The 4th International ICST Workshop on Channel Measurement and Modeling

Research Article

Application of artificial neural networks for path loss prediction in railway environments

Download724 downloads
  • @INPROCEEDINGS{10.4108/iwoncmm.2010.10,
        author={Di Wu and Gang Zhu and Bo Ai},
        title={Application of artificial neural networks for path loss prediction in railway environments},
        proceedings={The 4th International ICST Workshop on Channel Measurement and Modeling},
        publisher={IEEE},
        proceedings_a={IWONCMM},
        year={2011},
        month={1},
        keywords={Artificial neural network (ANN) back propagation network (BPN) learning algorithm path loss railway},
        doi={10.4108/iwoncmm.2010.10}
    }
    
  • Di Wu
    Gang Zhu
    Bo Ai
    Year: 2011
    Application of artificial neural networks for path loss prediction in railway environments
    IWONCMM
    IEEE
    DOI: 10.4108/iwoncmm.2010.10
Di Wu1,*, Gang Zhu1, Bo Ai1
  • 1: State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University, Beijing, China
*Contact email: 09111054@bjtu.edu.cn

Abstract

To balance the precision and generality of the prediction model, a new path loss artificial neural network (ANN) prediction model for railway environments is presented firstly in this paper. The utilization of back propagation ANN can overcome some disadvantages of such conventional prediction models as empirical and deterministic models. The training data is based on the electric field strength measurements in the Zhengzhou-Xi'an express railway line in China. Through many attempts and comparisons, the suitable architecture and learning algorithm are chosen in the proposed model. After training, the proposed model can predict the path losses accurately in typical similar railway environments. Comparisons between a conventional model and the proposed model, with the measured and predicted data show that the proposed model is sufficiently applicable in railway scenarios.