Analysis of privacy profiles applying fuzzy clustering techniques

DOI

10.2991/eusflat-19.2019.37How to use a DOI?

Keywords

privacy profiles fuzzy clustering membership degree fuzzifier cluster property

Abstract

Unsolved roots of ``privacy paradox'' motivate researchers to extricate the underlying reasons of such phenomenon. In the field of privacy research, the majority of empirical studies lack the availability of the real data collected from the actual platform instead of data received from the experimental lab setup. This paper uses the real-world data set of user privacy behavior. Different fuzzy clustering algorithms (such as Fuzzy C-means (FCM), Gustafson-Kessel (GK) algorithm, and Fuzzy Partitioning Around Medoids (PAM)) are applied to the given dataset, and their outfits are compared. The analysis provides the clustering validity procedures used to the data and then produces the partitioning results of the given set of data in the form of graphical visualizations. This work demonstrates how differently clustering algorithms behave with a given dataset producing various shapes and properties of clusters.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Aigul Kaskina
AU  - Oleksii Tyshchenko
PY  - 2019/08
DA  - 2019/08
TI  - Analysis of privacy profiles applying fuzzy clustering techniques
BT  - Proceedings of the 11th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT 2019)
PB  - Atlantis Press
SP  - 249
EP  - 255
SN  - 2589-6644
UR  - https://doi.org/10.2991/eusflat-19.2019.37
DO  - 10.2991/eusflat-19.2019.37
ID  - Kaskina2019/08
ER  -