Application of One-Class Classification in NLOS Identification of UWB Positioning

Zhimin Miao, Luwen Zhao, Weiwei Yuan, Fenglin Jin

2016 · 12 citations · 13 references

Concepts

Abstract

Non Line of Sight propagation is an important reason effecting to the positioning accuracy of Ultrawide Bandwidth system. It's difficult to model and distinguish NLOS signal, as the characteristics of NLOS signal are closely related to the environment. Therefore, the NLOS identification may be modeled a one-class classification problem. This method only uses LOS signal as the target class instance to determine the one-class classification interface and realize the detection of NLOS signals. The experimental results show that, without the NLOS signals, the detection performance of one-classclassification using only LOS signals is similar to support vector machine algorithm which need two kinds of signals.

References

13