混合物质谱的简单分类算法

有毒化合物质谱分类是以光谱数据的数值特性为基础的。这此数据的计算机分类提供了各种参数，用以确定属于有毒化合物中某一类的对应化合物。质谱数据的简单分类算法常被用于自相关变换质谱的主分量建模。主分量的有效值为相互确认为确定。对环境空气中１１９种被监测的有毒化合物，有色谱－质谱联用的试验和校正数据所得到的４类预报正确率为７６．５％。

Simple Classification Algorithm (SIMCA) Studies on Mass Spectra of the Mixture

Classification of mass spectra of toxic compounds is based on the numerical features derived from spectral data. Computer calculations on these data provide various parameters, which are used to determine the corresponding compounds belonging to a certain class of toxic compounds. SIMCA studies on spectral data from mass spectra were used with SIMCA principal components modeling of the autocorrelation transformed mass spectra. The significant number of principal components was determined by cross validation. With this technique, correct retes for the four classes were obtained with GC/MS from training, and calibration data for the 119 toxic compounds targeted in ambient air is 76. 5%.