eduzhai > Applied Sciences > Engineering >

Leveraging the Self-Transition Probability of Ordinal Pattern Transition Graph for Transportation Mode Classification

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 10 pages

Abstract: The analysis of GPS trajectories is a well-studied problem in Urban Computingand has been used to track people. Analyzing people mobility and identifyingthe transportation mode used by them is essential for cities that want toreduce traffic jams and travel time between their points, thus helping toimprove the quality of life of citizens. The trajectory data of a moving objectis represented by a discrete collection of points through time, i.e., a timeseries. Regarding its interdisciplinary and broad scope of real-worldapplications, it is evident the need of extracting knowledge from time seriesdata. Mining this type of data, however, faces several complexities due to itsunique properties. Different representations of data may overcome this. In thiswork, we propose the use of a feature retained from the Ordinal PatternTransition Graph, called the probability of self-transition for transportationmode classification. The proposed feature presents better accuracy results thanPermutation Entropy and Statistical Complexity, even when these two arecombined. This is the first work, to the best of our knowledge, that usesInformation Theory quantifiers to transportation mode classification, showingthat it is a feasible approach to this kind of problem.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×