跳到主要导航 跳到搜索 跳到主要内容

Neural Network and Collaborative Computing for Image-based Train Location Data Acquisition

  • Xiaoqing Wu
  • , Haifeng Song*
  • , Peng Wang
  • , Jianfeng Cheng
  • , Datian Zhou
  • , Hairong Dong
  • *此作品的通讯作者
  • Beijing Jiaotong University
  • China Academy of Railway Sciences

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

How to improve the performance and safety of the train has long been a question of great interest. The object of this study is to achieve the recognition of train speed and mileage that are provided by the train Driver Machine Interface (DMI) and reduce the time consumed by model training. For recognition part, a Convolutional Neural Network (CNN) and a Connectionist Temporal Classification (CTC) layer have been combined together to achieve an end-to-end recognition. For the part of time-consuming reduction, a collaborative computing was being utilized to offload the training tasks to each edge device. In addition, the process of offloading was modeled with Stochastic Petri Net (SPN). Overall, the recognition accuracy was significantly improved, compared to the traditional Optical Character Recognition (OCR) and CNNs, what is more, the time consumed on model training was also brought down as expect.

源语言英语
主期刊名Proceedings of 2021 5th Chinese Conference on Swarm Intelligence and Cooperative Control
编辑Zhang Ren, Yongzhao Hua, Mengyi Wang
出版商Springer Science and Business Media Deutschland GmbH
1797-1807
页数11
ISBN(印刷版)9789811939976
DOI
出版状态已出版 - 2023
活动5th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2021 - Shenzhen, 中国
期限: 19 1月 202222 1月 2022

出版系列

姓名Lecture Notes in Electrical Engineering
934 LNEE
ISSN(印刷版)1876-1100
ISSN(电子版)1876-1119

会议

会议5th Chinese Conference on Swarm Intelligence and Cooperative Control, CCSICC 2021
国家/地区中国
Shenzhen
时期19/01/2222/01/22

学术指纹

探究 'Neural Network and Collaborative Computing for Image-based Train Location Data Acquisition' 的科研主题。它们共同构成独一无二的学术指纹。

引用此