基于脉冲耦合神经网络的拉曼光谱定性分析

通过对脉冲耦合神经网络(pulse coupled neural network,PCNN)和拉曼光谱定性分析的研究,提出了基于PCNN的拉曼光谱定性分析方法.首先,利用PCNN神经元的疲劳与不应期特性将拉曼光谱数据进行编码;然后,基于改进的Horspool算法将检测样品对应编码与基码数据库中的所有基码逐一匹配,并得到各对应的匹配相似度,进而判定样品类别.相关实验和数据分析证明了该文方法的准确性和有效性.同时,该文方法避免了目前基于谱模版定性分析方法中待测样品拉曼光谱特征谱峰难以确定以及匹配分析冗余度高等不足,且对存储空间的要求仅为后者的5.8%.

Qualitative analysis of Raman spectra based on pulse coupled neural network

By studying on pulse coupled neural network (PCNN) and Raman spectra qualitative analysis, a method based on PCNN for Raman spectra qualitative analysis was proposed. After encoding the Raman spectra by using PCNN neurons' characteristics of fatigue and refractory period, the improved Horspool algorithm was used to match the code corresponding to the detected sample with all of the base code in the database one by one, and then their matching similarity was acquired to determine the sample type. Experimental results and analysis of data proved that the method proposed in this paper is accurate and effective for Raman spectra qualitative analysis. Meanwhile, traditional qualitative analysis method based on spectral template has some deficiencies, like that it is difficult to determine the characteristic peak of the detected sample and the matching analysis process has a high degree of redundancy. While our proposed method not only can avoid these deficiencies very well, but also needs a small amount of data storage. The requirement of the storage space was only 5.8% of that used in the traditional qualitative analysis method based on spectral template.