Belief Interval of Dempster-Shafer Theory for Line-of-Sight Identification in Indoor Positioning Applications

Location data are among the most widely used contextual data in context-aware and ubiquitous computing applications. Numerous systems with distinct deployment costs and levels of positioning accuracy have been developed over the past decade for indoor positioning purposes. The most useful method focuses on the received signal strength (RSS) and provides a set of signal transmission access points. Furthermore, most positioning systems are based on non-line-of-sight (NLOS) rather than line-of-sight (LOS) conditions, and this cause ranging errors for location predictions. Hence, manually compiling a fingerprint database measuring RSS involves high costs and is thus impractical in online prediction environments. In our proposed method, a comparison method is derived on the basis of belief intervals, as proposed in Dempster-Shafer theory, and the signal features are characterized on the LOS and NLOS conditions for different field experiments. The system performance levels were examined with different features and under different environments through robust testing and by using several widely used machine learning methods. The results showed that the proposed method can not only retain positioning accuracy but also save computation time in location predictions.