Detection of risk factors using trajectory mining

This paper proposes a method for grouping trajectories as two-dimensional time-series data. Our method employed a two-stage approach. Firstly, it compared two trajectories based on their structural similarity, and determines the best correspondence of partial trajectories. Then, it calculated the value-based dissimilarity for the all pairs of matched segments, and outputs their total sum as the dissimilarity of two trajectories. We evaluated this method on two data sets. Experimental results on the Australia sign language dataset and chronic hepatitis dataset demonstrate that our method could capture the structural similarity between trajectories even in the presence of noise and local differences, and could provide better proximity for discriminating objects.