论文部分内容阅读
The requirement of indoor localization draws a new challenge to the positioning technique.As the widely availability of WLAN infrastructures,wire-less signal fingerprint localization has attracted a lot of attentions.However,it is challenging due to the complexities of the indoor radio propagation characteristics exacerbated by the frequent change of indoor environment and the mobility of the user,the positioning accuracy cannot be guaranteed.Researchers propose crowd-sourced fingerprint localization.But designing a sustainable incentive mechanism of crowdsouring remains a challenge.We propose a virtual radio map based crowdsourced fingerprint indoor localization algorithm.The basic idea behind our proposed algorithm is simple: we propose Local Gaussian Process to create a virtual database using the training signal database.The virtual database,contains fixed number of reference points,is used for positioning.And the training data-base,created by user crowdsouring,is used for updating the virtual database.Simulation results show that our algorithm improves the accuracy for more than 30%.And the improvement keeps increasing as the change of indoor environment.A small scale experiment proves the efficiency of the algorithm.