摘要
对于超短脉冲激光与气体相互作用产生的复杂光谱,提出了基于递归最小方差方法的自适应小波算法,实现了对该类光谱数据的高效压缩.在对三种气体,共计27组光谱数据进行压缩后,数据由最初的3968个点被压缩成124个点,压缩比为32∶1.选择其中13组作为样本送入支持向量机神经网络进行训练,用剩下的14组进行检验,正确率为100%.
An adaptive wavelet analysis approach based on recursive least square (RLS) algorithm is proposed for analyzing the complicated spectra emitted by the interaction between femto-second laser and gases. The simulation results on twenty-seven sets of spectral data show that the proposed method has high efficiency in data compression. The data of the original spectra with 3968 points can be compressed to 124 points, and the correct recognition rate of support vector machine (SVM) can be as high as 100%, when thirteen or more compressed spectra are used for training and the others for testing.
出处
《物理学报》
SCIE
EI
CAS
CSCD
北大核心
2007年第6期3613-3618,共6页
Acta Physica Sinica
基金
教育部博士点基金(批准号:20030055022)
国家自然科学基金(批准号:60577017
60477009)
天津市自然科学基金重点项目(批准号:07JCZDJC05500)资助的课题~~
关键词
非线性荧光光谱
小波分析
递归最小方差算法
线性神经网络
nonlinear fluorescence spectra, wavelet analysis, recursive least square algorithm, linear neural network