摘要
将小波变换与神经网络相结合,对浮游植物活体的三维荧光光谱进行分类.首先利用小波变换对数据进行压缩,然后利用径向基函数(RadialBasisFunction,RBF)神经网络对光谱曲线进行逼近,从而进行物种的识别,平均识别率高达95.8%.结果表明,该方法较传统的统计方法更方便、准确率更高.
The 3D fluorescence spectra of phytoplankton is classified by wavelet transform with neural work combined. The original data is compressed by wavelet transformation method, and the curves of spectra are approximated by radial basis function （RBF） network. Thereby the species are recognized. And the average recognition rate is as high as 95.8%. Compared with the traditional statistic method, the experiments indicate that the method has good performance with high accuracy and convenience.
出处
《计算机辅助工程》
2006年第3期66-68,71,共4页
Computer Aided Engineering
关键词
小波变换
神经网络
径向基函数
高斯函数
wavelet transform
neural network
radial basis function（RBF）
Gauss function
