Estimating location using Wi-Fi

Abstract

The 2007 Data Mining Contest, sponsored by the IEEE International Conference on Data Mining, demonstrated the first realistic public benchmark data for indoor location estimation using radio signal strength (RSS) that client device received from Wi-Fi access points. The contest focused on two tasks, including indoor location estimation and transferring knowledge learned from training data for indoor location estimation. Participants were asked to predict a client's location on the basis of RSS values received from Wi-Fi access points and were provided with a set of data including RSS values and location labels as training data. System science and data mining made localization through Wi-Fi and sensor feasible. This data mining contest brought several innovative solutions to this important problem and also presented new research issues, including transfer learning and semi-supervised learning.