A Clustering Algorithm for Time Series Data

In the intelligent traffic system, the research about the analysis of time series of traffic flow is important and meaningful. Using clustering methods to analyze time series not only can find some typical patterns of traffic flow, but also can group the sections of highway by their different flow characteristics. In this paper, we propose an encoded-bitmap-approach-based swap method to improve the classic hierarchical method. Experiments show that the proposed method has a better performance on the change trend of time series than classic algorithm