Ten lectures on wavelets
Pattern Recognition with Fuzzy Objective Function Algorithms
Pattern Recognition with Fuzzy Objective Function Algorithms
CLARANS: A Method for Clustering Objects for Spatial Data Mining
IEEE Transactions on Knowledge and Data Engineering
Knowledge-Based Clustering: From Data to Information Granules
Knowledge-Based Clustering: From Data to Information Granules
Clustering of time series data-a survey
Pattern Recognition
Knowledge discovery in time series databases
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
| Hi-index | 0.00 |
The clustering of a group of large-scale time series with same lengths is a challenging problem. Facing with this problem, the existing clustering algorithms usually show high computation cost and low efficiency. In this paper, a knowledge-guided clustering approach is proposed for this problem. In this new approach, the given group of large-scale time series is first changed into some new groups of subsequences by segmentation. All the new groups have same sizes to that of the given group of large-scale time series. In each new group, all the subsequences have same lengths. Different subsequences are obtained from different large-scale time series and start from the same index. Thus, the clustering of the given group of large-scale time series is changed into the clustering of the last new group of subsequences which is implemented by the guidance of the cluster knowledge obtained from the previous new groups. In order to obtain better performance, we perform Haar wavelet transformation on the given group of large-scale time series, and the clustering is carried on the transformed time series. The simulation experiments are given and the results show that the new clustering approach exhibits with high efficiency in revealing the cluster property of the original group of large-scale time series.