提出了一种运用量子粒子群(quantum-behaved particle swarm optimization,QPSO)算法优化多输出最小二乘支持向量机(multi-output least squares support vector machine,MLSSVM)的新混合优化算法。该算法结合激光拉曼光谱技术可实现对...提出了一种运用量子粒子群(quantum-behaved particle swarm optimization,QPSO)算法优化多输出最小二乘支持向量机(multi-output least squares support vector machine,MLSSVM)的新混合优化算法。该算法结合激光拉曼光谱技术可实现对四组分食用调和油中花生油、芝麻油、葵花油和大豆油的快速定量鉴别。采用基线校正去除背景荧光,结合Savitzky-Golay Filters光谱平滑法对原始拉曼光谱进行预处理。构建基于QPSO-MLSSVM混合优化算法的定量分析模型,并采用20个组分组成的预测集对其进行模型校验。实验结果表明,基于QPSO-MLSSVM混合优化算法的定量分析模型对于四组分调和油的预测效果良好,均方差(mean square error,MSE)为0.0241,低于0.05,各油分预测相关系数均高于98%。研究结果充分表明,应用激光拉曼光谱技术结合QPSO-MLSSVM算法,对四组分调和油中各油分进行快速定量检测可行,具备较强的自适应能力和良好的预测精度,可以满足多组分调和油的成分鉴别。展开更多
Terahertz time-domain spectroscopy(THz-TDS)was used for the quantitative detection of sulfur content in gasoline.Models of chemo metrics methods and partial least squares(PLS)were built to measure THz-TDS and the sulf...Terahertz time-domain spectroscopy(THz-TDS)was used for the quantitative detection of sulfur content in gasoline.Models of chemo metrics methods and partial least squares(PLS)were built to measure THz-TDS and the sulfur content.All of the samples were divided into two parts.One part was used for calibration and the other one for validation.In order to evaluate the quality of the models,the correlation coefficient(R)and root-mean-square errors(RMSE)of calibration and validation models were calculated.The value of R and RMSE were close to 1 and 0 within acceptable levels,respectively,indicating that the combination of THz-TDS and PLS is a potential method for further quantitative detection.展开更多
基金supported by the National Key Basic Research Program of China(Grant No.2014CB744302)the Specially Funded Program on National Key Scientific Instruments and Equipment Development(Grant No.2012YQ140005)+1 种基金the Beijing National Science Foundation(Grant No4122064)the Science Foundation of the China University of Petroleum(Beijing)(Grant Nos.QZDX-2010-01 and KYJJ2012-06-27)
文摘Terahertz time-domain spectroscopy(THz-TDS)was used for the quantitative detection of sulfur content in gasoline.Models of chemo metrics methods and partial least squares(PLS)were built to measure THz-TDS and the sulfur content.All of the samples were divided into two parts.One part was used for calibration and the other one for validation.In order to evaluate the quality of the models,the correlation coefficient(R)and root-mean-square errors(RMSE)of calibration and validation models were calculated.The value of R and RMSE were close to 1 and 0 within acceptable levels,respectively,indicating that the combination of THz-TDS and PLS is a potential method for further quantitative detection.
