Efficient LCSS Distance Measure for Searching of Similar Time Series Trajectories

Many researchers have been attracted towards searching of similar moving objects trajectories due to its wide range of real time applications. Searching of similar trajectories of moving objects helps data mining users to take smart decisions and thereby improving the performance of systems. Trajectories are compared for similarity using edit distance measures such as DTW, ERP, EDR, and LCSS. These existing distance measures are popular distance measures and compare trajectories for similarity by computing proximity distance between them. Distance measures DTW, EDR, ERP, and LCSS support scaling and translation property but it does not support rotation invariant property. RI distance measure supports scaling, translation and rotation invariant property and hence RI distance measure is considered to be superior compared to other edit distance measures. Even though RI distance measure is better compared to other edit distance measures, it has two main drawbacks. The first one is, it does not compares trajectories based on the shape and this shape based searching is very much required, since proximity distance is not only the best way to compares trajectories. The second problem, RI is not robust to noise and produces poor results. In this paper, we have proposed Efficient Longest Common Sub-Sequence (ELCSS) distance measure to compares trajectories based on the shape feature. ELCSS distance measure is based on the angular distance of the trajectories. The angular distance captures the shape feature of the trajectory. We have carried out experimental study on the real time and synthetic datasets. Experimental results reveal that our proposed ELCSS distance measure compares the trajectories based on the shape feature. Further, our experimental results reveal that, ELCSS distance measure supports rotation invariant property and very robust to the noise.