Naslov
Improved Algorithm For Distributed Points Positioning Using Uncertain Objects Clustering

Autori
Lukić, Ivica ; Köhler, Mirko ; Galba, Tomislav

Izvornik
Tehnički Vjesnik-Technical Gazette (1330-3651) 26 (2019), 2; 283-288

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Clustering ; Data Mining ; Euclidian Distance ; Information Service ; Positioning

Sažetak
Positioning of mobile objects that require communication with some kind of online service application is very challenging task. Proper positioning with minimal deviation ensures that mobile service system (MSS) e.g. taxi service used in this paper, would complete its tasks to the end users and reduce overall travel distance. This paper is focused on development of the algorithm that will find the best location for MSS object and to improve its efficiency when uncertain data clustering is used. If best location for the mobile system object is chosen, then the respond time can be minimized and the given tasks could also be performed in a reasonable time. Improved bisector pruning method was proposed for clustering previous data of MSS objects to find the best location for its application. Cluster centres are used as best locations for MSS objects. In this way, total expected distance from tasks that have been set to the service system is minimized. Therefore, MSS will be improved and capable to fulfil more tasks during the shortest period of time.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

POVEZANOST RADA