摘要
本文利用红外光谱结合主成分(PCA)和偏最小二乘法判别分析(PLS-DA)研究了朝天椒(簇生椒)和涮涮辣。测试了2种辣椒60个样品的红外光谱,对光谱范围1800~950cm^-1做二阶导数处理,发现在该区间存在着明显的差异,利用该区间二阶导数光谱数据进行主成分分析和偏最小二乘法,结果表明PCA和PLSDA都能很好的区别两种辣椒,其中主成分的正确率为100%,偏最小二乘法在隐含潜含变量为12个时其正确率最好,朝天椒的正确率为86.7%,涮涮辣的正确率为93.3%。结果表明小波变换结合PCA和PLS-DA用于傅里叶变换红外光谱技术中能够准确地识别朝天椒和涮涮辣,为区分不同品种的辣椒提供快速和有效的方法。
Fourier transform infrared(FTIR)spectroscopy combined with principal component analysis(PCA)and partial least squares discriminant analysis(PLS-DA)were used to study Capsicum frutescens var and shuanshuan pepper.FTIR spectra of 60 samples of 2species of Capsicum frutescens L were obtained,the results showed that the infrared spectra of Capsicum frutescens L were similar,but tiny differences in wave-numbers and absorption intensities of peaks were observed in the range of 1800~950cm^-1.PCA and PLS-DA were performed on the second derivative infrared spectra in this range.Results show that the PCA and PLS-DA can distinguish two kinds of chili peppers.PCA provides about 100% of classification accuracy,and PLS-DA yield 86.7% classification accuracy for Capsicum frutescens var and 93.3%for shuanshuan pepper.It is proved that FTIR spectroscopy combined with PCA and PLS-DA could be used to discriminate Capsicum frutescens var and shuanshuan pepper.
出处
《光散射学报》
北大核心
2015年第1期69-73,共5页
The Journal of Light Scattering
基金
国家自然科学基金项目(30960179)
云南省高校科技创新团队支持计划资助