基于核系数样本选择算法的光谱模型更新  

Samples are Selected Based on Kernel Coefficients for Spectral Model Updates

作　　者：贺忠海 曹功伟 贾琼 张晓芳[3] HE Zhong-hai;CAO Gong-wei;JIA Qiong;ZHANG Xiao-fang(School of Control Engineering,Northeastern University at Qinhuangdao,Qinhuangdao 066004,China;Hebei Key Laboratory of Micro and Nano Sensing,Qinhuangdao 066004,China;School of Optoelectronics,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]东北大学秦皇岛分校控制工程学院,河北秦皇岛066004 [2]河北省微纳传感重点实验室,河北秦皇岛066004 [3]北京理工大学光电学院,北京100081

出　　处：《分析测试学报》2023年第12期1652-1658,共7页Journal of Instrumental Analysis

基　　金：河北省自然科学基金资助项目(F2020501040)。

摘　　要：近红外光谱建立的偏最小二乘(PLS)模型的预测能力通常因待测样品的组分或环境条件发生变化,不能很好地预测新样本。该情况下需把新标记样本加入标定集合进行模型更新。但由于旧标定集合中的样本数量大,少量新样本的加入在模型中难以体现。为快速更新模型,该文提出了一种利用核系数选择重要旧样本(Kernel Coefficient Selection,KCS)以减少样本数量的方法,即对旧样本建立核模型,计算各样本在模型中的系数,选择在系数大的样本中加入新样本更新模型。以模拟和豆粕数据集进行实验,对KCS选择部分旧样本加入新样本的模型和全部旧样本加入新样本的模型进行对比。结果显示,KCS选择部分旧样本用于模型更新后,其预测均方根误差分别从更新前的1.165、0.730下降至更新后的0.961、0.654,分别下降了17.5%和10.4%;全部旧样本用于模型更新后,其预测均方根误差分别从更新前的1.110、0.720下降0.980、0.662,分别下降了11.7%和8.1%。实验结果表明,这种挑选部分重要旧样本用于模型更新的方法解决了新旧样本数量失衡的问题,提高了模型的更新速度。The predictive ability of the partial least squares(PLS)model established by near-infrared spectroscopy is often limited when there are changes in the composition of the test sample or environ⁃mental conditions,making it difficult to predict new samples accurately.In this case,the labeled samples containing the new changes need to be added to the calibration set for model update.Howev⁃er,the large size of the old calibration set combined with the limited number of new samples can make it difficult for the new changes to be reflected in the model.To be able to update the model quickly,this paper proposes a method to reduce the number of samples by selecting important old samples using kernel coefficients(KCS).A kernel model is built for the old samples to obtain the co⁃efficients of each sample in the model,larger coefficients correspond to greater sample importance.Thus,samples with higher coefficients are chosen to reduce the sample size,and new samples are added to the part of old samples to update the model.The experiment compared the model updates of KCS by including a portion of old samples with the model updates by including all old samples with the new samples.The experiments were conducted on simulated and soybean meal datasets.Using a portion of old samples for model updates in KCS decreased the root mean square errors(RMSE)of the predictions from 1.165 and 0.730 before the update to 0.961 and 0.654 after the update,which rep⁃resents a decrease of 17.5%and 10.4%,respectively.Using all old samples for model updates in KCS decreased the RMSE of the predictions from 1.110 and 0.720 before the update to 0.980 and 0.662 after the update,which represents a decrease of 11.7%and 8.1%,respectively.The results show that this method of selecting some important old samples for model updating solves the imbal⁃ance of the number of new and old samples,thereby accelerating the update speed of models.

关 键 词：PLS 核系数 模型更新 选择重要样本 

分 类 号：O657.3[理学—分析化学] O141.4[理学—化学]