Poster Abstract: Frugal Crowd Sensing for Bus Arrival Time Prediction in Developing Regions

The design of crowd sensing applications that can supplement public transportation information systems have generally assumed availability of high-speed Internet connections coupled with high data sampling and gathering via data-hungry application interfaces. But, in developing regions, low-income users generally avoid the use of data-intensive applications over the Internet connection provided by their mobile operator. Moreover, transit centers and bus operators in such regions are generally poorly equipped or incapable of providing any infrastructure support. Based on this fact, this paper presents the system requirements and system concept of a mobile application that is being developed for the problem of bus arrival time prediction in developing regions. The proposed application seeks minimal data exchange with each user, by gathering data only when the user is static, standing at a bus stop.