Machine-Learning Indoor Localization with Access Point Selection and Signal Strength Reconstruction

Indoor localization technique is a key enabling technology for the future Internet of things (IoT) paradigm. Improving the precision of indoor localization will expand the horizon of indoor IoT applications. In this paper, we propose an enhanced machine-learning indoor localization scheme which incorporates access point (AP) selection and the proposed signal strength reconstruction to enhance robustness in noisy environments. The proposed signal strength reconstruction scheme estimates/reconstructs the received signal strength indicator (RSSI) values of the nonselected APs from those of the selected APs to increase the size of the feature space for enhanced noise robustness. The proposed concept can be applied to various machine-learning frameworks. Simulation results demonstrate improved precision yielded by the proposed method in conjunction with support vector regression (SVR), ensemble SVR, and artificial neural network (ANN) models, as compared to these machinelearning techniques alone.