm, which is again based on the Vivaldi algorithm and performs accurate community detection.