Sustainable indoor trajectory modeling through participatory sensing and WiFi signal fusion.

Abstract

In this paper a general machine learning approach for offering indoor location awareness without the need to invest in additional and specialised hardware is presented. We explore use cases where visitors equipped with their smart phones would interact with the available WiFi infrastructure to estimate their location, since the indoor requirement poses a limitation to standard GPS solutions. The need for human participation, also referred to as human capital, is highlighted as a critical factor to the success of the approach, in order to compensate for the omission of specialized indoor location estimation equipment. Furthermore, the proposed framework enables knowledge discovery from fragmented indoor mobility trajectories by fusing sensor signals, aligning with recent advances in multi-sensor trajectory analytics. The results have shown that the proposed approach achieves accuracy of less than 2 m and in the case where a substantial number of BSSIDs are dropped, the fusion has the ability to maintain the accuracy of the approach.