Exploiting spatial abstraction in predictive analytics of vehicle traffic
Andrienko, N., Andrienko, G. & Rinzivillo, S. (2015). Exploiting spatial abstraction in predictive analytics of vehicle traffic. ISPRS International Journal of Geo-Information, 4(2), pp. 591-606. doi: 10.3390/ijgi4020591
Abstract
By applying visual analytics techniques to vehicle traffic data, we found a way to visualize and study the relationships between the traffic intensity and movement speed on links of a spatially abstracted transportation network. We observed that the traffic intensities and speeds in an abstracted network are interrelated in the same way as they are in a detailed street network at the level of street segments. We developed interactive visual interfaces that support representing these interdependencies by mathematical models. To test the possibility of utilizing them for performing traffic simulations on the basis of abstracted transportation networks, we devised a prototypical simulation algorithm employing these dependency models. The algorithm is embedded in an interactive visual environment for defining traffic scenarios, running simulations, and exploring their results. Our research demonstrates a principal possibility of performing traffic simulations on the basis of spatially abstracted transportation networks using dependency models derived from real traffic data. This possibility needs to be comprehensively investigated and tested in collaboration with transportation domain specialists.
Publication Type: | Article |
---|---|
Publisher Keywords: | Science & Technology; Physical Sciences; Technology; Geography, Physical; Remote Sensing; Physical Geography; visual analytics; mobility; traffic modeling; traffic simulation; MOVEMENT DATA; SIMULATION |
Subjects: | Q Science > QA Mathematics |
Departments: | School of Science & Technology > Mathematics School of Science & Technology > Computer Science > giCentre |
Related URLs: | |
SWORD Depositor: |
Available under License Creative Commons: Attribution International Public License 4.0.
Download (2MB) | Preview
Export
Downloads
Downloads per month over past year