Gaussian Process Regression Plus Method for Localization Reliability Improvement

Abstract

Location data are among the most widely used context data in context-aware and ubiquitous computing applications. Many systems with distinct deployment costs and positioning accuracies have been developed over the past decade for indoor positioning. The most useful method is focused on the received signal strength and provides a set of signal transmission access points. However, compiling a manual measuring Received Signal Strength (RSS) fingerprint database involves high costs and thus is impractical in an online prediction environment. The system used in this study relied on the Gaussian process method, which is a nonparametric model that can be characterized completely by using the mean function and the covariance matrix. In addition, the Naive Bayes method was used to verify and simplify the computation of precise predictions. The authors conducted several experiments on simulated and real environments at Tianjin University. The experiments examined distinct data size, different kernels, and accuracy. The results showed that the proposed method not only can retain positioning accuracy but also can save computation time in location predictions.

Gauss process state-space model optimization algorithm with expectation maximization

“…In simulation experiments, the BFGS algorithm 21 is used to train hyperparameters of the GPSSM*, which are recorded in Table 2. (X Ã 0:50 , Y Ã 1:50 ) are the input data and the output data to construct the kernel functions of the GPSSMs [1][2][3][4] . fY i 1:50 g 4 i = 1 are taken as measurements in these non-laboratory environments.…”

“…The kernel functions k f 1 ,k f 2 , and k h in Table 3 are defined in formulas (15) and (16). Figures 4-7 show the smoothed estimation mean of pendulum models [1][2][3][4] obtained after running the EM- GP-RTSS to optimize the GPSSM*, respectively. And, the estimation of the GP-RTSS with the GPSSM* and the estimation of the URTSS with the true SSM (53) are also given.…”

“…and fs h , W h , s y g where W f i = ½s 2 f i, 1 , 0; 0, s 2 f i, 2 and W h = ½s 2 h 1 , 0; 0, s 2 h 2 . fX i 0:50 , Y i 1:50 g 4 i = 1 are obtained by running the pendulum models [1][2][3][4] separately, where X i 0:50 is unknown in the non-laboratory environment. If the GPSSM* is used to estimate X i 0:50 given Y i 1:50 , there is an overfitting issue.…”

“…For example, GPSSMs are used for target monitoring and location problems in wireless sensor networks. 1,2 In order to train the GPSSM of a nonlinear system, its true system states are required. However, paradoxically, its states are usually unknown and needed to be estimated.…”

An Efficient Radio Map Updating Algorithm based on K-Means and Gaussian Process Regression

“…However, sparse deployment of APs may degrade the performance and the APs' locations are needed. Liu et al (2016) focused on a GPRP method based on GPR and the Naive Bayes algorithm to reduce the computational complexity of indoor localisation, and it retains the flexibility of the GPR models. However, the environment is limited, and it requires additional hardware.…”