Micro-Raman and X-ray fluorescence spectroscopy data fusion for the classification of ochre pigments

Two different data-fusion strategies are evaluated for the combination of the outputs of combined Raman/X-Ray fluorescence instrument. The studied application deals with the classification of ochre pigments investigated in the field of cultural heritage. The two fusion strategies are: (1) first level fusion: combines raw signals obtained from each technique and (2) second level fusion: combines extracted features provided individually by each technique. Classification tool is partial least squares-discriminant analysis (PLS-DA). Classification results obtained performing different data-fusion strategies are compared with those results obtained performing a single classification model for each data source. The results show that the combination of signal features is the most suitable for a rapid and unique processing of both types of spectra. Benefits and drawbacks of each strategy are also discussed.     

Data fusion in the wavelet domain by means of fuzzy aggregation connectives

Dual-domain classification analysis is proposed to identify pigments used in works of art studied by Raman spectroscopy and X-ray fluorescence spectrometry. By means of this methodology, Raman and X-ray fluorescence data are jointly processed by a high-level fusion approach. The system proposed aims to avoid the pre-processing stage and directly process raw data obtained from the instrument. The system is tested with spectra contaminated with background components of different shapes and intensities and with those with the background removed by line segment correction. The benefits of the approach were well demonstrated in a study of an ochre pigment classification.The approach is based on the main advantage of wavelet transform, which is multiresolution. Each spectrum is split into blocks, according to a specific frequency, to form a wavelet prism. Partial least squares-discriminant analysis (PLS-DA) is then applied to those blocks which contain the deterministic part of the signal and are not influenced by noise and background signal components. At the end, to obtain the final classification assignment, high-level data fusion of the classifications results (decision levels) obtained from PLS-DA analysis is done by means of fuzzy aggregation connective operators. Our study showed that fuzzy aggregation may be suitable for performing high-level data fusion on dual-domain data. This method can be automated so that classification can be rapid. It can handle classifications with different levels of difficulty and requires no prior knowledge of sample composition.     

Classification of Rhizoma et Radix Notoperygii by HPLC Fingerprints with the Aid of Chemometrics

Chromatographic profiles of Rhizoma et Radix Notoperygii (RRN, “Qianghuo” in Chinese), a complex traditional Chinese medicine (TCM), were collected by high-performance liquid chromatography with diode array detection (HPLC-DAD) at 330 nm. These data profiles were used as fingerprints to investigate quality control classification modeling of the RRN samples. In contrast to the classical methods for discrimination of TCMs, that is, just using common HPLC peaks, all chromatographic profile data were pre-processed by the correlation optimized warping method and polynomial functions; then, these data were submitted as fingerprints (variables) for classification on the basis of sample origin. Chemometrics methods used for calibration modeling and subsequent sample classification-least square support vector machine (LS-SVM), artificial neural network (ANN), and partial least square discriminant analysis (PLS-DA); all produced satisfactory calibrations as well as classification results.     

Multi-Elemental Composition Data Handled by Chemometrics for the Discrimination of High-Value Italian Pecorino Cheeses

The multi-elemental composition of three typical Italian Pecorino cheeses, Protected Designation of Origin (PDO) Pecorino Romano (PR), PDO Pecorino Sardo (PS) and Pecorino di Farindola (PF), was determined by Inductively Coupled Plasma Optical Emission Spectrometry (ICP-OES). The ICP-OES method here developed allowed the accurate and precise determination of eight major elements (Ba, Ca, Fe, K, Mg, Na, P, and Zn). The ICP-OES data acquired from 17 PR, 20 PS, and 16 PF samples were processed by unsupervised (Principal Component Analysis, PCA) and supervised (Partial Least Square-Discriminant Analysis, PLS-DA) multivariate methods. PCA revealed a relatively high variability of the multi-elemental composition within the samples of a given variety, and a fairly good separation of the Pecorino cheeses according to the geographical origin. Concerning the supervised classification, PLS-DA has allowed obtaining excellent results, both in calibration (in cross-validation) and in validation (on the external test set). In fact, the model led to a cross-validated total accuracy of 93.3% and a predictive accuracy of 91.3%, corresponding to 2 (over 23) misclassified test samples, indicating the adequacy of the model in discriminating Pecorino cheese in accordance with its origin.     

Classification of time-of-flight secondary ion mass spectrometry spectra from complex Cu–Fe sulphides by principal component analysis and artificial neural networks

Artificial neural network (ANN) and a hybrid principal component analysis-artificial neural network (PCA-ANN) classifiers have been successfully implemented for classification of static time-of-flight secondary ion mass spectrometry (ToF-SIMS) mass spectra collected from complex Cu–Fe sulphides (chalcopyrite, bornite, chalcocite and pyrite) at different flotation conditions. ANNs are very good pattern classifiers because of: their ability to learn and generalise patterns that are not linearly separable; their fault and noise tolerance capability; and high parallelism. In the first approach, fragments from the whole ToF-SIMS spectrum were used as input to the ANN, the model yielded high overall correct classification rates of 100% for feed samples, 88% for conditioned feed samples and 91% for Eh modified samples. In the second approach, the hybrid pattern classifier PCA-ANN was integrated. PCA is a very effective multivariate data analysis tool applied to enhance species features and reduce data dimensionality. Principal component (PC) scores which accounted for 95% of the raw spectral data variance, were used as input to the ANN, the model yielded high overall correct classification rates of 88% for conditioned feed samples and 95% for Eh modified samples.     

FT-MIR and UV–vis data fusion strategy for origins discrimination of wild Paris Polyphylla Smith var. yunnanensis

Paris Polyphylla Smith var. yunnanensis (Franch.) Hand.-Mazz has multiple therapeutic properties and the origins may affect clinical efficacy. Tracing the geographical origin is important to the authentication and quality assessment of this species. 177 wild samples collected from central, southeast and northwest Yunnan Province, China, were analyzed by single analytical method and data fusion strategies (low- and mid-levels) using Fourier transform mid-infrared (FT-MIR) and ultraviolet-visible (UV–vis) spectroscopies combined with chemometrics (partial least squares discrimination analysis (PLS-DA) and support vector machines grid search (SVM-GS)), for categorizing samples from different geographic origins. According to the results, mid-level data fusion strategy presented a better generalization performance and accuracy rates based on latent variables selected by PLS-DA than single analytical method and low-level data fusion strategy. Accuracy rates were almost 100% when both of the PLS-DA and SVM-GS were employed for classifying samples picked from southeast and northwest districts based on mid-level dataset. For samples collected from central of Yunnan where was divided into seven categories in this paper, the accuracy rates of training set and test set of PLS-DA and SVM-GS were preferable (>87%). Based on the mid-level data set, both of the classification results of PLS-DA and SVM-GS presented satisfying accuracy for 177 samples. Additionally, as small as possible parameters showed in mid-level data set, it suggested that this method was robust and generalized. Therefore, the comprehensive method was established for the origin traceability of wild P. Polyphylla Smith var. yunnanensis, which is meaningful for the quality control of herbal medicines.     

Determining the adulteration of spices with Sudan I-II-II-IV dyes by UV-visible spectroscopy and multivariate classification techniques

We propose a very simple and fast method for detecting Sudan dyes (I, II, III and IV) in commercial spices, based on characterizing samples through their UV-visible spectra and using multivariate classification techniques to establish classification rules. We applied three classification techniques: K-Nearest Neighbour (KNN), Soft Independent Modelling of Class Analogy (SIMCA) and Partial Least Squares Discriminant Analysis (PLS-DA). A total of 27 commercial spice samples (turmeric, curry, hot paprika and mild paprika) were analysed by chromatography (HPLC-DAD) to check that they were free of Sudan dyes. These samples were then spiked with Sudan dyes (I, II, III and IV) up to a concentration of 5 mg L⁻¹. Our final data set consisted of 135 samples distributed in five classes: samples without Sudan dyes, samples spiked with Sudan I, samples spiked with Sudan II, samples spiked with Sudan III and samples spiked with Sudan IV.Classification results were good and satisfactory using the classification techniques mentioned above: 99.3%, 96.3% and 90.4% of correct classification with PLS-DA, KNN and SIMCA, respectively. It should be pointed out that with SIMCA, there are no real classification errors as no samples were assigned to the wrong class: they were just not assigned to any of the pre-defined classes.     

NMR and chemometric methods: a powerful combination for characterization of Balsamic and Traditional Balsamic Vinegar of Modena

This work presents the capability of NMR spectroscopy combined with Chemometrics in predicting the ageing of Balsamic and Traditional Balsamic Vinegar of Modena. The need of an analytical method is an important requirement for both research oriented and commercial evaluation of these very valuable products. ¹H NMR spectroscopy, based on the advantage of rapid sample analysis without any manipulation or derivatization, is here proposed as a valid tool to describe Balsamic and Traditional Balsamic Vinegar of Modena. For this purpose, 72 reliable samples, were divided into three different groups according to their ageing process: young (<12 years), old (>12 and <25 years) and extra old (>25 years). Hierarchical Projection to Latent Structures Discriminant Analysis (PLS-DA) allowed us to characterize the ageing process. Variables showing the largest VIP (Variable Importance in the Projection) were extracted from PLS-DA model, thus shedding lights onto the role played by specific compounds in this complex ageing process. Two robust classification models, were built by PLS-DA and Naïve Bayes classifier and compared to prove the accuracy of the representation on both training and test sets. The predictions obtained for 41 “unknown” vinegar samples with these both methods gave more than 80% agreement among them.     

超高效液相色谱-四极杆飞行时间质谱分析不同加工何首乌中差异化学成分

建立了超高效液相色谱-四极杆飞行时间质谱(UPLC-QTOF-MS)结合多元统计分析技术对不同加工何首乌中化学成分差异的分析方法。何首乌样品采用甲醇在室温下超声提取后,采用UPLC-QTOF-MS进行分析,对采集的图谱通过峰匹配、峰对齐、滤噪处理等进行特征峰提取,然后用主成分分析(PCA)和偏最小二乘法-判别分析(PLS-DA)对数据进行分析。结果显示,不同加工何首乌样品间的化学组成存在显著性差异;根据一级质谱精确质荷比和二级质谱碎片信息,结合软件数据库搜索及相关文献进行成分鉴定,初步筛选并鉴定出33种不同加工何首乌间差异显著的化学成分,其中15种为共有差异化学成分,并呈现出不同的变化规律。研究结果可为揭示不同加工方法对何首乌代谢产物差异性的影响规律提供依据。     

Flow injection mass spectroscopic fingerprinting and multivariate analysis for differentiation of three Panax species

This study describes the use of spectral fingerprints acquired by flow injection(FI)-MS and multivariate analysis to differentiate three Panax species: P. ginseng, P. quinquefolius, and P. notoginseng. Data were acquired using both high resolution and unit resolution MS, and were processed using principal component analysis (PCA), soft independent modeling of class analogy (SIMCA), partial least squares-discriminant analysis (PLS-DA), and a fuzzy rule-building expert system (FuRES). Both high and unit resolution MS allowed discrimination among the three Panax species. PLS-DA and FuRES provided classification with 100% accuracy while SIMCA provided classification accuracies of 77 and 88% by high- and low-resolution MS, respectively. The method does not quantify any of the sample components. With FI-MS, the analysis time was less than 2 min.     

Tracing the origin of extra virgin olive oils by infrared spectroscopy and chemometrics: A case study

In this paper, the potential of coupling mid- and near-infrared spectroscopic fingerprinting techniques and chemometric classification methods for the traceability of extra virgin olive oil samples from the PDO Sabina was investigated. To this purpose, two different pattern recognition algorithm representative of the discriminant (PLS-DA) and modeling (SIMCA) approach to classification were employed. Results obtained after processing the spectroscopic data by PLS-DA evidenced a rather high classification accuracy, NIR providing better predictions than MIR (as evaluated both in cross-validation and on an external test set). SIMCA confirmed these results and showed how the category models for the class Sabina can be rather sensitive and highly specific. Lastly, as samples from two harvesting years (2009 and 2010) were investigated, it was possible to evidence that the different production year can have a relevant effect on the spectroscopic fingerprint. Notwithstanding this, it was still possible to build models that are transferable from one year to another with good accuracy.     

Metabolite profiling on apple volatile content based on solid phase microextraction and gas-chromatography time of flight mass spectrometry

A headspace SPME GC-TOF-MS method was developed for the acquisition of metabolite profiles of apple volatiles. As a first step, an experimental design was applied to find out the most appropriate conditions for the extraction of apple volatile compounds by SPME. The selected SPME method was applied in profiling of four different apple varieties by GC-EI-TOF-MS. Full scan GC-MS data were processed by MarkerLynx software for peak picking, normalisation, alignment and feature extraction. Advanced chemometric/statistical techniques (PCA and PLS-DA) were used to explore data and extract useful information. Characteristic markers of each variety were successively identified using the NIST library thus providing useful information for variety classification. The developed HS-SPME sampling method is fully automated and proved useful in obtaining the fingerprint of the volatile content of the fruit. The described analytical protocol can aid in further studies of the apple metabolome.     

Screening analysis to detect adulteration in diesel/biodiesel blends using near infrared spectrometry and multivariate classification

This paper proposes an analytical method to detect adulteration of diesel/biodiesel blends based on near infrared (NIR) spectrometry and supervised pattern recognition methods. For this purpose, partial least squares discriminant analysis (PLS-DA) and linear discriminant analysis (LDA) coupled with the successive projections algorithm (SPA) have been employed to build screening models using three different optical paths and the following spectra ranges: 1.0 mm (8814-3799 cm⁻¹), 10 mm (11,329-5944 cm⁻¹ and 5531-4490 cm⁻¹) and 20 mm (11,688-5952 cm⁻¹ and 5381-4679 cm⁻¹). The method is validated in a case study involving the classification of 140 diesel/biodiesel blend samples, which were divided into four different classes, namely: diesel free of biodiesel and raw vegetal oil (D), blends containing diesel, biodiesel and raw oils (OBD), blends of diesel and raw oils (OD), and blends containing a fraction of 5% (v/v) of biodiesel in diesel (B5). LDA-SPA models were found to be the best method to classify the spectral data obtained with optical paths of 1.0 and 20 mm. Otherwise, PLS-DA shows the best results for classification of 10 mm cell data, which achieved a correct prediction rate of 100% in the test set.     

Identification of discriminatory variables in proteomics data analysis by clustering of variables

This article presents a data analysis method for biomarker discovery in proteomics data analysis. In factor analysis-based discriminate models, the latent variables (LV's) are calculated from the response data measured at all employed instrument channels. Since some channels are irrelevant and their responses do not possess useful information, the extracted LV's possess mixed information from both useful and irrelevant channels. In this work, clustering of variables (CLoVA) based on unsupervised pattern recognition is suggested as an efficient method to identify the most informative spectral region and then it is used to construct a more predictive multivariate classification model. In the suggested method, the instrument channels (m/z value) are clustered into different clusters via self-organization map. Subsequently, the spectral data of each cluster are separately used as the input variables of classification methods such as partial least square-discriminate analysis (PLS-DA) and extended canonical variate analysis (ECVA). The proposed method is evaluated by the analysis of two experimental data sets (ovarian and prostate cancer data set). It is found that our proposed method is able to detect cancerous from healthy samples with much higher sensitivity and selectivity than conventional PLS-DA and ECVA methods.     

Pattern recognition of Inductively Coupled Plasma Atomic Emission Spectroscopy of human scalp hair for discriminating between healthy and Hepatitis C patients

Inductively Coupled Plasma Atomic Emission Spectroscopy measurements of six trace elements were performed on the scalp hair of 155 donors, 73 of which have been diagnosed with Hepatitis C and 82 Controls. Principal Components Analysis (PCA) was employed to visualise the separation between groups and show the relationship between the elements and the diseased state. Pattern recognition methods for classification involving Quadratic Discriminant Analysis and Partial Least Squares Discriminant Analysis (PLS-DA) were applied to the data. The number of significant components for both PCA and PLS were determined using the bootstrap. The stability of training set models were determined by repeatedly splitting the data into training and test sets and employing visualisation for two components models: the percent classification ability (CC), predictive ability (PA) and model stability (MS) were computed for test and training sets.     

The use of high performance liquid chromatography-quadrupole time-of-flight mass spectrometry coupled to advanced data mining and chemometric tools for discrimination and classification of red wines according to their variety

In this study, the potential of high performance liquid chromatography coupled to quadrupole time-of-flight mass spectrometry (HPLC–QTOFMS) for metabolomic profiling of red wine samples was examined. Fifty one wines representing three varieties (Cabernet Sauvignon, Merlot, and Pinot Noir) of various geographical origins were sourced from the European and US retail market. To find compounds detected in analyzed samples, an automated compound (feature) extraction algorithm was employed for processing background subtracted single MS data. Stepwise reduction of the data dimensionality was followed by principal component analysis (PCA) and partial least square-discriminant analysis (PLS-DA) which were employed to explore the structure of the data and construct classification models. The validated PLS-DA model based on data recorded in positive ionization mode enabled correct classification of 96% of samples. Determination of molecular formula and tentative identification of marker compound was carried out using accurate mass measurement of full single MS spectra. Additional information was obtained by correlating the fragments obtained by MS/MS accurate mass spectra using the QTOF with collision induced dissociation (CID) of precursor ions.     

Classification of Brazilian Coffee Using Near-Infrared Spectroscopy and Multivariate Calibration

This work describes the use of near infrared spectroscopy (NIRS) and chemometric techniques calibration for the classification of coffee samples from different lots and producers acquired in supermarkets and roasting industries in some Brazilian cities. Seventy-three samples of finely ground roasted coffee were acquired in the market and 91 samples of roasted ground Arabica beans were analyzed in the full NIR spectral range (800–2500 nm) using a diffuse reflectance accessory coupled to an MB160 Bomem spectrophotometer. Two classification models were constructed: Soft Independent Modeling Class Analogy (SIMCA) and PLS Discriminant Analysis (PLS-DA). All findings reveal that NIR spectroscopy, coupled with either SIMCA or PLS-DA multivariate models, can be a useful tool to differentiate roasted coffee grains and to replace sensory tests.     

基于RF_AdaBoost模型的血液种属鉴别算法

针对人类和非人类血液种属鉴别对无损、 高效分析方法的需求, 结合随机森林(Random Forest)和AdaBoost(Adaptive Boosting Algorithm)算法, 提出了一种血液种属鉴别方法(RF_AdaBoost). 该方法将RF作为AdaBoost的弱分类器, 以达到提高模型鉴别准确度, 增强模型鲁棒性的目的. 采用RF、 支持向量机(SVM)、 极限学习机(ELM)、 核极限学习机(KELM)、 堆栈自编码网络(SAE)、 反向传播网络(BP)、 主成分分析-线性判别法(PCA-LDA)及偏最小二乘判别分析(PLS-DA)与RF_AdaBoost模型进行对比, 以不同规模血液拉曼光谱数据训练集进行鉴别实验评估其性能. 结果表明, 随着训练样本的增加, RF_AdaBoost鉴别准确度最高达100%, 预测标准偏差趋于0. 与其它模型相比, RF_AdaBoost具有较高的分类准确度及较强的稳定性, 为血液种属的鉴别工作提供了新方法.     

1H NMR and UV-visible data fusion for determining Sudan dyes in culinary spices

Two data fusion strategies (variable and decision level) combined with a multivariate classification approach (Partial Least Squares-Discriminant Analysis, PLS-DA) have been applied to get benefits from the synergistic effect of the information obtained from two spectroscopic techniques: UV-visible and ¹H NMR. Variable level data fusion consists of merging the spectra obtained from each spectroscopic technique in what is called “meta-spectrum” and then applying the classification technique. Decision level data fusion combines the results of individually applying the classification technique in each spectroscopic technique. Among the possible ways of combinations, we have used the fuzzy aggregation connective operators. This procedure has been applied to determine banned dyes (Sudan III and IV) in culinary spices. The results show that data fusion is an effective strategy since the classification results are better than the individual ones: between 80 and 100% for the individual techniques and between 97 and 100% with the two fusion strategies.