Improving the Performance of Mobile Phone Crowdsourcing Applications

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. This paper describes our experiences developing a mobile phone crowdsourcing app, Kpark, for monitoring parking availability on a university campus. Our system combines multiple trustbased data fusion techniques to improve the quality of user submitted parking reports and is currently being used by over 1500 students.