To search, Click below search items.


All Published Papers Search Service


Scatter-PCA for Visual Clustering of Spatio-Temporal Data


Aina Musdholifah, Siti Zaiton Mohd Hashim


Vol. 14  No. 1  pp. 72-76


In order to verify the clustering results, domain experts usually require it to be represented in interpretable and meaningful ways. For that reason, the spatio-temporal clusters obtained are essentially needed to be visualized in an understandable view to support visual exploration of cluster structures. Scatter-Principal Component Analysis (Scatter-PCA) is proposed to visualize the spatio-temporal clustering result. Scatter-PCA combines PCA that projected m-dimensional spatio-temporal data into 2 dimensional spatio-temporal data with scatter plot to visualize the structure of clusters. Two spatio-temporal data: crime data and traffic accident data are utilized to validate the visual clustering approach. The experimental results on two clustering result of spatio-temporal data demonstrate the effectiveness of our visual clustering approach to investigate the structure of clusters.


Cluster, visualization, interpretation, principal component analysis, scatter plot