CAJ | 학술논문

以蚕茧茧层量为研究对象,研究了基于可见-近红外光谱技术的蚕茧茧层量无损检测方法.采用最小二乘支持向量机(least square-support vector machine,LS-SVM)建立可见-近红外光谱模型.采用无信息变量消除算法(uninformative variable elimination,UVE)与连续投影算法(successive projections algorithm,SPA)相结合选取光谱有效波长.结果表明,基于UVE-SPA法进行变量选择,最终将原始光谱的600个光谱变量减少到了8个(673,937,963,982,989,992,995和1 008 nm).基于此8个变量建立的LS-SVM模型得到了预测集的确定系数(R_p~2)为0.5354,误差均方根(RMSEP)为0.0373的预测结果.表明可见-近红外光谱可以用于对蚕茧的茧层量进行无损检测,同时UVE-SPA是一种有效的光谱变量选择方法.
이잠충충층량위연구대상,연구료기우가견-근홍외광보기술적잠충충층량무손검측방법.채용최소이승지지향량궤(least square-support vector machine,LS-SVM)건립가견-근홍외광보모형.채용무신식변량소제산법(uninformative variable elimination,UVE)여련속투영산법(successive projections algorithm,SPA)상결합선취광보유효파장.결과표명,기우UVE-SPA법진행변량선택,최종장원시광보적600개광보변량감소도료8개(673,937,963,982,989,992,995화1 008 nm).기우차8개변량건립적LS-SVM모형득도료예측집적학정계수(R_p~2)위0.5354,오차균방근(RMSEP)위0.0373적예측결과.표명가견-근홍외광보가이용우대잠충적충층량진행무손검측,동시UVE-SPA시일충유효적광보변량선택방법.
Visible and near-infrared reflectance spectroscopy (Vis-NIRS) was applied to measure cocoon shell weight. Least square-support vector machine (LS-SVM) was used to establish the Vis-NIR model. Uninformative variable elimination and successive projections algorithm were combined to select wavelength from Vis-NIR spectroscopy. Eight wavelength variables, namely 673, 937, 963, 982, 989, 992, 995 and 1 008 nm, were selected. The UVE-SPA-LS-SVM model was established based on these eight wavelength variables. The results showed that the determination coefficient for prediction set (R_p~2) was 0.5354, and the root mean square error for prediction (RMSEP) was 0.0373. It is concluded that Vis-NIRS can be used in the cocoon shell weight measurement, and UVE-SPA is a feasible and efficient algorithm for the spectral variable selection.