Acoustic NLOS identification using acoustic channel characteristics for smartphone indoor localization

As the demand for indoor localization is increasing to support our daily life in large and complex indoor environments, sound-based localization technologies have attracted researchers’ attention because they have the advantages of being fully compatible with commercial off-the-shelf (COTS) smartphones, they have high positioning accuracy and low-cost infrastructure. However, the non-line-of-sight (NLOS) phenomenon poses a great challenge and has become the technology bottleneck for practical applications of acoustic smartphone indoor localization. Through identifying and discarding the NLOS measurements, the positioning performance can be improved by incorporating only the LOS measurements. In this paper, we focus on identifying NLOS components by characterizing the acoustic channels. Firstly, by analyzing indoor acoustic propagations, the changes of acoustic channel from the line-of-sight (LOS) condition to the NLOS condition are characterized as the difference of channel gain and channel delay between the two propagation scenarios. Then, an efficient approach to estimate relative channel gain and delay based on the cross-correlation method is proposed, which considers the mitigation of the Doppler Effect and reduction of the computational complexity. Nine novel features have been extracted, and a support vector machine (SVM) classifier with a radial-based function (RBF) kernel is used to realize NLOS identification. The experimental result with an overall 98.9% classification accuracy based on a data set with more than 10 thousand measurements shows that the proposed identification approach and features are effective in acoustic NLOS identification for acoustic indoor localization via a smartphone. In order to further evaluate the performance of the proposed SVM classifier, the performance of an SVM classifier is compared with that of traditional classifiers based on logistic regression (LR) and linear discriminant analysis (LDA). The results also show that a SVM with the RBF kernel function method outperforms others in acoustic NLOS identification.