波谱学杂志 ›› 1996, Vol. 13 ›› Issue (3): 283-290.

• 研究论文 • 上一篇    下一篇

己知信号的计算机快速识别

李鲠颖1, 潘涛2   

  1. 1. 华东师范大学分析测试中心, 上海 200062;
    2. 苏州铁道师范学院物理系, 苏州 215008
  • 收稿日期:1995-08-21 出版日期:1996-06-05 发布日期:2018-01-17
  • 基金资助:
    上海市科委"青年科技启明星重点培养计划"资助项目

FAST RECOGNITION OF KNOWN SIGNAL BY COMPUTER

Li Gengying1, Pan Tao2   

  1. 1. Analytical Center, East China Normal University, Shanghain 200062;
    2. Department of Physics, Suzhou Railway Teacher's College, Suzhou 215008
  • Received:1995-08-21 Online:1996-06-05 Published:2018-01-17

摘要: 从计算机模拟和14N远程NQR实验上研究了神经网络在对已知信号的自动识别问题.证实了多层网络的反向传播算法对解决这一问题的有效性.实验结果表明,在信噪比很低和存在很强的干扰条件下,B-P算法仍然保持了很高的识别率(≥ 90%),这在远程NQR实际应用中是非常有意义的.

关键词: 信号识别, 神经网络, 远程核四极共振

Abstract: Problems associated to signal automatic recognition by Neural Networks is studied with computer simulations and 14N remote NQR experiments.The effectiveness of the multiple layer back propagation algorithm for solving the problems is venfied.The experimental result indicates that,under the condition of very low signal-to-noise ratio and very strong interferences,the B-P algorithm still keeps a very high recognition (>90%).This is of significant improtance in remote NQR applications.

Key words: Signal Recognition, Neural networks, Remote NQR