• search hit 10 of 133
Back to Result List

Non-TI Clustering in the Context of Social Networks

  • Traditional clustering algorithms like K-medoids and DBSCAN take distances between objects as input and find clusters of objects. Distance functions need to satisfy the triangle inequality (TI) property, but sometimes TI is violated and, thus, may compromise the quality of resulting clusters. However, there are scenarios, for example in the context of social networks, where TI does not hold but a meaningful clustering is still possible. This paper investigates the consequences of TI violation with respect to different traditional clustering techniques and presents instead a clique guided approach to find meaningful clusters. In this paper, we use the quantum logic-based query language (CQQL) to measure the similarity value between objects instead of a distance function. The contribution of this paper is to propose an approach of non-TI clustering in the context of social network scenario.

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author: Sanjit Kumar Saha, Ingo SchmittORCiDGND
DOI:https://doi.org/10.1016/j.procs.2020.03.031
ISSN:1877-0509
Title of the source (English):Procedia Computer Science : The 11th International Conference on Ambient Systems, Networks and Technologies (ANT) / The 3rd International Conference on Emerging Data and Industry 4.0 (EDI40) / Affiliated Workshops
Document Type:Conference publication peer-reviewed
Language:English
Year of publication:2020
Tag:Clique; Clustering; Social Network; Triangle Inequality
Volume/Year:170
First Page:1186
Last Page:1191
Faculty/Chair:Fakultät 1 MINT - Mathematik, Informatik, Physik, Elektro- und Informationstechnik / FG Datenbank- und Informationssysteme
Einverstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.