Trajectory Clustering in an Intersection by GDTW
نویسندگان
چکیده
GPS trajectory data in intersections are series with different lengths. Dynamic time wrapping (DTW) is good to measure the similarity between lengths, however, traditional DTW could not deal inclusive relationship well series. We propose a unified generalized algorithm (GDTW) by extending boundary constraint and continuity of using weighted local distance normalize cumulative distance. Based on density peak clustering DPCA asymmetric GDTW two trajectories, we an improved (ADPC) adopt this measurement. In experiments proposed method, number clusters reduced.
منابع مشابه
Clustering by intersection-merging
We propose Interse tion-Merging (IM), a wrapper algorithm for model-based lustering. The algorithm takes a set of lusterings obtained e.g. by EM, breaks down the lusterings into sub lusters via an interse tion step, and then agglomerates them via a merging step. We introdu e two versions of merging: greedy (standard IM) and by simulated annealing (IMSA). Experiments on several data sets show th...
متن کاملShape-based Trajectory Clustering
Automatic trajectory classification has countless applications, ranging from the natural sciences, such as zoology and meteorology, to urban planning and sports analysis, and has generated great interest and investigation. The purpose of this work is to propose and test new methods for trajectory clustering, based on shape, rather than spatial position, as is the case with previous methods. The...
متن کاملTrajectory Clustering and Coastal Surveillance
In this paper we explore trajectory clustering as a means for representing the normal behavior of vessels in a coastal surveillance scenario. Trajectory clustering however suffers from some drawbacks in this type of setting and we therefore propose a new approach, spline-based clustering, with a potential for solving the task of representing the normal course of events.
متن کاملIn-DBMS Sampling-based Sub-trajectory Clustering
In this paper, we propose an efficient in-DBMS solution for the problem of sub-trajectory clustering and outlier detection in large moving object datasets. The method relies on a two-phase process: a voting-and-segmentation phase that segments trajectories according to a local density criterion and trajectory similarity criteria, followed by a sampling-and-clustering phase that selects the most...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Advanced Transportation
سال: 2022
ISSN: ['0197-6729', '2042-3195']
DOI: https://doi.org/10.1155/2022/5978704