TY - GEN
T1 - Comparison of the millimeter wave path loss estimation model with outages
AU - Lee, Kyung Gyu
AU - Oh, Seong Jun
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/4/26
Y1 - 2017/4/26
N2 - The millimeter wave is in an extremely high frequency band whose frequency and wavelength ranges are 30-300 GHz and 10-1 mm, respectively. Owing to the large distance loss and weak diffraction, a channel in the millimeter wave band experiences a propagation loss that is much worse than that of a low frequency band. When the path loss in the millimeter wave band is measured, it is observed that the data is confined within a certain range owing to limitations. If the original least square is applied to the measurement data without considering the limitations of certain values, the path loss exponent can be underestimated. Therefore, both censoring and truncation environments should be taken into account in the regression model. In this paper, the performance of the Tobit maximum likelihood estimation, Heckman two-stage model and truncation regression model are compared with the ray-tracing simulation.
AB - The millimeter wave is in an extremely high frequency band whose frequency and wavelength ranges are 30-300 GHz and 10-1 mm, respectively. Owing to the large distance loss and weak diffraction, a channel in the millimeter wave band experiences a propagation loss that is much worse than that of a low frequency band. When the path loss in the millimeter wave band is measured, it is observed that the data is confined within a certain range owing to limitations. If the original least square is applied to the measurement data without considering the limitations of certain values, the path loss exponent can be underestimated. Therefore, both censoring and truncation environments should be taken into account in the regression model. In this paper, the performance of the Tobit maximum likelihood estimation, Heckman two-stage model and truncation regression model are compared with the ray-tracing simulation.
UR - http://www.scopus.com/inward/record.url?scp=85019742880&partnerID=8YFLogxK
U2 - 10.1109/COMPEM.2017.7912810
DO - 10.1109/COMPEM.2017.7912810
M3 - Conference contribution
AN - SCOPUS:85019742880
T3 - 2017 IEEE International Conference on Computational Electromagnetics, ICCEM 2017
SP - 276
EP - 278
BT - 2017 IEEE International Conference on Computational Electromagnetics, ICCEM 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2017 IEEE International Conference on Computational Electromagnetics, ICCEM 2017
Y2 - 8 March 2017 through 10 March 2017
ER -