Improving location reliability in crowd sensed data with minimal efforts

Abstract

People-centric sensing with smart phones can be used for large scale sensing of the physical world by leveraging the cameras, microphones, GPSs, accelerometers, and other sensors on the phones. Ranging from manual photo tasks to automated sensing tasks for activity monitoring, any task can be crowd sourced to smart phones to sense data from different locations at reduced cost. However, the sensed data submitted by participants is not always reliable as they can submit false data to earn money without executing the actual task. Therefore, it is important to validate the sensed data. Validating the context of every sensed data point of each participant is not a scalable solution. One alternative is to first validate the location associated with the sensed data points in order to achieve a certain degree of reliability about the sensed data. However, location validation without support from the wireless carriers is difficult. To address this problem, we propose ILR, a scheme in which we Improve the Location Reliability of mobile crowd sensed data with minimal human efforts. In this scheme, we bootstrap the trust in the system by first manually or automatically using image processing techniques validating a small number of photos submitted by participants. Based on these validations, the location of these photos is assumed to be trusted. Second, we extend this location trust to co-located sensed data points found in the Bluetooth range of the devices that provided the validated photos. This transitive trust is extended until all the co-located tasks are trusted or no new data points are found. In addition, the scheme also helps to detect false location claims associated with sensed data. We applied ILR on data collected from our McSense prototype deployed on Android phones used by students on our campus and detected a significant percentage of the malicious users. Simulation results demonstrate that ILR works well at various densities and helps detect the false location claims based on a minimal numher of validations.