Channel Estimation Based on Extreme Learning Machine for High Speed Environments

Due to the complexity and extensive application of wireless systems, channel estimation has been a hot research issue, especially for high speed environments. High mobility challenges the speed of channel estimation and model optimization. Unlike conventional estimation implementations, this paper proposes a new channel estimation method based on extreme learning machine (ELM) algorithm. Simulation results of path loss estimation and channel type estimation show that the ability of ELM to provide extremely fast learning make it very suitable for estimating wireless channel for high speed environments. The results also show that channel estimation based on ELM can produce good generalization performance. Thus, ELM is an effective tool in channel estimation.

[1]  Theodore S. Rappaport,et al.  Wireless communications - principles and practice , 1996 .

[2]  Andreas F. Molisch,et al.  Geometry-based directional model for mobile radio channels - principles and implementation , 2003, Eur. Trans. Telecommun..

[3]  Larry J. Greenstein,et al.  An empirically based path loss model for wireless channels in suburban environments , 1999, IEEE J. Sel. Areas Commun..

[4]  A. Lee Swindlehurst,et al.  Performance Bounds for MIMO-OFDM Channel Estimation , 2009, IEEE Transactions on Signal Processing.

[5]  Jiuwen Cao,et al.  Protein Sequence Classification with Improved Extreme Learning Machine Algorithms , 2014, BioMed research international.

[6]  Zhiping Lin,et al.  Bayesian signal detection with compressed measurements , 2014, Inf. Sci..

[7]  Tao Tang,et al.  Design and performance tests in an integrated TD-LTE based train ground communication system , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[8]  Bo Ai,et al.  Handover schemes and algorithms of high-speed mobile environment: A survey , 2014, Comput. Commun..

[9]  Gaurav S. Sukhatme,et al.  Mitigating multi-path fading in a mobile mesh network , 2013, Ad Hoc Networks.

[10]  Hsing-Chung Chen,et al.  Neural Network-Based Estimation for OFDM Channels , 2015, 2015 IEEE 29th International Conference on Advanced Information Networking and Applications.

[11]  Limin Xiao,et al.  Fading Characteristics of Wireless Channel on High-Speed Railway in Hilly Terrain Scenario , 2013 .

[12]  Eric Pierre Simon,et al.  On the use of tracking loops for low-complexity multi-path channel estimation in OFDM systems , 2015, Signal Process..

[13]  Rupaban Subadar,et al.  Capacity analysis of M-SC receivers over TWDP fading channels , 2014 .

[14]  Katherine Siakavara,et al.  Mobile radio propagation path loss prediction using Artificial Neural Networks with optimal input information for urban environments , 2015 .

[15]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[16]  Kira Kastell.  Challenges and improvements in communication with vehicles and devices moving with high-speed , 2011, 2011 13th International Conference on Transparent Optical Networks.

[17]  Alfonso Fernández-Durán,et al.  Long term evolution in high speed railway environments: Feasibility and challenges , 2013, Bell Labs Technical Journal.

[18]  Zhiping Lin,et al.  Extreme Learning Machines on High Dimensional and Large Data Applications: A Survey , 2015 .

[19]  Fakhri Karray,et al.  Localization in vehicular ad hoc networks using data fusion and V2V communication , 2015, Comput. Commun..