Time series similarity matching based on event
Xue‐Yan Wu, Daoping Huang · Journal of Computer Applications · 2010
In order to do the time-series similarity matching with the users' needs and improve the accuracy,the time-series similarity matching based on event(SMBE) was proposed.First,the users' needs were defined as the event and SMBE was constructed.Then,the corresponding similarity matrix was constituted and the optimal path value was searched as the similarity measurement.Finally,the clustering method based on SMBE was proposed.The experimental results show that the clustering based on SMBE can get the accuracy of 90% with the reasonable parameters.SMBE improves the accuracy of similarity measurement with the users' needs represented by the event.