共查询到18条相似文献,搜索用时 125 毫秒
1.
2.
建立塑料饮料瓶物证快速准确检验鉴别方法。利用差分拉曼光谱法检验42个塑料饮料瓶样品,优化积分时间并进行重现性检验。在40 s最优积分时间条件下采集光谱,任选41个样品作为建立模型的数据集,剩余样品作为盲样,对41个样品材质初步定性分为聚对苯二甲酸乙二醇酯(PET)和聚乙烯(PE)两类。建立基于系统聚类(HCA)、多层感知器神经网络和径向基神经网络的PET样品鉴别模型,确定最优鉴别模型及样品最佳分类。结果表明,系统聚类-多层感知器神经网络为最优鉴别模型,PET样品最佳分类为2类。差分拉曼光谱法结合系统聚类和神经网络可实现塑料饮料瓶有效鉴别。 相似文献
3.
4.
5.
6.
建立一个无损检验药品塑料包装瓶并对其进行分类的模型。利用差分拉曼光谱技术对47个样品进行检测,首先在原始数据的基础上进行差分拉曼光谱分析并进行人工分类,再运用Fisher判别法(FDA)和主成分分析法(PCA)对数据进行处理,结合人工神经网络算法(ANN-MLP/RBF)构建分类模型。在多层神经网络(MLP)模型中,使用原始数据、FDA处理后的数据、PCA降维后的数据对样本分类的正确率分别为87.23%、93.62%、97.87%,MLP模型下对样本分类的整体准确率为93%;在径向基神经网络(RBF)模型下,使用原始数据、FDA处理后的数据、PCA降维后的数据对样本分类的正确率分别为87.23%、93.62%、95.74%,RBF模型下对样本分类的整体准确率为92%。在研究相同条件下对药品塑料包装瓶进行分类时,采用PCA+MLP模型为最佳方案。 相似文献
7.
8.
为建立一种快速无损检验区分塑料拖鞋鞋底的方法,利用显微共聚焦激光拉曼光谱仪采集了43个不同来源的塑料拖鞋鞋底样本的拉曼光谱图。拉曼数据经主成分分析降维后提取特征矩阵,对得到的特征矩阵进行系统聚类,建立Fisher判别函数对系统聚类的结果进行评价。最终构建径向基函数神经网络(RBFNN)实现对样本的鉴别分类,并绘制接受者操作特征曲线用以评估诊断价值。结果表明:拉曼数据提取出的特征矩阵经系统聚类被分为4组,Fisher判别分析经交叉验证后准确率为97.7%,径向基函数神经网络的准确率为100%。该方法实现了对样本快速无损的分类及预测,模型结构准确,可以为公安实际办案提供一种新思路。 相似文献
9.
10.
11.
12.
为实现对案发现场车用保险杠物证快速、无损、准确的分类与识别,提出了一种显微激光拉曼光谱分析技术结合多元建模用于车用保险杠模式分类方法。选择自动基线校正、峰面积归一化、Savitzky-Golay平滑(3次多项式,7点平滑)作为预处理方法,借助主成分分析和线性判别分析构建分类模型。结果表明,前27个主成分下,除了奥迪品牌的2个样本被误判在了广汽品牌的样本当中,其他不同品牌的样本均实现了100.00 %的准确区分,总体分类准确率为95.24 %,分类效果较为理想;针对实际案件中的未知样本,借助该方法确定其属于别克品牌,这与实际案件中物证信息相吻合;利用显微激光拉曼光谱分析技术多元建模分析可实现对不同品牌保险杠样本准确的识别与分类,可为微量物证鉴定方面的相关研究提供一定的思路与参考。 相似文献
13.
14.
Max Naumann Natalie Arend Rustam R. Guliev Christian Kretzer Ignacio Rubio Oliver Werz Ute Neugebauer 《International journal of molecular sciences》2023,24(1)
Macrophages are important cells of the innate immune system that play many different roles in host defense, a fact that is reflected by their polarization into many distinct subtypes. Depending on their function and phenotype, macrophages can be grossly classified into classically activated macrophages (pro-inflammatory M1 cells), alternatively activated macrophages (anti-inflammatory M2 cells), and non-activated cells (resting M0 cells). A fast, label-free and non-destructive characterization of macrophage phenotypes could be of importance for studying the contribution of the various subtypes to numerous pathologies. In this work, single cell Raman spectroscopic imaging was applied to visualize the characteristic phenotype as well as to discriminate between different human macrophage phenotypes without any label and in a non-destructive manner. Macrophages were derived by differentiation of peripheral blood monocytes of human healthy donors and differently treated to yield M0, M1 and M2 phenotypes, as confirmed by marker analysis using flow cytometry and fluorescence imaging. Raman images of chemically fixed cells of those three macrophage phenotypes were processed using chemometric methods of unmixing (N-FINDR) and discrimination (PCA-LDA). The discrimination models were validated using leave-one donor-out cross-validation. The results show that Raman imaging is able to discriminate between pro- and anti-inflammatory macrophage phenotypes with high accuracy in a non-invasive, non-destructive and label-free manner. The spectral differences observed can be explained by the biochemical characteristics of the different phenotypes. 相似文献
15.
Hillary N. Bengtson Dr. Dmitry M. Kolpashchikov 《Chembiochem : a European journal of chemical biology》2014,15(2):228-231
Differential receptors use an array of sensors to recognize analytes. Each sensor in the array can recognize not one, but several analytes with different rates, so a single analyte triggers a response of several sensors in the array. The receptor thus produces a pattern of signals that is unique for each analyte, thereby enabling identification of a specific analyte by producing a “fingerprint” pattern. We applied this approach for the analysis of DNA sequences of Mycobacterium tuberculosis strains that differ by single nucleotide substitutions in the 81‐bp hot‐spot region that imparts rifampin resistance. The technology takes advantage of the new multicomponent, selfassembling sensor, which produces a fluorescent signal in the presence of specific DNA sequences. A differential fluorescent receptor (DFR) contained an array of three such sensors and differentiated at least eight DNA sequences. The approach requires only one molecular‐beacon‐like fluorescent reporter, which can be used by all three sensors. The DFR developed in this study represents a cost‐efficient alternative to molecular diagnostic technologies that use fluorescent hybridization probes. 相似文献
16.
为了更好地认识和了解CL-20晶体结构演变规律和相变行为,利用金刚石对顶砧超高压实验技术,在0~50GPa下,研究了高压下ε-CL-20的原位拉曼光谱和红外光谱。结果表明,CL-20晶体在整个加压过程中存在两个相变,第一个相变发生在4.2~7.5GPa,认为是ε相到对称性更低的γ相转变,相变产生的原因是在压强的作用下,笼环外的硝基方向发生改变,电子云密度重置导致的分子构型转变;第二个相变发生在14.2~18.9GPa,属于γ相到ζ相的晶体结构转变;卸压后,拉曼和红外光谱恢复常压状态,表明CL-20晶体在研究压强范围内的相变过程是可逆的。 相似文献
17.
为建立一种检验塑钢窗物证的方法,利用X射线荧光光谱仪对收集到的40个不同品牌、同一品牌不同系列、同一品牌同一系列不同批次塑钢窗进行检验。采用Niton XL3t GOLDD+手持式荧光光谱仪,通过预实验确定了检测条件:Ag作阳极靶;检测电压为50kV;检测电流为200μA;采集时间为70s,在此条件下对样品进行检测,根据不同塑钢窗样本所测出的特征元素种类及质量分数可对样本进行区分。为了使分类结果科学准确,首先利用主成分分析法对实验结果进行降维处理,指定提取了4个因子,再利用系统聚类和K?Means快速聚类方法对样品数据进行聚类处理,将40个样本分为28类,并利用Fisher判别分析法验证了分类结果的科学合理性。该方法结合谱图分析和化学计量学,能快速、准确、无损地对样品做出分类,为公安基层实际办案提供帮助。 相似文献
18.
提出基于近红外(NIR)光谱的汽油牌号快速识别算法,主要包括预处理、特征提取和分类建模几部分,比较了各种分类方法的识别能力。实验结果表明:采用主元分析(PCA)提取特征进行模式识别的性能普遍优于直接在光谱波长域的方法,通过选择合适的PCA主元可以获得满意的分类效果,可用于汽油产品的牌号快速识别。 相似文献