An Application of Cluster Analysis Algorithm in Traffic Control
Wang Huan-chen · Systems Engineering · 2004
Cluster analysis is a process of grouping a set of physical or abstract objects into classes of similar objects. And the objects within a cluster have high similarity in comparison to one another, but are very dissimilar to objects in other clusters. Partitioning Around Medoids(PAM) is a partitioning algorithm based on distance measure, and it still works well in the presence of noise and outlier. In this paper, we apply the PAM algorithm into the time-partition of the traffic control. The validation analysis proves that a good clustering result is achieved.