Time series clustering is an important solution to various problems in numerous fields of research, including business, medical\nscience, and finance. However, conventional clustering algorithms are not practical for time series data because they are essentially\ndesigned for static data. This impracticality results in poor clustering accuracy in several systems. In this paper, a new hybrid\nclustering algorithm is proposed based on the similarity in shape of time series data. Time series data are first grouped as subclusters\nbasedon similarity intime.The subclusters are thenmergedusing the k-Medoids algorithmbased on similarity in shape. Thismodel\nhas two contributions: (1) it is more accurate than other conventional and hybrid approaches and (2) it determines the similarity in\nshape among time series data with a low complexity. To evaluate the accuracy of the proposed model, themodel is tested extensively\nusing syntactic and real-world time series datasets.
Loading....