Search

In a qualitative analysis of near-infrared spectroscopy (NIRS), when the samples to be analyzed are difficult to obtain or there are few counterexamples, the robustness of the models is poor, resulting in the decline of the generalization ability of the models. In this case, the effective method is to construct virtual samples to achieve the balance of categories. In this contribution, three virtual spectrum construction strategies including Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN), and Deep Convolutional Generative Adversarial Network (DCGAN) were explored to deal with the problem of insufficient or imbalanced sample numbers in NIRS analysis. The strategies were tested with the melamine and Yali pears two spectral datasets. The PLS-DA and Correct Recognition Rate (CRR) were used for discriminant model construction and accuracy evaluation, respectively. The results show that SMOTE, ADASYN, and DCGAN processing strategies can all improve the global CRR (CRR glob). The SMOTE and ADASYN can improve the CRR for majority class sample (CRR maj), but the CRR for minority class sample (CRR min) has decreased. For the DCGAN method, the CRR glob , CRR maj , and CRR min were all improved. The standard deviation of the results of the multiple parallel calculations demonstrates the robustness of DCGAN generation method. Therefore, the DCGAN method has good reliability and practicability, and can increase the robustness and generalization ability of the NIRS model. [Display omitted] • Exploring virtual spectrum construction strategies. • Evaluate the plausibility and diversity of the virtual spectrum. • Improve the robustness and generalization ability of the NIRS model. • Test model performance on public datasets and experimental data. [ABSTRACT FROM AUTHOR]

Generative adversarial linear discriminant analysis (GALDA) is formulated as a broadly applicable tool for increasing classification accuracy and reducing overfitting in spectrochemical analysis. Although inspired by the successes of generative adversarial neural networks (GANs) for minimizing overfitting artifacts in artificial neural networks, GALDA was built around an independent linear algebra framework distinct from those in GANs. In contrast to feature extraction and data reduction approaches for minimizing overfitting, GALDA performs data augmentation by identifying and adversarially excluding the regions in spectral space in which genuine data do not reside. Relative to non-adversarial analogs, loading plots for dimension reduction showed significant smoothing and more prominent features aligned with spectral peaks following generative adversarial optimization. Classification accuracy was evaluated for GALDA together with other commonly available supervised and unsupervised methods for dimension reduction in simulated spectra generated using an open-source Raman database (Romanian Database of Raman Spectroscopy, RDRS). Spectral analysis was then performed for microscopy measurements of microsphereroids of the blood thinner clopidogrel bisulfate and in THz Raman imaging of common constituents in aspirin tablets. From these collective results, the potential scope of use for GALDA is critically evaluated relative to alternative established spectral dimension reduction and classification methods. [Display omitted] • Generative adversarial linear discriminant analysis (GALDA) was developed for spectral classification. • A theoretical foundation for implementing GALDA for spectral dimension reduction and classification was derived. • Simulations with known ground truth spectral classes supported the assessment of GALDA. • Application of GALDA improved classification accuracy in polymorph discrimination by conventional Raman spectroscopy. • Pixel-wise application of GALDA produced composition maps in good agreement with manual assignments for model system. [ABSTRACT FROM AUTHOR]

The selection of a training set is the key to determining the quality of the model. In the spectrum analysis, due to various interference factors, the quality of the collected spectral data of some samples has a serious deviation. If directly used in modeling, it will introduce bias to the establishment of the model. Therefore, to get the most representative samples, it is necessary to select samples before establishing the model. This paper proposes a two-dimensional sample selection (TDSS) method, which selects samples from two angles of spectral data quality and variable correlation. This method and Mahalanobis distance method were respectively applied to dynamic spectrum (DS) data to screen samples. The samples screened by the two methods were used for modeling. Finally, establish partial least squares (PLS) linear regression model with a quadratic nonlinear correction method to predict the target components. The experimental results show that the sample screening method significantly improved the accuracy and prediction performance of the model, and it is better than the Mahalanobis distance method. In the prediction of triglyceride and total cholesterol, the correlation coefficient can reach above 0.82. The experimental results fully prove the effectiveness of the sample selection method in this paper, and it has a remarkable effect on improving the accuracy and robustness of the model. This paper provides a new way for sample selection of modeling set in spectral analysis of complex solutions. [Display omitted] • Propose a new training set sample screening method. • Consider two dimensions: sample data quality and variable correlation. • Based on statistical and dynamic spectrum data. • Improve the accuracy of non-invasive blood component detection. • This method is a universal method for sample screening in spectral analysis. [ABSTRACT FROM AUTHOR]

Quantitative mass spectrometry analysis for multi-component gas phase reaction processes is a typical multi-input and multi-output (MIMO) nonlinear problem. Conventional calibration and analytical methods that are based on the common hypothesis of linearity of the detected signal and gas parameters, could result in misjudgment of the reaction mechanism and inaccuracy in the determination of the reaction kinetics. In the present work, theoretical derivations based on equivalent characteristic spectrum analysis (ECSA®), discrete mode experiments and continuous mode experiments were performed, and the nonlinearity of mass spectrometry was confirmed. It is only possible to determine the physical parameters such as flow rate and/or concentrations of gases by properly handling the nonlinearity of mass spectrometry. In such case comprehensive reaction mechanisms and even the kinetics of the process can be accurately characterized. Well-handled nonlinear mass spectrometry analysis ensures a reliable and highly accurate identification for the multi-component gas phase reaction processes, and ensures high signal-to-noise ratio for detecting the small-flow gases at a wide range of carrier gas flow. [Display omitted] • The MS nonlinearity between MI and MO signals is found and expounded firstly. • The MS nonlinearity is confirmed through theoretical derivation and experiments. • Taking the nonlinearity ensures the MS reliability, and high signal-to-noise ratio. • Using ECSA® it was possible to well interpret the nonlinearity. [ABSTRACT FROM AUTHOR]

The newest achievements in the field of glow microdischarges generated in contact with a flowing liquid cathode (FLC) and a flowing liquid anode (FLA), used as the excitation sources for optical emission spectrometry (OES), were summarized herein. The design of recently reported discharge systems was compared and comprehensively discussed. A lot of effort was devoted to evaluate the effect of selected operating parameters, i.e. , discharge voltage and current, sample flow rate, sample pH, jet-supporting gas flow rate, and discharge gap, on the microplasma stability and the intensity of measurable analytical signals. Furthermore, the influence of chemical modifiers, i.e. , organic acids, alcohols, and surfactants, aimed at improving the sensitivity and reducing matrix effects, was referred to as well. Finally, the analytical performance and the application of these promising excitation sources for the elemental analysis of different-matrix samples were presented. [Display omitted] • Flowing liquid cathode a Atmospheric pressure glow discharge was described reviewed over the past 5 years. • Discharge system design and operating conditions were surveyed. • Susceptibility to interferences and analytical performance were recalled. • Applications in element analysis were given. [ABSTRACT FROM AUTHOR]