@article{1,
  keywords = {Classification, GIS, Machine learning, Mode identification, Spatial statistics, Spatiotemporal, Transit, Transportation},
  author = {Akram Nour and Bruce Hellinga and Jeffrey Casello},
  title = {2016 Transportation Mode Classification Based on Smart-Phone data:  Enhancing Accuracy Using Spatial Statistics and GIS},
  abstract = {<p>As the practices of transportation engineering and planning evolve from “data poor” to “data rich”, methods to automate the translation of data to information become increasingly important. A major field of study is the automatic identification of travel modes from passively collected GPS data. In previous work, the authors have developed a robust modal classification system using an optimized combination of statistical inference techniques. One problem that remains very difficult is the correct identification of transit travel, particularly when the system is operating in mixed traffic. This type of operation generates a wide range of values for many travel parameters (average speed, maximum speed, and acceleration for example) which have similar characteristics to other urban modes. In this paper, we supplement the previous research to improve the identification of transit trips. The method employed evaluates the likelihood that GPS travel data belong to transit by comparing the location and pattern of zero-travel speeds (stopping) to the presence of transit stops and signalized intersections. These comparisons are done in a GIS. The consideration of the spatial attributes of GPS data vastly improves the accuracy of transit travel prediction.</p>
},
  year = {2016},
  journal = {Journal of Transportation Geography},
  volume = {51},
  chapter = {36},
  pages = {36-44},
  month = {02/2016},
  url = {http://www.sciencedirect.com/science/article/pii/S0966692315002070},
  doi = {http://dx.doi.org/10.1016/j.jtrangeo.2015.11.005},
}