Search for: All records

The massive use of vehicles as a primary means of transportation as well the increasing adoption of vehicles’ on-board sensors represents a unique opportunity for sensing and data collection. However, vehicles tend to cluster in specific regions such as highways and a few popular roads, making their utilization for data collection in isolated regions with low-density traffic difficult. We address this problem by proposing an incentive mechanism that encourages vehicles to deviate from their pre-planned trajectories to visit these isolated places. At the core of our proposal is the idea of compensation based on participants’ location diversity, which allows for rewarding vehicles in low-density traffic areas more than those located in high-density ones. We model this problem as a non-cooperative game in which participants are the vehicles and their new trajectories are their strategies. The output of this game is a new set of stable trajectories that maximize spatial coverage. Simulations show our approach outperforms the approach that doesn't take into account participants’ location diversity in terms of spatial coverage and road utilization. 

Vehicular crowdsensing (VCS) is a subset of crowd-sensing where data collection is outsourced to group vehicles. Here, an entity interested in collecting data from a set of Places of Sensing Interest (PsI), advertises a set of sensing tasks, and the associated rewards. Vehicles attracted by the offered rewards deviate from their ongoing trajectories to visit and collect from one or more PsI. In this win-to-win scenario, vehicles reach their final destination with the extra reward, and the entity obtains the desired samples. Unfortunately, the efficiency of VCS can be undermined by the Sybil attack, in which an attacker can benefit from the injection of false vehicle identities. In this paper, we present a case study and analyze the effects of such an attack. We also propose a defense mechanism based on generative adversarial neural networks (GANs). We discuss GANs' advantages, and drawbacks in the context of VCS, and new trends in GANs' training that make them suitable for VCS.