Adaptive Indoor Localization with Wi-Fi Based on Transfer Learning

摘要

Many approaches used in The Wi-Fi based indoor location system (WILS) typically assume the distribution of the signal strength data is time invariant. However, the assumption does not hold in real world, which degrades the location accuracy. We propose an algorithm that can adjust the distribution of training data by mixing a fraction of new data. Experimental results show that our algorithm can greatly improve the localization accuracy and reduce a great amount of the calibration effort.