波谱学杂志 ›› 2007, Vol. 24 ›› Issue (1): 43-51.

• 研究论文 • 上一篇    下一篇

基于神经网络的NMR谱图自动相位校正综合算法

黄颖颖; 李鹏; 刘小征; 杨光*   

  1. (上海市功能磁共振成像重点实验室(华东师范大学), 华东师范大学 物理系,上海 200062)
  • 收稿日期:2006-05-23 修回日期:2006-06-14 出版日期:2007-03-05 发布日期:2009-12-05
  • 通讯作者: 杨光

A Synthetical Algorithm for Automatic Phase Correction of NMR Spectra Based on Neural Network (NNAPC)

HUANG Ying-ying; LI Peng; LIU Xiao-zheng; YANG Guang*    

  1. (Shanghai Key Laboratory of Functional Magnetic Resonance Imaging (East China Normal University), Department of Physics, East China Normal University, Shanghai, 200062, China)
  • Received:2006-05-23 Revised:2006-06-14 Online:2007-03-05 Published:2009-12-05
  • Contact: Yang Guang

摘要: 目前,已有多种算法被应用在核磁共振谱图自动相位校正中,由于各种算法本身特性和所基于谱图的具体特性的差异,不同算法对于特征不同的谱图的适用性也各不相同. 针对这一情况,文在综合研究多种现有自动相位校正算法的基础上,提出了一种基于神经网络的,可以根据谱图的特征来选取最合适的算法进行自动相位校正的综合算法. 实验表明,本算法可以获得比以往方法更好的计算结果.

关键词: 自动相位校正, 核磁共振, 神经网络, 综合算法, NNAPC

Abstract: A synthetical algorithm for automatic phase correction of NMR spectra based on neural network (NNAPC) is proposed. Taking into account the characteristics of the NMR spectrum or the resonance peak, the proposed algorithm uses an artificial neural network to choose the most appropriate algorithm to calculate the phase angles of a given peak. Statistical analysis demonstrated that the NNAPC algorithm is more accurate and stable than the existing phase correction algorithms referenced.

Key words: NMR, automatic phase correction, neural network, NNAPC

中图分类号: