CAJ | 학술논문

应用紫外可见（ultraviolet/visible ，UV/Vis）光谱技术对表征水产养殖水体中有机物浓度的指标化学需氧量（chemical oxygen demand ，COD）进行快速测量，对采集到的135份甲鱼养殖水样进行 UV/Vis波段全光谱扫描，采用无信息变量消除（uninformative variable elimination ，UVE）和连续投影算法（successive projections algorithm ，SPA）相结合的变量选择算法选取全波段光谱中的特征波长，从201个 UV/Vis光谱变量中选取了7个特征波长，只占全波段光谱变量的3.48％，降低了建模的时间和模型的复杂度。结合最小二乘支持向量机（least-square support vector machine ，LS-SVM ）算法进行COD预测建模，结果表明：使用特征波长建模的预测效果（相关系数 r（correlation coefficient）＝0.89，预测均方根误差（root mean square error of prediction ，RMSEP）＝15.46 mg · L -1）好于使用全波段光谱建模的预测效果（r＝0.88，RMSEP ＝15.71 mg · L -1）。使用UVE-SPA变量选择算法获取UV/Vis光谱特征波长，结合LS-SVM建模，可以快速、准确的测量水产养殖水体中的COD浓度，为进一步实现水产养殖水质的在线检测以及其他水质参数的快速测定奠定了基础。
응용자외가견（ultraviolet/visible ，UV/Vis）광보기술대표정수산양식수체중유궤물농도적지표화학수양량（chemical oxygen demand ，COD）진행쾌속측량，대채집도적135빈갑어양식수양진행 UV/Vis파단전광보소묘，채용무신식변량소제（uninformative variable elimination ，UVE）화련속투영산법（successive projections algorithm ，SPA）상결합적변량선택산법선취전파단광보중적특정파장，종201개 UV/Vis광보변량중선취료7개특정파장，지점전파단광보변량적3.48％，강저료건모적시간화모형적복잡도。결합최소이승지지향량궤（least-square support vector machine ，LS-SVM ）산법진행COD예측건모，결과표명：사용특정파장건모적예측효과（상관계수 r（correlation coefficient）＝0.89，예측균방근오차（root mean square error of prediction ，RMSEP）＝15.46 mg · L -1）호우사용전파단광보건모적예측효과（r＝0.88，RMSEP ＝15.71 mg · L -1）。사용UVE-SPA변량선택산법획취UV/Vis광보특정파장，결합LS-SVM건모，가이쾌속、준학적측량수산양식수체중적COD농도，위진일보실현수산양식수질적재선검측이급기타수질삼수적쾌속측정전정료기출。
Ultraviolet/visible (UV/Vis) spectroscopy was investigated for the rapid determination of chemical oxygen demand (COD) which was an indicator to measure the concentration of organic matter in aquaculture water .A total number of 135 col-lected turtle breeding water samples were scanned for UV/Vis spectrum ,uninformative variable elimination (UVE) and succes-sive projections algorithm (SPA) were combined as a mixed variable selection method to perform characteristic wavelength selec-tion from the full wavelength spectrum ,7 characteristic wavelengths were selected from full 201 UV/Vis spectral variables , which were just 3 .48% number of the full range spectrum ,and the calibration time and complexity of the modeling were greatly reduced .The predicted results which were obtained by using least squares-support vector machine (LS-SVM) calibration showed that the characteristic wavelengths achieved better results (0.89 for correlation coefficient (r) ,15.46 mg · L -1 for root mean square error of prediction (RMSEP)) than full wavelengths did (0.88 for r and 15.71 mg · L -1 for RMSEP) .The comprehen-sive results revealed that the UV/Vis characteristic wavelengths which were obtained by UVE-SPA variable selection method , combined with LS-SVM calibration could apply to the rapid and accurate determination of COD in aquaculture water .Moreover , this study laid the foundation for further implementation of online analysis of aquaculture water and rapid determination of other w ater quality parameters .