Rapid Detection of Adulteration in Extra-Virgin Olive Oil using Three-Dimensional Fluorescence Spectra Technology with Selected Multivariate Calibrations

To rapidly and efficiently detect the presence of adulterants in extra-virgin olive oil, 3D fluorescence spectra technology was employed with the help of multivariate calibration. Parallel factor analysis and characteristic parameters method were comparatively employed to compress and extract the data of 3D fluorescence spectra. Then, three different non-linear and linear classification tools (i.e., back-propagation artificial neural network, least-square support vector machine and k-nearest neighbor) were systemically studied and compared in developing the model. The number of principle components and parameters of models were optimized by cross-validation. Compared with parallel factor analysis, characteristic parameters method, in this article, has its own superiority. Experimental results also showed that the performance of least-square support vector machine model is the best among the three models. The optimal least-square support vector machine model was achieved when seven principle components were used, with the discrimination rate of 98.96% in calibration set and 96.88% in prediction set, respectively. The misclassified samples are adulterated extra-virgin olive oil, and their adulterated concentrations were lower than 2.5% (wt/wt). The overall results sufficiently demonstrated that 3D fluorescence spectroscopy technology coupled with characteristic parameters method and least-square support vector machine classification tool has the potential to detect adulterated extra-virgin olive oil products when their adulterant concentrations are more than 2.5% (wt/wt).     

基于PCA-SVM的红枣缺陷识别方法

以干制红枣的黑斑、破头以及分类难度较高的干条3种病害图像作为研究对象,分别采用颜色矩和灰度共生矩阵提取颜色、纹理特征中的14维特征向量,然后采用主成分分析法对特征向量进行优化,得到4个主因素特征向量作为支持向量机输入。采用交叉算法确定最优支持向量机惩罚参数c和核函数参数g对支持向量机多分类模型进行训练,利用训练后的模型对红枣进行多分类试验。结果证明,该方法能够对红枣黑斑、破头和干条3种缺陷果进行快速准确的识别,识别率分别为93.3%,100.0%和96.6%,总识别率可达97.2%,且分类效率高。     

Application of hybrid image features for fast and non-invasive classification of raisin

A new approach for the non-invasive classification of raisins is presented based on the hybrid image features, namely morphological, color and texture features. A total of 74 features (8 morphological, 30 color, and 36 textural) were extracted from RBG images. Seven kinds of models were established based on different feature sets. They were three kinds of models established based on single feature set, three kinds of models established based on the combination of two feature sets, and one kind of model established based on the combination of all feature sets. Five kinds of classifiers, namely partial least squares (PLS), linear discriminant analysis (LDA), soft independent modeling of class analogy (SIMCA), and least squares support vector machine (LS-SVM) with linear and radial basis function (RBF) kernels were used for the model establishment based on different feature sets. The best correct answer rates (CAR) of 99% was obtained when LDA was used to establish the classification model based on the combination of all feature sets, which was higher than those of the models established based on single feature set or the combination of two feature sets. The results show that the feature combination is helpful to improve the accuracy of raisin classification. It was concluded that the varieties of raisin could be accurately classified based on RGB image features and the combination of morphological, color and texture features was an accurate way to improve the accuracy of classification.     

基于高光谱成像技术的祁门红茶等级无损检测

为实现快速无损的茶叶产品等级评估,应用近红外（900~1700 nm）高光谱成像技术对6个等级的祁门红茶进行分类。首先利用线性和非线性降维方法对高光谱数据进行可视化处理,可视化算法包括线性方法的主成分分析（Principal Component Analysis,PCA）、多维尺度变换（Multi-Dimensional Scaling,MDS）,和非线性方法的t分布随机邻域嵌入（t-Distributed Stochastic Neighbour Embedding,t-SNE）、Sammon非线性映射。其次利用支持向量机（Support Vector Machine,SVM）和极限学习机（Extreme Learning Machine,ELM）建立分类模型来鉴定祁门红茶的不同等级。最后利用SVM和ELM分类模型对高光谱图像每个像素点进行识别,得到预测图。结果表明,t-SNE可以将6个等级的祁门红茶分在六个不同的簇,SVM和ELM的预测集准确率分别为100%和96.35%。t-SNE可视化效果最佳,SVM的检测模型能够有效地对祁门红茶六个等级进行识别。本文为茶叶产品等级的快速、无损检测提供了一种有效的方法,对茶叶产品的质量控制、真伪检测和掺假检测具有重要意义。     

基于分类特征提取和深度学习的牛肉品质识别

目的：降低数据差异性和光谱特征冗余度对牛肉品质识别的影响。方法：提出一种基于分类特征提取和深度学习的牛肉品质识别方法,采用改进的DPeak算法对光谱数据进行自适应聚类分析,实现对数据的差异性分析。定义牛肉光谱特征提取目标函数,采用离散狮群算法进行求解,提取每个分类的最佳光谱特征子集,最大限度降低特征冗余度。运用改进狮群算法(ILSO)对每个分类对应的支持向量机(SVM)模型参数进行优化,提出融合分类特征提取和ILSO优化SVM的牛肉品质识别模型,完成对牛肉品质的分类识别。结果：相比于SSA-SVM、PCA-SVM识别模型,该模型识别精度提高了约12.3%~14.5%。结论：基于分类特征提取和深度学习的牛肉品质识别模型能够提高牛肉品质识别精度。     

Bruise detection on red bayberry (Myrica rubra Sieb. & Zucc.) using fractal analysis and support vector machine

A new method to sort red bayberries based on the presence of bruises was proposed. Principal component-support vector machine (PC-SVM) and support vector machine (SVM) models combined with fractal analysis were developed and compared with classification models based on RGB intensity values. The results of this study show the classification models based on fractal parameters achieved 100% total accuracy rate, but the models based on RGB values was only 85.29%. In addition, the performance of the SVM model in terms of iteration time and the number of support vectors was better than the PC-SVM model. Therefore, the SVM model based on fractal analysis is recommended for detecting bruises on red bayberries.     

拉曼光谱结合模式识别方法鉴别大米种类

为实现大米种类准确、快速的鉴别,选购72份大米样品,粉碎,采集粒度为100-140目米粉的拉曼光谱,对谱图数据进行去噪、归一化和特征提取后,综合运用主成分分析（PCA）、层次聚类分析（HCA）和支持向量机（SVM）三种方法对粳米、籼米和糯米进行聚类与模式识别研究。三种大米经PCA分析可直观地归为三簇,籼米和糯米可被区分开,但粳米与糯米、粳米与籼米不能区分。HCA结果表明粳米与籼米较难区分,糯米与其它两种米有较大差异,三种大米经HCA聚类分析准确率为81.94%。而采用SVM判别方法经10次运行后的平均识别率达98.86%。实验证明：拉曼光谱法结合支持向量机用于大米种类的分类与识别简单快速,在分析数据相对复杂的情况下,可快速建立分类模型并实现大米种类间的鉴定与识别。     

基于近红外光谱技术的茶叶新旧鉴别及产地溯源研究

摘 要：目的 建立基于近红外光谱的定性分析模型,实现对茶叶的新旧分类和产地溯源。方法 首先采用傅里叶近红外光谱仪采集茶叶样品的漫反射光谱数据,然后使用SG平滑算法（savitzky-golay smoothing, SG）和数据标准化（normalization）对光谱数据进行预处理,最后基于遗传优化算法（genetic algorithem, GA）和粒子群优化算法（particle swarm optimization, PSO）分别建立了优化向量机模型（support vector machine, SVM）,从而实现新旧茶叶的分类以及产地溯源。结果 与GA-SVM模型相比,PSO-SVM模型的建模效果较好,且分类时间更短,在新旧鉴别和产地溯源实验中都达到了100%的预测精度。结论 基于近红外光谱建立的PSO-SVM模型可以实现茶叶新旧的判别以及产地溯源,为鉴别茶叶年份和追踪茶叶产地提供了理论支撑和技术指导。     

A Study on Soluble Solids Content Assessment Using Electronic Nose: Persimmon Fruit Picked on Different Dates

Soluble solids content is an important internal quality attribute in determining fruit maturity and harvesting time. In this study, an electronic nose was used to monitor the soluble solids content based on the change of volatile compounds of persimmon fruit during different picking-dates. Principal component analysis was applied to investigate whether the sensors’ response of the electronic nose was able to distinguish persimmons among different picking dates corresponding to different maturity levels. The loading analysis was used to identify those sensors that contribute most for flavor modeling. The results indicated that the electronic nose could distinguish the different picking dates using principal component analysis. The model testing showed that a support vector machine could achieve better prediction accuracy and generalization than multiple linear regression and back-propagation neural network and the average prediction accuracy, root mean square error, and mean relative error of the soluble solids content. By using support vector machine models were 91.36, 0.71, and 0.58%, respectively, which implied that the electronic nose was effective for soluble solids content prediction of persimmons on the basis of the support vector machine model.     

马铃薯品质鉴别的近红外光谱与多源信息耦合

建立了基于机器视觉和近红外光谱技术的分级概率输出,利用DS证椐融合规则,搭建适用于异源数据的无损检测分级决策模型。采用方向梯度直方图和主成分提取方法提取光谱特征,并应用支持向量机和AdaBoost分类器进行识别,在此基础上,构建了基于特征层融合的马铃薯分级模型。采用多源信息融合技术,建立了融合无损检测分级决策和特征层融合的多源信息融合农产品品质鉴别模型。仿真结果表明,相比于单一鉴别模型,多源信息融合鉴别模型识别率提高了12.7%~30.2%,达95.7% 以上。     

基于高光谱成像技术的白茶储藏年份判别

储藏年份是决定白茶经济价值的一大因素。为了实现快速便捷地判别白茶储藏年份,本文提出了基于高光谱成像技术判别分析白茶储藏年份的无损检测方法。通过对3、6、10年寿眉高光谱图像感兴趣区域光谱数据的提取,采用最小二乘平滑滤波、标准正态变换、归一化、多元散射校正预处理算法,并用支持向量机、偏最小二乘联合线性判定法、逻辑回归建模对不同预处理后的光谱数据进行判别分析。最后,通过分析混淆矩阵、精确率、召回率来评估模型性能。分析结果表明,经过标准正态变换预处理结合支持向量机所建立的模型判别效果最佳,训练集和测试集的精确率分别为90.83%和86.02%。由此可见,利用高光谱成像技术对白茶储藏年份进行快速无损的判别具有一定的可行性。     

基于决策融合的苹果分级检测关键技术研究

提出了一种判别树和改进支持向量机决策融合的苹果分级方法。采用判别树分类方法根据果径、缺陷区域、色泽等进行分类,采用粒子群对支持向量机分类模型进行优化,根据果形、纹理和成熟度等高维特征进行分类,使用核主成分分析法降低维度,并引入决策融合的概念,结合单一特征对样本等级进行综合评估。结果表明,该方法是切实可行的,其分类准确性为98%以上,可用于苹果的有效分级。     

基于介电特性的鸡蛋品种无损鉴别

为更合理有效实现鸡蛋品种分类,研究一种介电特性无损鉴别鸡蛋品种方法。本实验以4组不同品种鸡蛋(江苏镇江洋鸡蛋、江苏镇江草鸡蛋、安徽老南沟草鸡蛋、江苏东台草鸡蛋)为研究对象,采用平行极板法测量4组鸡蛋在10~200 k Hz条件下的介电特性参数,并利用支持向量机(support vector machine,SVM)算法建立鸡蛋品种鉴别分类检测模型。研究不同核函数(线性核函数、多项式核函数、RBF核函数和Sigmoid核函数)、不同参数寻优算法(网格搜索法、遗传算法和粒子群算法)选择对分类模型准确率的影响。结果表明,以线性核函数为SVM核函数、粒子群算法为SVM参数寻优算法时,建立的鸡蛋品种SVM分类模型的性能最优,其训练集正确率为95.83%,测试集正确率为95.83%。利用介电特性无损检测技术结合SVM算法,取得了很好的分类效果,为鸡蛋品种鉴别提供了一种新的快速有效的方法。     

Raisin Quality Classification Using Least Squares Support Vector Machine (LSSVM) Based on Combined Color and Texture Features

In this paper, an approach based on combined color and texture features to classify raisins is presented. Least squares support vector machine (LSSVM), linear discriminant analysis, and soft independent modeling of class analogy were used to construct classification models. A total of 480 images were captured from four grades of raisin samples by a Basler 601 fc IEEE1394 digital camera, 200 images were randomly selected to create calibration model (training set), and remaining images were used to verify the model (prediction set). Color features and texture features were obtained from two color spaces: red–green–blue and hue–saturation–intensity using histogram method and gray level co-occurrence matrix method, respectively. Our results indicate that the best performance with about 95% of average correct answer rate is achieved by LSSVM using combined color and texture features from HSI color space. This result is significantly higher than the performance of solely used color or texture features. The combined color and texture features coupled with a LSSVM classifier are a highly accurate way for raisin quality classification.     

Polyphenolic Profile of Red Wines for the Discrimination of Controlled Designation of Origin

The aims were to determine the polyphenolic profile of red wines from Spanish Designation of Origin (DO) Rías Baixas and Ribeira Sacra and to evaluate the feasibility of using polyphenolic profiles and chemometric tools to classify wines for authentication purposes. Trans-resveratrol, oenin, malvin, (+)-catechin, (?)-epicatechin, quercetin and syringic acid were determined in 39 samples. Soft independent modeling of class analogy (SIMCA), linear discriminant analysis (LDA) and support vector machine classification (SVM) were used to classify. For resveratrol, Ribeira Sacra red wines showed higher values than Rías Baixas wines (4.60 and 3.36 mg L^?1, respectively). SVM classification was adequate for 100 % classification of wines by their polyphenolic profile. SIMCA classification was also adequate for wine classification of DO Rías Baixas and Ribeira Sacra wines. As conclusion, polyphenolic profile can be used for classification of DOs. The models can discriminate outside wines. Thus, this approach can be useful for authentication purposes.     

Lychee Variety Discrimination by Hyperspectral Imaging Coupled with Multivariate Classification

This current study was carried out to investigate the ability of hyperspectral imaging (HSI) technique and multivariate classification for the differentiation of lychee varieties. A total of 122 lychee samples from three varieties (“Baila,” “Jizhui,” and “Guiwei”) were used. The relationship between reflectance spectra and lychee varieties were established. Principal component analysis (PCA) was implemented on the region of interest (ROI) image to reduce data dimensionality and visualize the cluster trend. The first two principal components (PCs) explained over 97 % of variances of all spectral bands. Linear (soft independent modeling of class analogy (SIMCA) and partial least square discriminant analysis (PLS-DA)) and nonlinear (back propagation neural network (BPNN) and support vector machine (SVM)) multivariate classification methods were used to develop discrimination models. The results revealed that SVM model achieved the best result, with the identification rate of 100 % in the calibration set and 87.81 % in the prediction set. BPNN had a discrimination rate of 100 % for the training set and 85.37 % for prediction set, while PSL-DA and SIMCA model had a discrimination rate of 78.05 % and 60.98 % for prediction sets, respectively. The nonlinear classification methods used were superior to the linear ones. The overall results showed that HSI system with SVM classification tool could be used in identification of lychee varieties.     

基于复杂网络提取和支持向量机模型分类的服装领型研究

为解决服装打版中款式自动搜索的问题,以服装衣领款式的结构特征为背景,以服装圆领型图像为例,先通过构建复杂网络对其进行复杂网络特征的描述与提取,然后采用支持向量机的模型实现8种衣领类型图像的分类。实验结果表明:样本整体的平均分类准确率为98%,各类别的平均分类准确率均达到96%以上,其中,圆领的平均分类准确率为100%;在原样本图像库中加入一定程度椒盐噪声和高斯噪声后,样本整体的分类准确率在80%上下浮动,表明支持向量机模型分类的方法适用于含有一定程度噪声的图像识别。因而,本文基于复杂网络提取和支持向量机模型分类的服装领型研究的提取和分类准确率高,且分类结果相对稳定。     

基于嗅觉可视化技术的眉茶等级分类方法

为了快速、准确地对眉茶等级进行分类,提出了一种基于嗅觉可视化技术的眉茶等级快速分类方法。首先,根据卟啉显色反应预实验结果,选定了12 种显色效果明显的卟啉指示剂制备嗅觉可视化传感器阵列,通过该传感器阵列与不同等级的眉茶茶汤进行反应,获取不同的特征图像。然后,对特征图像数据进行主成分分析和降维,将得到的不同维数的主成分分析结果作为输入变量,构建支持向量机（support vector machine,SVM）眉茶等级分类模型。最后,引入3 种群体智能优化算法（萤火虫算法、灰狼优化算法、布谷鸟算法）对SVM分类模型的惩罚因子c和核函数参数g进行优化。结果显示：未经优化的SVM分类模型对测试集的分类正确率为80%,所需的主成分个数为12 个;经过优化的SVM模型的分类正确率均有所提升,其中经过布谷鸟算法优化的SVM模型对测试集的分类正确率达到了93.3%,且所需的主成分个数减少为6 个。这表明应用嗅觉可视化技术能够实现对眉茶等级的分类,而通过群体智能优化算法优化SVM分类模型可以显著增强模型的性能,提高分类正确率。