Intelligent Agents Lab


Creating Social Systems

Kpark

Mobile phone crowdsourcing is a powerful tool for many types of distributed sensing problems. However, a central issue with this type of system is that it relies on user contributed data, which may be sparse or erroneous. For the Kpark project, we have been researching methods to overcome these data limitations. Kpark, our mobile phone crowdsourcing app, monitors parking availability on the UCF campus. Our system combines multiple trust-based data fusion techniques to improve the quality of user submitted parking reports and was used by over 1600 students during the 2014-2015 academic year.

  • Code: The entire codebase for the project can be downloaded here.  
  • Data: For this project, we both used an agent-based model to simulate campus transportation patterns and collected real data from users: data.rar  
  • README: describes how to use the datasets and code.

Citation

If you want to use the data or code for this project, please cite the following paper:
"Improving the Performance of Mobile Phone Crowdsourcing Applications" Erfan Davami and Gita Sukthankar. Proceedings of the International Conference on Autonomous Agents and Multiagent Systems 2015. (pdf)


Other Publications

Please see the following publications for more information:

"Evaluating Trust-Based Fusion Models for Participatory Sensing Applications (Extended Abstract)" Erfan Davami and Gita Sukthankar. Proceedings of the International Conference on Autonomous Agents and Multi-agent Systems. 2014. pp. 1377-1378 (pdf)

Current Contributors

  • Erfan Davami
  • Gita Sukthankar