Izvorni znanstveni članak
https://doi.org/10.1080/00051144.2018.1541645
Parallel mining of uncertain data using segmentation of data set area and Voronoi diagrams
Ivica Lukić
; Department of Computer Engineering and Automation, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia
Željko Hocenski
; Department of Computer Engineering and Automation, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia
Mirko Köhler
; Department of Computer Engineering and Automation, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia
Tomislav Galba
; Department of Computer Engineering and Automation, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia
Sažetak
Clustering of uncertain objects in large uncertain databases and problem of mining uncertain data has been well studied. In this paper, clustering of uncertain objects with location uncertainty is studied. Moving objects, like mobile devices, report their locations periodically, thus their locations are uncertain and best described by a probability density function. The number of objects in a database can be large which makes the process of mining accurate data, a challenging and time consuming task. Authors will give an overview of existing clustering methods and present a new approach for data mining and parallel computing of clustering problems. All existing methods use pruning to avoid expected distance calculations. It is required to calculate the expected distance numerical integration, which is time-consuming. Therefore, a new method, called Segmentation of Data Set Area-Parallel, is proposed. In this method, a data set area is divided into many small segments. Only clusters and objects in that segment are observed. The number of
segments is calculated using the number and location of clusters. The use of segments gives the possibility of parallel computing, because segments are mutually independent. Thus, each segment can be computed on multiple cores.
Ključne riječi
Clustering algorithms; data mining; data uncertainty; Euclidean distance; parallel algorithms
Hrčak ID:
225211
URI
Datum izdavanja:
12.12.2018.
Posjeta: 733 *