TY - GEN
T1 - A novel indoor coverage measurement scheme based on FRFT and gaussian process regression
AU - Wu, Shaochuan
AU - Zhou, Xiaokang
AU - Gao, Yulong
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/12
Y1 - 2019/12
N2 - Techniques like femtocells are widely used to extend service coverage in indoors and other areas that are unreachable for traditional radio access technologies. In this paper, we consider the indoor coverage measurement problem. We formulate this problem into two parts: the sampling and the reconstruction of received signal strength (RSS) field. Traditional methods cannot solve the RSS fluctuation problem efficiently and require a large number of sensor nodes. To this end, we propose a novel indoor coverage measurement scheme to tackle these problems. First, a fractional Fourier transform (FRFT) based method is proposed to mitigate RSS fluctuation during the sampling process. Then, Gaussian process regression (GPR) is used to reduce the number of sensor nodes being deployed. And a new kernel for GPR is designed to better accomplish the RSS reconstruction task. Simulation analysis shows the proposed scheme can achieve greater advantages in terms of accuracy and flexibility compared with other baselines.
AB - Techniques like femtocells are widely used to extend service coverage in indoors and other areas that are unreachable for traditional radio access technologies. In this paper, we consider the indoor coverage measurement problem. We formulate this problem into two parts: the sampling and the reconstruction of received signal strength (RSS) field. Traditional methods cannot solve the RSS fluctuation problem efficiently and require a large number of sensor nodes. To this end, we propose a novel indoor coverage measurement scheme to tackle these problems. First, a fractional Fourier transform (FRFT) based method is proposed to mitigate RSS fluctuation during the sampling process. Then, Gaussian process regression (GPR) is used to reduce the number of sensor nodes being deployed. And a new kernel for GPR is designed to better accomplish the RSS reconstruction task. Simulation analysis shows the proposed scheme can achieve greater advantages in terms of accuracy and flexibility compared with other baselines.
KW - Fractional Fourier Transform
KW - Gaussian Process Regression
KW - Indoor Coverage Measurement
UR - https://www.scopus.com/pages/publications/85082295156
U2 - 10.1109/GCWkshps45667.2019.9024373
DO - 10.1109/GCWkshps45667.2019.9024373
M3 - 会议稿件
AN - SCOPUS:85082295156
T3 - 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings
BT - 2019 IEEE Globecom Workshops, GC Wkshps 2019 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 IEEE Globecom Workshops, GC Wkshps 2019
Y2 - 9 December 2019 through 13 December 2019
ER -