Tag Archives: gps

A Simulation Study on Automated Transport Mode Detection in Near-Real Time using a Neural Network

Das, R.D., Ronald, N., and Winter. S. (2015), A Simulation Study on Automated Transport Mode Detection in Near-Real Time using a Neural Network. In Proceedings of Research@Locate’15, Brisbane, Australia.

Detecting transport modes in near-real time is important for various context-aware location based services and understanding urban dynamics. In this paper we present a simulated study on detecting transport modes in near-real time using a neural network. We have shown how detection accuracy will vary with different temporal window sizes and different combination of modes. Since in urban environment transport modes move slowly due to traffic, considering movement attributes or kinematics alone for mode detection is not sufficient. That is why we investigated how spatial information can improve mode detection accuracy. The model has achieved 82%-95% accuracy and proves its efficacy over other detection models.

This paper is available online in the Research@Locate proceedings.

Clustering based Transfer Detection with Fuzzy Activity Recognition from Smart-phone GPS Trajectories

Das, R. D., Ronald, N., Winter, S. (2014), Clustering based Transfer Detection with Fuzzy Activity Recognition from Smart-phone GPS Trajectories, 17th International IEEE Conference on Intelligent Transportation Systems. IEEE, Qingdao, China.

This paper introduces an adaptive clustering-based transfer detection framework. Existing transfer detection algorithms are based on a walking-based approach. But in a walking-based approach it is difficult to set a deterministic walking threshold. However during transfer people generally move slowly or wait for a while and thus the spatio-temporal points are located close to each other and tend to form clusters. To mitigate such problems an adaptive density-based fuzzy approach is proposed for detecting transfers and activities performed during transfers.

Please contact one of the authors for a copy.

ITSC 2014, 8-11 October

iMoD is well-represented at this week’s IEEE Intelligent Transport Systems Conference in Qingdao, China.

Rahul Deb Das will present his work on automated detection of mode transfers based on GPS data. A poster by Michael Rigby on visualising pickup locations for ridesharing will also appear. Joint work by Stephan Winter with Iven Mareels (Dean, Melbourne School of Engineering) and IBM Research on personalized (leased) public transportation will also be presented.

Please feel free to contact Rahul or Stephan to organise a meeting about the iMoD project.