| 基于可扩展的自表示学习波段选择算法在近红外光谱回归建模中的影响研究 |
| 点此下载全文 |
|
| 基金项目:国家自然科学基金重点项目（62031021）；陕西省教育厅-科学研究计划项目（20JK0533） |
|
| 中文摘要:该文提出了一种基于可扩展的自表示学习（SOP－SRL）波段选择与偏最小二乘（PLS）建模的定量模型分析方法，以安胎丸指标含量阿魏酸、黄芩苷和汉黄芩苷为研究对象，通过SOP－SRL选取代表性波段，采用PLS建立近红外光谱回归模型，并与相关系数法（CC）、正则化自表示学习算法（RSR）和稀疏子空间聚类法（SSC）3种波段选择算法的建模结果进行对比，以校正决定系数（R2c）、校正均方根误差（RMSECV）、预测决定系数（R2p）和预测均方根误差（RMSEP）为评价标准，对回归模型的预测性能进行评估。结果显示，SOP－SRL在3种数据集上均取得了较好的结果，建模波段从全波长的800分别减少到70、67、87；RMSEP分别从0.080 1、6.349 5、0.742 5下降到0.065 3、3.620 8、0.407 3，分别下降了18%、43%、45%；相应的R2p分别从0.911 9、0.879 4、0.915 8提高到0.938 8、0.952 6、0.970 1，分别提高了3%、8%、6%。结果表明，经SOP－SRL波长选择后模型的预测能力相比于其他几种算法得到显著提升，基于SOP－SRL的PLS模型可以实现安胎丸指标含量的快速检测。 |
| 中文关键词:近红外光谱 波段选择 可扩展的自表示学习方法（SOP－SRL） 偏最小二乘法（PLS） 指标含量测定 |
| |
| Effects of Scalable One-pass Self-representation Learning on Near Infrared Spectroscopy Regression Modeling |
|
|
| Abstract:Near-infrared spectroscopy is widely applied in the quality monitoring process of traditional Chinese medicine since it features with rapid detection，and making no damage to the samples and no pollution to the environment in the meantime. In order to realize the rapid prediction of the target ingredients of Antai Pills，a new near-infrared spectroscopy modeling method was proposed，which combines scalable one-pass self-representation learning（SOP－SRL） with partial least-squares（PLS）. Taking ferulicacid，baicalin and wogonoside in Antai pills as the research objects，the representative bands selected by SOP－SRL were compared with three band selection algorithms，such as correlation coefficient method（CC），regularized self-representation algorithm（RSR） and sparse subspace clustering （SSC）. Then，the quantitative model was established by PLS. The evaluation criteria of the model are root mean squares error of cross validation（RMSECV），corrected determination coefficient（R2c），predicted root mean square error（RMSEP） and predicted determination coefficient（R2p）. Results indicated that the SOP－SRL had good results on all three datasets. Compared with all bands，the selected bands of SOP－SRL were reduced from 800（FULL） to 70，67 and 87， respectively. The RMSEP decreased from 0.080 1，6.349 5，0.742 5 to 0.065 3，3.620 8，0.407 3，decreased by 18%，43% and 45%，respectively. The R2p increased from 0.911 9，0.879 4，0.915 8 to 0.938 8，0.952 6，0.970 1，respectively，increased by 3%，8% and 6%. Therefore，the results of the SOP－SRL algorithm were significantly better than other comparison algorithms. The SOP－SRL algorithm could improve the accuracy of quantative model. The model combining SOP－SRL with PLS could rapidly detect the target ingredients of Antai pills. |
| Key Words:near infrared spectroscopy wavelength selection scalable one-pass self-representation learning（SOP－SRL） partial least-squares（PLS） target ingredients determination |
| 引用本文：郭拓，梁小娟，马晋芳，袁凯，葛发欢，肖环贤.基于可扩展的自表示学习波段选择算法在近红外光谱回归建模中的影响研究[J].分析测试学报,2022,41(8):1214-1220. |
| 摘要点击次数: 1036 |
| 全文下载次数: 1088 |
| 查看全文 下载PDF阅读器 |
|
|
