高光谱喷墨打印墨水数据的非线性降维及分类建模方法研究

在法庭科学实践中,往往需要通过对文件中字迹墨水的成分分析来精确判定检材和样本文件的同一性。该文利用高光谱成像技术结合机器学习对喷墨打印墨水的种类进行区分,分别采集14套不同品牌、型号的4色（黑、青、品红和黄色）喷墨打印墨水打印的文件在400～1 000 nm范围的高光谱图像,共提取56种样品墨迹的光谱数据。使用均匀流形逼近与投影技术（UMAP）和T分布随机近邻嵌入技术（t-SNE）两种算法对高光谱喷墨打印墨水数据进行降维处理,然后建立极致梯度提升（XGBoost）、轻量级梯度提升机器学习（LightGBM）和支持向量机（SVM）3种分类模型,以1∶4的比例确定测试集和训练集,分别对原始数据和降维后的数据进行分类。实验结果显示,UMAP降维算法结合SVM模型对喷墨打印墨水分类的效果最优,黑色墨水样品的分类精度为90%左右,其余颜色墨水样品的分类精度均为100%。该研究为喷墨打印文件的检验鉴定提供了一种新的、无损、准确的鉴别方法。     

基于高光谱的黑色签字笔墨水种类鉴别方法研究

该文提出了高光谱成像技术结合机器学习快速无损鉴别黑色签字笔墨水种类的新方法。采集36支不同品牌型号的黑色签字笔笔迹的高光谱图像,对每支签字笔笔迹的高光谱图像选取18个感兴趣区域,共提取648个平均光谱作为样本集。对450～950 nm的原始光谱进行Savitzky－Golay平滑、Z－Score标准化和两种组合方法光谱预处理,使用线性判别分析（LDA）和随机子空间－线性判别分析（RSM－LDA）分别构建黑色签字笔墨水种类鉴别模型。实验结果表明：不同预处理方法对RSM－LDA模型的鉴别准确率影响较小,而对于LDA模型,组合预处理具有更优的鉴别准确率;相比LDA模型,RSM－LDA模型分类效果更佳,训练集的平均分类准确率达100%,交叉验证平均分类准确率达99.09%,测试集的平均分类准确率达90.70%,每类样本的准确率、精准率、召回率均高于LDA模型分类结果,模型的接受者操作特征曲线下方面积（AUC值）达0.998 3,模型性能良好。因此,采用高光谱成像技术结合RSM－LDA可实现不同品牌型号黑色签字笔墨水的快速无损鉴别。     

气相色谱-质谱法分析3种常见品牌喷墨打印机84种墨水制备的墨迹样本中挥发性溶剂成分

建立了气相色谱-质谱法(GC-MS)分析市售3种常见品牌喷墨打印机所使用的84种墨水制备的墨迹样品中的挥发性溶剂成分,并对不同墨迹中的溶剂成分的组成进行了归类总结.用不同型号的A、B品牌打印机的原装墨水打印A4纸,将C品牌打印机不同型号的墨水滴在A4纸上制备墨迹样本,第二天用打孔器取样,用含5mg·L-1苯甲酸乙酯的甲...     

基于高光谱成像的光敏印油种类区分实验

印油种类区分是法庭科学文件检验领域的重要一环,为研究无损高效区分光敏印油种类的方法。以33种不同品牌光敏印油的原始光谱数据当作对照组,对原始数据进行t-SNE降维和UMAP降维后,选择XGBoost、SVM和MLP三种分类算法,以1比4的比例确定测试集和训练集,对原始数据和降维后的数据进行分类,同时使用网格搜索和五倍交叉验证来优化模型的性能和泛化能力。结果表明,上述三种分类算法对降维后光谱数据区分的平均准确率高于对原始光谱数据区分的平均准确率,且UMAP-MLP分类模型的区分准确率最高,可达到98%。提出的分类模型可用于光敏印油种类的快速区分。     

喷墨打印墨水和墨迹可挥发性成分的GC-MS检验

为研究喷墨打印文件的比对区分和溯源技术,建立了一种墨水可挥发性成分的GC-MS分析方法,分别对90种常见市售喷墨打印墨水、纸张墨迹和假币墨迹中的可挥发性成分进行了分析。研究发现,喷墨打印墨水中含有甘油、二甘醇、三甘醇、吡咯烷酮等极性溶剂;同一型号不同颜色的墨水使用相近的配方;不同厂家墨水的配方存在差异;墨水中的可挥发性成分可在纸张中存在较长时间。据此对4起实际案例中缴获的喷墨打印制作的假币进行了检验,检出若干种溶剂成分,通过溶剂特征对假币进行了比对,相关两起假币案件得到串并。本方法筛选出的部分特征溶剂可用于喷墨打印文件的比对区分,并为相关案件的溯源串并提供技术情报。     

差分拉曼光谱结合SVM对便签纸的鉴别分析

基于差分拉曼光谱技术与支持向量机(SVM)模型,提出了一种对便签纸类检材的快速可视化鉴别方法。实验获取了40组不同品牌便签纸样本的差分拉曼光谱数据,利用BP神经网络和差分技术完成谱图的除噪与基线校正后,借助F检验与主成分分析提取谱段信息,构建出SVM分类模型。实验结果表明,当设置Linear为SVM模型的核函数时,可以实现对样本测试集的完全准确划分,K折交叉验证的结果理想。相比于传统聚类分析手段,本方法可以在原始高维光谱数据中筛选出有效特征矩阵,且SVM模型兼具高效性和准确性,为公安实践中纸张类物证的区分鉴别提供一种新思路。     

功能喷墨墨水的图案化与应用

近年来,利用喷墨打印技术实现材料图案化的研究取得了重要进展,功能喷墨墨水的开发成为新型材料与器件领域的研究热点之一。本文综述了功能墨水在图案化方面的研究进展,分别围绕聚合物、无机和金属墨水在图案化方面的重要进展与应用进行了介绍,进一步展望了喷墨功能墨水在先进材料图案化、功能器件制备及3D打印技术领域的应用前景。     

近红外光谱技术对烟草pH值的快速测定

提出了一种基于近红外漫反射光谱技术快速测定烟草pH值的方法.采集不同烟草粉末样品的近红外漫反射光谱,并对其原始光谱数据进行一阶微分、二阶微分及平滑等预处理,用偏最小二乘法(PLS)方法建立pH值预测模型(建模样品572个).从光谱主成分分布和pH值分布方面考察了81个验证集样品,结果表明验证集样品分布范围较大,分布较合理.利用主仪器模型对验证集样品进行预测,结果表明主仪器一阶微分模型和二阶微分模型对验证集样品的pH值预测与实际测量值的平均绝对偏差分别为0.057、0.065,t检验表明预测值和实测值之间没有显著性差异,达到了较好的结果.考察了主仪器pH值一阶微分、二阶微分模型在同一型号不同仪器间的直接转移效果,一阶微分模型转移给了子仪器A ～F,二阶微分模型转移给了子仪器G,7台子仪器pH值预测的平均绝对偏差为0.049 ～0.070,且都通过了F检验.实验表明,该主仪器模型能够快速预测烟叶中的pH值,并成功转移到同类仪器上进行检测.     

支持向量机回归法在近红外光谱测定植物纤维原料中甲氧基含量中的应用

以26个植物纤维原料为实验材料,由20个样品作校正样品,采用径向基核函数方法对纤维原料中甲氧基含量与纤维原料样品近红外光谱进行支持向量机(SVM)回归建模.以所建SVM回归模型对6个纤维原料样品中甲氧基含量进行预测,回归模型的预测结果与采用改良的维伯克法确定的甲氧基含量的相关系数为0.977,预测样本集的标准偏差为0.43.将SVM回归模型的预测效果与PLS回归模型的预测结果进行比较,所建近红外光谱测定植物纤维原料中甲氧基含量的SVM回归模型可用于实际植物纤维原料样品的定量分析,且具有较好的分析效果.     

近红外光谱结合LSTSVM算法判别不同等级烟叶

本文用近红外光谱结合最小二乘双胞胎支持向量机(LSTSVM)算法建立了烟叶等级分类模型。从三个等级共210个烟叶样品中,取出120个样品作为建模集,剩余90个样品作为预测集。为了建立最优模型,对光谱预处理方法和模型参数进行筛选优化,最优模型对预测集样品的平均识别率为95.56%,结果表明该方法可以作为烟叶等级分类的一种有效方法。此外,将该算法与SIMCA、PLS-DA、SVM等三种常见的模式识别算法进行了比较,结果表明基于样品的原始光谱,同等条件下,LSTSVM算法的预测效果优于其他三种算法。     

纳米粒子的制备及其在打印印刷领域的应用

本文简要介绍了几类纳米粒子的制备及其在打印印刷领域的应用.包括无机纳米粒子复合材料用于绿色打印制版、聚合物乳胶纳米粒子用于喷墨打印制备光子晶体、金属纳米粒子用于印刷电路以及纳米材料用于3D打印,并展望了其发展前景.     

基于高光谱技术的培养基上细菌菌落分类方法研究

利用高光谱技术对培养基上细菌(大肠杆菌、李斯特菌和金黄色葡萄球菌)菌落进行快速识别和分类。采集琼脂培养基上细菌菌落的高光谱反射图像(390~1040 nm),在对波段差图像进行大津阈值分割的基础上自动提取细菌菌落光谱,并建立细菌分类检测的全波长和简化偏最小二乘判别( PLS-DA)模型。全波长模型对预测集样本的分类准确率和置信预测分类准确率分别为100%和95.9%。此外,利用竞争性自适应重加权算法( CARS)、遗传算法( GA)和最小角回归算法( LARS-Lasso)进行波长优选并建立对应简化模型。其中,CARS简化模型在精度、稳定性及分类准确率方面均优于GA和LARS-Lasso简化模型,其对预测集样本的分类准确率和置信预测分类准确率分别达到了100%和98.0%。研究表明,高光谱是一种细菌菌落高精度、快速、无损识别检测的有效方法。简化模型中优选的波长可以为开发低成本检测仪器提供理论依据。     

Characterisation and Classification of Foodborne Bacteria Using Reflectance FTIR Microscopic Imaging

This work investigates the application of reflectance Fourier transform infrared (FTIR) microscopic imaging for rapid, and non-invasive detection and classification between Bacillus subtilis and Escherichia coli cell suspensions dried onto metallic substrates (stainless steel (STS) and aluminium (Al) slides) in the optical density (OD) concentration range of 0.001 to 10. Results showed that reflectance FTIR of samples with OD lower than 0.1 did not present an acceptable spectral signal to enable classification. Two modelling strategies were devised to evaluate model performance, transferability and consistency among concentration levels. Modelling strategy 1 involves training the model with half of the sample set, consisting of all concentrations, and applying it to the remaining half. Using this approach, for the STS substrate, the best model was achieved using support vector machine (SVM) classification, providing an accuracy of 96% and Matthews correlation coefficient (MCC) of 0.93 for the independent test set. For the Al substrate, the best SVM model produced an accuracy and MCC of 91% and 0.82, respectively. Furthermore, the aforementioned best model built from one substrate was transferred to predict the bacterial samples deposited on the other substrate. Results revealed an acceptable predictive ability when transferring the STS model to samples on Al (accuracy = 82%). However, the Al model could not be adapted to bacterial samples deposited on STS (accuracy = 57%). For modelling strategy 2, models were developed using one concentration level and tested on the other concentrations for each substrate. Results proved that models built from samples with moderate (1 OD) concentration can be adapted to other concentrations with good model generalization. Prediction maps revealed the heterogeneous distribution of biomolecules due to the coffee ring effect. This work demonstrated the feasibility of applying FTIR to characterise spectroscopic fingerprints of dry bacterial cells on substrates of relevance for food processing.     

基于支持向量机的药物诱导磷脂质病预测模型

本文应用一种组合遗传算法和共轭梯度法的支持向量机(GA-CG-SVM)方法建立了药物诱导磷脂质病分类预测模型.首先对描述符进行了优化,选出了19个描述符用于模型的构建,所建模型对训练集的预测准确率为81.6%,对测试集的预测精度为87.5%,说明所建SVM分类模型不仅能正确预测训练集药物诱导的磷脂质病,也对其他化合物具...     

Micro-spectrochemical analysis of document paper and gel inks by laser ablation inductively coupled plasma mass spectrometry and laser induced breakdown spectroscopy

Current methods used in document examinations are not suitable to associate or discriminate between sources of paper and gel inks with a high degree of certainty. Nearly non-destructive, laser-based methods using laser induced breakdown spectroscopy (LIBS) and laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS) were used to improve the forensic comparisons of gel inks, ballpoint inks and document papers based on similarities in elemental composition. Some of the advantages of these laser-based methods include minimum sample consumption/destruction, high sensitivity, high selectivity and excellent discrimination between samples from different origins. Figures of merit are reported including limits of detection, precision, homogeneity at a micro-scale and linear dynamic range. The variation of the elemental composition in paper was studied within a single sheet, between pages from the same ream, between papers produced by the same plant at different time intervals and between seventeen paper sources produced by ten different plants. The results show that elemental analysis of paper by LIBS and LA-ICP-MS provides excellent discrimination (> 98%) between different sources. Batches manufactured at weekly and monthly intervals in the same mill were also differentiated. The ink of more than 200 black pens was analyzed to determine the variation of the chemical composition of the ink within a single pen, between pens from the same package and between brands of gel inks and ballpoint inks. Homogeneity studies show smaller variation of elemental compositions within a single source than between different sources (i.e. brands and types). It was possible to discriminate between pen markings from different brands and between pen markings from the same brand but different model. Discrimination of ~ 96–99% was achieved for sets that otherwise would remain inseparable by conventional methods. The results show that elemental analysis, using either LA-ICP-MS or LIBS, provides an effective, practical and robust technique for the discrimination of document paper and gel inks with minimum mass removal (9–15 μg) and minimum damage to the document's substrate.     

显微共聚焦拉曼光谱结合群分析的黑色直液笔墨迹鉴别研究

黑色直液笔是一种新型书写工具,目前对该种笔墨迹的相关研究较少。为给文件检验工作中墨迹的分析提供新的参考依据,本实验使用显微共聚焦拉曼光谱技术,采集了30支不同品牌、型号的黑色直液笔墨迹光谱数据,进行Savitzky-Golay卷积平滑处理后,依据光谱图的拉曼位移及拉曼谱峰差异对墨迹进行初步分析。设置聚类方法为组间联接,区间距离测量方式为平方欧式距离,对采集的光谱数据进行群分析,将30支黑色直液笔墨迹样本分成了3类,并与品牌建立了相关联系;同时通过主成分分析验证了群分析的可靠性和准确性。研究表明,显微共聚焦拉曼光谱技术结合群分析方法可实现对黑色直液笔墨迹的无损分析及有效鉴别,该方法操作简便、结果准确,适用于法庭科学文件检验。     

Pure Ion Chromatograms Combined with Advanced Machine Learning Methods Improve Accuracy of Discriminant Models in LC–MS-Based Untargeted Metabolomics

Untargeted metabolomics based on liquid chromatography coupled with mass spectrometry (LC–MS) can detect thousands of features in samples and produce highly complex datasets. The accurate extraction of meaningful features and the building of discriminant models are two crucial steps in the data analysis pipeline of untargeted metabolomics. In this study, pure ion chromatograms were extracted from a liquor dataset and left-sided colon cancer (LCC) dataset by K-means-clustering-based Pure Ion Chromatogram extraction method version 2.0 (KPIC2). Then, the nonlinear low-dimensional embedding by uniform manifold approximation and projection (UMAP) showed the separation of samples from different groups in reduced dimensions. The discriminant models were established by extreme gradient boosting (XGBoost) based on the features extracted by KPIC2. Results showed that features extracted by KPIC2 achieved 100% classification accuracy on the test sets of the liquor dataset and the LCC dataset, which demonstrated the rationality of the XGBoost model based on KPIC2 compared with the results of XCMS (92% and 96% for liquor and LCC datasets respectively). Finally, XGBoost can achieve better performance than the linear method and traditional nonlinear modeling methods on these datasets. UMAP and XGBoost are integrated into KPIC2 package to extend its performance in complex situations, which are not only able to effectively process nonlinear dataset but also can greatly improve the accuracy of data analysis in non-target metabolomics.