Published in 2018 International Conference on Innovation in Engineering and Technology (ICIET), 2018
Gaussian Process Regression (GPR) is highly accurate for predicting online radio maps in fingerprinting-based localization, but its accuracy depends on the mean function used; this paper compares various Indoor Positioning Systems (IPS) with GPR mean functions and introduces two new neural network-based mean functions that outperform traditional ones.
Recommended citation: M. S. Anwar, F. Hossain, N. Mehajabin, M. Mamun-Or-Rashid and M. A. Razzaque, "A Comparative Study on Gaussian Process Regression-based Indoor Positioning Systems," 2018 International Conference on Innovation in Engineering and Technology (ICIET), Dhaka, Bangladesh, 2018, pp. 1-5, doi: 10.1109/CIET.2018.8660860. keywords: {Ground penetrating radar;Artificial neural networks;Predictive models;Gaussian processes;IP networks;Data models;Indoor Positioning System;Gaussian Process Regression;Neural Network;Fingerprinting},
Download Paper