원문정보
초록
영어
In the terms of indoor positioning, the location of the fingerprint technology that based on receiving wireless LAN WIFI signal strength (RSS) has been widely used. In the process of location of fingerprint offline training, the traditional method has more manpower and time. In this paper, we propose a location of fingerprint database constructing method that based on Gaussian process regression (GPR), compared with the process of the traditional method for collecting a large number of fingerprint, now we based on the propagation law of space radio signals, the Gaussian process regression model is applied to the construction of the location fingerprint database, and forecast the location of fingerprint inside the located area through the study of collected samples, by doing this we can reduce the collecting density of fingerprint samples, improve the efficiency of position fingerprint positioning technology.
목차
1. Introduction
2. The Gaussian Process Regression Model Sketch
2.1. Determine the Objective Function
2.2. The Calculation of the Likelihood Function
2.3. Parameter Learning
2.4 Forecasting the Output
3. RSS Gaussian Process Regression Model
3.1. Model Selection
3.2 Algorithm Implementation
4. Experiment and Result Analysis
5. Conclusion
References