Chemometrics and Intelligent Laboratory Systems最新文献

A comprehensive multi-scale computational strategy was developed in this study based on mass transfer and machine learning for simulation of drug concentration distribution in a biomaterial matrix. The controlled release was modeled and validated via the hybrid model. Mass transfer equations along with kinetics models were solved numerically and the results were then used for machine learning models. We investigated the performance of three regression models, namely Decision Tree (DT), Random Forest (RF), and Extra Tree (ET) in predicting medicine concentration (C) based on r and z data. Hyper-parameter optimization is conducted using Glowworm Swarm Optimization (GSO). Results revealed high predictive accuracy across all models, with ET demonstrating superior performance, achieving a coefficient of determination value (R²) of 0.99854, an RMSE of 1.1446E-05, and a maximum error of 6.49087E-05. DT and RF also exhibit notable performance, with coefficients of determination equal to 0.99571 and 0.99655, respectively. These results highlight the effectiveness of ensemble tree-based methods in accurately predicting chemical concentrations, with Extra Tree (ET) Regression emerging as the most promising model for this specific dataset.

Accurate baseline correction is a fundamental requirement for extracting meaningful spectral information and enabling precise quantitative analysis using Raman spectroscopy. Although numerous baseline correction techniques have been developed, they often require meticulous parameter adjustments and yield inconsistent results. To address these challenges, we have introduced a novel approach, namely constrained Gaussian radial basis function fitting (CGF). Our method involves solving a curve-fitting problem using Gaussian radial basis functions under specific constraints. To ensure stability and efficiency, we developed a linear programming algorithm for the proposed approach. We evaluated the performance of CGF using simulated Raman spectra and demonstrated its robustness across various scenarios, including changes in data length and noise levels. In contrast to standard methods, which frequently require complicated parameter adjustments and may exhibit varying errors, our approach provides a simple parameter search and consistently achieves low errors. We further assessed CGF using real Raman spectra, leading to enhanced accuracy in the quantitative analysis of the Raman spectra of chemical warfare agents. Our results emphasize the potential of CGF as a valuable tool for Raman spectroscopy data analysis, significantly advancing sophisticated analytical techniques.

Spectroscopic measurements can show distorted spectral shapes arising from a mixture of absorbing and scattering contributions. These distortions (or baselines) often manifest themselves as non-constant offsets or low-frequency oscillations. As a result, these baselines can adversely affect analytical and quantitative results. Baseline correction is an umbrella term where one applies pre-processing methods to obtain baseline spectra (the unwanted distortions) and then remove the distortions by differencing. However, current state-of-the art baseline correction methods do not utilize analyte concentrations even if they are available, or even if they contribute significantly to the observed spectral variability. We modify a class of state-of-the-art methods (penalized baseline correction) that easily admit the incorporation of a priori analyte concentrations such that predictions can be enhanced. This modified approach will be deemed supervised and penalized baseline correction (SPBC). Performance will be assessed on two near infrared data sets across both classical penalized baseline correction methods (without analyte information) and modified penalized baseline correction methods (leveraging analyte information). There are cases of SPBC that provide useful baseline-corrected signals such that they outperform state-of-the-art penalized baseline correction algorithms such as AIRPLS. In particular, we observe that performance is conditional on the correlation between separate analytes: the analyte used for baseline correlation and the analyte used for prediction—the greater the correlation between the analyte used for baseline correlation and the analyte used for prediction, the better the prediction performance.

This study illustrates the effective control of COVID-19 infection through the adsorption of safranal (SAF) on B₁₆N₁₆ and Al₁₆N₁₆ fullerene-like cages. The SAF adsorption onto the B₁₆N₁₆ and Al₁₆N₁₆ surfaces in gas, water (H₂O), and chloroform (CHCl₃) environments were assessed using density functional theory (DFT) and time-dependent (TD) density functional theory methods, analyzing the substrates and their complexes. The Al₁₆N₁₆/SAF complex exhibited the most negative binding energy and structural stability in the water phase compared to the B₁₆N₁₆/SAF complex at the PBE0-D3 level. The thermodynamic parameters indicated that the adsorption of SAF onto the fullerene-like cages is exothermic, particularly for the Al₁₆N₁₆/SAF complex. Additionally, the interaction of SAF with the fullerene-like cages in the water phase is more pronounced than in gas and chloroform environments. The complexes' energy gap (Eg) decreases in all three environments compared to the perfect systems, with a significant reduction of over 21 % in all phases. This substantial decrease in the energy gap suggests that the complexes have increased reactivity and sensitivity to SAF, likely due to a significant change in electronic conductivity. The results of molecular docking indicate that the Al₁₆N₁₆/SAF complex in the water phase exhibited a strong binding affinity compared to the other compounds studied. These findings suggest that the Al₁₆N₁₆/SAF complex holds promise as a potential inhibitor for COVID-19 and as a valuable material for biomedical applications and drug delivery systems.

The first stage in the industrial production of Styrene-Butadiene Rubber (SBR) typically consists in obtaining a latex from a train of continuous stirred tank reactors. Accurate real-time estimation of some key process variables is of paramount importance to ensure the production of high-quality rubber. Monitoring the mass conversion of monomers in the last reactor of the train is particularly important. To this effect, various soft sensors (SS) have been proposed, however they have not addressed the underlying complex dynamic relationships existing among the process variables. In this work, a SS based on recurrent neural networks (RNN) is developed to estimate the mass conversion in the last reactor of the train. The main challenge is to obtain an adequate estimate of the conversion both in its usual steady-state operation and during its frequent transient operating phases. Three architectures of RNN: Elman, GRU (Gated Recurrent Unit), and LSTM (Long Short-Term Memory) are compared to critically evaluate their performances. Moreover, a comprehensive analysis is conducted to assess the ability of these models to represent different operational modes of the train. The results reveal that the GRU network exhibits the best performance for estimating the mass conversion of monomers. Then, the performance of the proposed model is compared with a previously-developed SS, which was based on a linear estimation model with a Bayesian bias adaptation mechanism and the use of Control Charts for decision-making. The model proposed here proved to be more efficient for estimating the mass conversion of monomers, particularly during transient operating phases. Finally, to evaluate the methodology utilized for designing the SS, the same RNN architectures were trained to online estimate another quality variable: the mass fraction of Styrene bound to the copolymer. The obtained results were also acceptable.

Among the most frequently diagnosed diseases in citrus, citrus Huanglongbing disease has caused severe economic losses to the citrus industry worldwide since there is no curable method and it spreads quickly. As callose accumulation in phloem is one of the early response events to Asian species Candidatus Liberibacter asiaticus (CLas) infection, the dynamic perception of the sieve plate region can be used as an indicator for the early diagnosis of citrus HLB disease. In this study, one-dimensional convolutional neural network (1D-CNN) models were established to achieve early detection of HLB disease based on spectral information in the sieve plate region using Fourier transform infrared microscopy (micro-FTIR) spectrometer. Partial least squares regression (PLSR) and the least squares support vector machine regression (LS-SVR) models are used for the prediction of callose based on the micro-FTIR information in the sieve plate region of the citrus midrib. Furthermore, an improved data augmentation method by superimposing Gaussian noise was proposed to expand the spectral amplitude. The proposed method has achieved 98.65 % classification accuracy, which was higher than that of other traditional algorithms such as the logistic model tree (LMT), linear discriminant analysis (LDA), Bayes (BS), support vector machine (SVM) and k-nearest neighbors (kNN), and also than that of the molecular detection qPCR (Quantitative real-time polymerase chain reaction) method. Finally, based on the established early detection model with laboratory samples, it can also be used to detect the citrus HLB in complex field samples by using model updating methods, and the overall detection accuracy of the model reached 91.21 %. Our approach has potential for the early diagnosis of citrus HLB disease from the microscopic scale, which would provide useful and precise guidelines to prevent and control citrus HLB disease.

In the era of chemical big data, the high complexity and strong interdependencies present in the datasets pose considerable challenges when constructing accurate parametric models. The Gaussian process model, owing to its non-parametric nature, demonstrates better adaptability when confronted with complex and interdependent data. However, the standard Gaussian process has two significant limitations. Firstly, the time complexity of inverting its kernel matrix during the inference process is $O{\left(n\right)}^3$. Secondly, all data share a common kernel function parameter, which mixes different data types and reduces the model accuracy in mixing-category data identification problems. In light of this, this paper proposes a mixture Gaussian process model that addresses these limitations. This model reduces time complexity and distinguishes data based on different data features. It incorporates a Gaussian mixture distribution for the inducing variables to approximate the original data distribution. Stochastic Variational Inference is utilized to reduce the computational time required for parameter inference. The inducing variables have distinct parameters for the kernel function based on the data category, leading to improved analytical accuracy and reduced time complexity of the Gaussian process model. Numerical experiments are conducted to analyze and compare the performance of the proposed model on different-sized datasets and various data category cases.

In the chemical plants, data-driven process monitoring serves as a vital tool to ensure product quality and maintain production line safety. However, the accuracy of monitoring hinges directly upon the quality of process data. Given the inherently slow and complex nature of chemical processes, coupled with the potential for gross errors in process data leading to inaccuracies in model predictions, this paper proposes a method called Conditional Dynamic Variational Autoencoder combined with a Particle Filter (CDVAE-PF) for data reconciliation and subsequent process monitoring. CDVAE-PF leverages the capabilities of Conditional Dynamic Variational Autoencoder (CDVAE) to effectively model chemical process data in the presence of noise. This probabilistic model serves as the foundation for the Particle Filter (PF), which is employed for data reconciliation. Moreover, CDVAE-PF incorporates mechanisms to detect and rectify gross errors in process data, further enhancing its efficacy in data reconciliation. Subsequently, monitoring indices based on CDVAE are established to facilitate process monitoring. Through numerical simulations of a two-to-one variables Continuous Stirred Tank Reactor (CSTR) example and a fifteen-to-one variables dichloroethane distillation process from an actual chemical plant, CDVAE-PF demonstrates its effectiveness by reducing mean absolute error to 7.8 % and 12.8 % respectively in gross error data reconciliation. Moreover, in terms of monitoring performance, CDVAE-PF successfully mitigates misjudgments caused by gross errors, thereby significantly enhancing the reliability of process monitoring in chemical plants.

The present work involves extreme gradient boosting in combination with shapley values, a thriving amalgamation under the terrain of Explainable artificial intelligence, along with genetic algorithm for the analysis of thrombin inhibitory activity of diverse pool of 2803 molecules. The methodology involves genetic algorithm for feature selection, followed by extreme gradient boosting analysis. The eight parametric genetic algorithm - extreme gradient boosting analysis has high statistical acceptance with R²_tr = 0.895, R²_L10%O = 0.900, and Q2F3 = 0.873. Shapley additive explanations, which provide each variable in a model an importance value, served as the foundation for the interpretation. Then, ceteris paribus approach involving comparison of counterfactual examples has been used to understand the influence of a structural feature on activity profile. The analysis indicates that aromatic carbon, ring/non-ring nitrogen in combination with other structural features govern the inhibitory profile. The genetic algorithm - extreme gradient boosting model's simplicity and predictions suggest that “Explainable AI” is useful in the future for identifying and using structural features in drug discovery.

Feature selection on incomplete datasets is a challenging task. To address this challenge, existing methods first employ imputation methods to complete the dataset and then perform feature selection based on the imputed dataset. Since missing value imputation and feature selection are entirely independent, the importance of features cannot be considered during imputation. However, in real-world scenarios or datasets, different features have varying degrees of importance. To this end, we proposed a novel incomplete data feature selection framework that considers feature importance. The framework mainly consists of two alternating iterative stages: M-stage and W-stage. In the M-stage, missing values are imputed based on a given feature importance vector and multiple initial imputation results. In the W-stage, an improved reliefF algorithm is employed to learn the feature importance vector based on the imputed data. In particular, the feature importance output by the W-stage in the current iteration will be used as the input of the M-stage in the next iteration. Experimental results on artificial and real missing datasets demonstrate that the proposed method outperforms other approaches significantly.