OFDM Multiple Antennas Cognitive Radio Relay CDMA Synchronization Channel Estimation Spectrum Sharing Interference Cancellation Full duplex Spectrum Sensing Resource Allocation Neural Networks Stochastic Geometry Equalizer Bi-Directional Feedback Femtocell Energy Harvesting Heterogeneous Networks Device-to-Device (D2D) Cross-link interference Cell Search SINR mismatch problem Ultra-dense small cell networks HetNet Idle cells Spectral efficiency Dynamic TDD interference management NOMA FBMC selection diversity Handoff outage probability mode selection B5G multi-spectral achievable sum rate Grant-free Transmission Filtered OFDM tabu-search bursty traffic model flexible duplex 5G Asynchronous Transmission Preamble Deep learning Shortened TTI automatic repeat request (ARQ) Two-way communications transmission capacity (TC) in-band full-duplex system self-interference cancellation Complexity Ultra-dense small cell sensing duration Correlated MIMO Cognitive relay networks Heterogeneous channel estimation capability Bi-directional full-duplex full-duplex cellular full-duplex relay Simultaneous Sensing and Transmission UWB OQAM Windowing Vehicle-to-vehicle communication prototype filter pilot signal LTE-based V2V link reliability resource size control interference to noise ratio eigen decomposition TS-W-OFDM C-V2V massive connectivity Reliability Vehicle-to-Vehicle full-spreading NOMA Resource management Cooperative systems Coexistence scenarios mixed numerology 6G Cell-free Coexisting network Multiple access Railway CP-OFDM MLP Edge computing Full-duplex Mobility non-orthogonal multiple access HST interference mitigation Computation offloading TDD configuration Singular Vale Decomposition
Status : Published 
Date : 2020-12 
Title : RSRP-based Doppler Shift Estimator using Machine Learning in High-Speed Train Systems 
Authors : Taehyung Kim, Kyeongjun Ko, Incheol Hwang, Daesik Hong, Sooyong Choi,and Hanho Wang 
Journal : IEEE Transactions on Vehicular Technology 
Abstract : In the fifth-generation (5G) high-speed train (HST) system operating in the millimeter-wave (mmWave) band, a much higher Doppler shift occurs. Doppler shift severely degrades reception performance in orthogonal frequency division multiplexing (OFDM)-based wireless communication systems. The performance of the Doppler shift estimator is directly related to safety in the HST because the 5G HST system is used for train control. Therefore, it is necessary to develop a fast and accurate Doppler shift estimator (DSE) with low complexity. In this paper, we propose a new machine learning-based DSE (MLDSE). Taking note of the fact that an HST travels the same path repeatedly, the MLDSE estimates the Doppler shift by using the reference signal received power (RSRP) values measured by the mobile receiver at all times. However, since there is a oneto-many mapping problem when the RSRP values reflecting the 5G beam sweeping and selection correspond to Doppler shifts, machine learning cannot be performed. To solve this problem, we design an RSRP ambiguity reducer (AR) for the machine learning input so that the pattern of RSRP values can be mapped and learned into corresponding Doppler shifts. As a result, MLDSE can estimate Doppler shift more accurately than any HST DSEs known to the authors. In addition, an MLDSE consisting of only three layers is superior to the conventional techniques in terms of computational complexity as well as estimation accuracy. 
URL : https://ieeexplore.ieee.org/document/9292473 

.

List of Articles
No.
Statussort Date
» [IEEE Trans. Veh. Technol.] Taehyung Kim, Kyeongjun Ko, Incheol Hwang, Daesik Hong, Sooyong Choi and Hanho Wang, "RSRP-Based Doppler Shift Estimator Using Machine Learning in High-Speed Train Systems," in IEEE Transactions on Vehicular Technology, Jan. 2021 Published  2020-12