In this paper, we propose an approach that extracts patterns from a temporal signal sequence without prior knowledge about the lengths, positions and the number of the patterns. Previous research  proposes a scheme for extracting recurrent patterns from noise free signal without temporal warping. To handle noise and non-linear temporal warping, Threshold Finite State Machine (TFSM) is proposed to perform spatial-temporal data modeling. The TFSM is first roughly initialized. A variance of Segmental K-means is used to train the TFSM. The training results give us both the patterns embedding in the signal sequence and the trained TFSM that can be used to represent and detect the patterns.
|Original language||English (US)|
|Number of pages||4|
|Journal||Proceedings - International Conference on Pattern Recognition|
|State||Published - 2000|
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition