Partial Least-squares Artificial Neural Network Research Articles

Enterprise Collaboration Optimization in China Based on Supply Chain Resilience Enhancement

With the promotion of the new round of industrial revolution, the development environment of enterprises has undergone tremendous changes. Collaboration among enterprises has become crucial for enhancing core competitiveness, with the concept of the supply chain playing a key role. However, the complex and vulnerable nature of the supply chain operation environment poses various risks, hampering effective cooperative relationships between enterprises. This article proposed integrating the partial least-squares-artificial neural network (PLS-ANN) method to address this issue and optimize collaborative enterprise practices. The study examined enterprise collaboration optimization. This article uses used artificial neural network (ANN) to classify various complex data, implement an intelligent algorithm model for synchronous processing, and combine partial least squares (PLS) to classify and process the data information generated by collaborative networks to find the best match, minimizing the negative impact of multiple correlations of variables on enterprise collaboration. An empirical analysis was conducted in 2022, focusing on a manufacturing enterprise's supply chain and external cooperation management. The analysis examined two aspects: the supply chain's risk resistance level and the effectiveness of enterprise cooperation. Results showed that after implementing the PLS-ANN model, the average trust index between the enterprise and eight cooperative partners increased to approximately 0.652, compared to the initial average trust index of only 0.528. Detailed data analysis indicated that the PLS-ANN method effectively improved the supply chain's risk resistance capability while optimizing the cooperative relationships among all participating enterprises.

Application of advanced machine learning algorithms for anomaly detection and quantitative prediction in protein A chromatography

Protein A capture chromatography, which forms the core of the mAb purification platform, demands cautious use and maximum resin utilization due to high cost associated with resin. In this paper, we propose an application of advanced machine learning (ML) algorithms to address two most crucial objectives of column integrity breach and yield prediction for resin cycling study of protein A chromatography. Two approaches have been considered to detect anomalies in case of column integrity breach. The first approach utilized the traditional Principal Component Analysis (PCA) method for dimensionality reduction followed by anomaly detection using Isolation Forest (IF) algorithm. The second approach involved the application of deep learning neural network based Long Short Term Memory autoencoder (LSTM AE). Both the algorithms could successfully predict the column integrity failure 4 cycles ahead of the actual cycle. In the case of prediction of percentage yield decay, a partial least squares-artificial neural network (PLS-ANN) augmented model was utilized and compared with the traditional PLS regression model. The developed PLS-ANN model with higher R2 and lower RMSE values of 0.96 and 0.014 respectively could outperform the classical PLS model with lower R2 and RMSE values of 0.88 and 0.028, resulting in more accurate yield prediction. The developed ML algorithms for both case studies could not only successfully forecast anomalies by detecting subtle changes in column packing quality and thereby facilitate real time control decisions for preventive measures, a prerequisite for continuous manufacturing, but also demonstrated the ability to predict complex yield decay behaviour for protein A chromatography. As biopharmaceutical manufacturing adopts continuous processing, copious amount of data will be generated from the process and analytical equipment on the manufacturing floor, and the proposed advanced ML algorithms have significant potential in dealing with nonlinearities of the different unit operations simultaneously and facilitate real-time control decision making.

Nondestructive Prediction of Rice Seed Viability Using Spectral and Spatial Information Modeling of Visible–Near Infrared Hyperspectral Images

HighlightsAn NIR-Vis hyperspectral imaging approach was developed to predict the viability of rice seeds.Through multi-step accelerated aging, seed lots in various states were used for the experiments.Models using spectral information and spectral-spatial information of hyperspectral images were used and compared.Abstract. Rice is one of the world’s most important food crops, and rice seed viability is an important factor in rice crop production. In this study, a visible–near infrared (vis–NIR) hyperspectral imaging system and spectral–spatial information modeling are used to predict the viability of rice seeds. Experimental samples are prepared using seeds harvested in two different years and artificially aged for various periods. Vis-NIR hyperspectral acquisition and germination tests of the prepared seed samples are performed. Partial least square (PLS)–discriminant analysis, a support vector machine (SVM), a PLS–SVM, a PLS–artificial neural network, and a one-dimensional–convolutional neural network (CNN) for the mean spectra of seeds, as well as a CNN, a PLS–CNN, and dual branch networks for the hyperspectral images of the seeds are applied for viability prediction modeling. Result shows that an accuracy of approximately 90% and high f1 scores can be obtained in most models. Furthermore, it is confirmed that models using spectral and spatial information can classify hard samples more effectively. Keywords: Deep learning, Hyperspectral images, Rice, Seed, Spectroscopy, Viability.

Determination of the uranium elemental concentration in molten salt fuel using laser-induced breakdown spectroscopy with partial least squares-artificial neural network hybrid models

Accurate uranium (U) composition analysis of the molten salt nuclear fuel mixture is a necessary step in nuclear fuel quality control. Laser-induced breakdown spectroscopy (LIBS) is an optical emission spectrometry technique for elemental composition. The non-linear phenomena in LIBS signal are the drawback of this technique, especially for high atomic number (Z) element in a complex matrix. To overcome this limitation, a hybrid chemometrics model of the partial least squares-artificial neural network (PLS-ANN) was used to quantify the U composition in the salt fuel mixture of Molten salt breeder reactor. This work shows the optimisation of several parameters, viz., spectra pre-treatment procedure, factor number of PLS for ANN input, number of hidden neurons and layers in ANN, activation function, and number of ANN iterations. The collective advantages of data dimension reduction from PLS and the nonlinear processing ability from ANN, improved the accuracy of LIBS quantitative analysis for U from ≈7% using simple PLS to ≈4% precision using a hybrid model.

Determination of the nutrient profile in plant materials using laser-induced breakdown spectroscopy with partial least squares-artificial neural network hybrid models.

Nutrient profile determination for plant materials is an important task to determine the quality and safety of the human diet. Laser-induced breakdown spectroscopy (LIBS) is an atomic emission spectrometry of the material component analytical technique. However, quantitative analysis of plant materials using LIBS usually suffers from matrix effects and nonlinear self-absorption. To overcome this problem, a hybrid quantitative analysis model of the partial least squares-artificial neural network (PLS-ANN) was used to detect the compositions of plant materials in the air. Specifically, fifty-eight plant materials were prepared to split into calibration, validation and prediction sets. Nine nutrient composition profiles of Mg, Fe, N, Al, B, Ca, K, Mn, and P were employed as the target elements for quantitative analysis. It demonstrated that the prediction ability can be significantly improved by the use of the PLS-ANN hybrid model compared to the method of standard calibration. Take Mg and K as examples, the root-mean-square errors of calibration (RMSEC) of Mg and K were decreased from 0.0295 to 0.0028 wt.% and 0.2884 to 0.0539 wt.%, and the mean percent prediction errors (MPE) were decreased from 5.82 to 4.22% and 8.82 to 4.12%, respectively. This research provides a new way to improve the accuracy of LIBS for quantitative analysis of plant materials.

Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

<p>Predictive models is crucial in near-infrared (NIR) spectroscopic analysis. Partial least square - artificial neural network (PLS-ANN) is a hybrid method that may improve the performance of prediction in NIR spectroscopic analysis. This study investigates the advantage of PLS-ANN over the well-known modelling in spectroscopy analysis that is partial least square (PLS) and artificial neural network (ANN). The results show that ANN that coupled with first order SG derivatives achieved the best prediction with root mean square error of prediction (RMSEP) of 0.3517 gd/L and coefficient of determination ( ) of 0.9849 followed by PLS-ANN with RMSEP of 0.4368 gd/L and of 0.9787, and PLS with RMSEP of 0.4669 gd/L and of 0.9727. This suggests that the spectrum information may unable to be totally represented by the first few latent variables of PLS and a nonlinear model is crucial to model these nonlinear information in NIR spectroscopic analysis.</p>

Development of a partial least squares-artificial neural network (PLS-ANN) hybrid model for the prediction of consumer liking scores of ready-to-drink green tea beverages

In order to develop products that would be preferred by consumers, the effects of the chemical compositions of ready-to-drink green tea beverages on consumer liking were studied through regression analyses. Green tea model systems were prepared by dosing solutions of 0.1% green tea extract with differing concentrations of eight flavour keys deemed to be important for green tea aroma and taste, based on a D-optimal experimental design, before undergoing commercial sterilisation. Sensory evaluation of the green tea model system was carried out using an untrained consumer panel to obtain hedonic liking scores of the samples. Regression models were subsequently trained to objectively predict the consumer liking scores of the green tea model systems. A linear partial least squares (PLS) regression model was developed to describe the effects of the eight flavour keys on consumer liking, with a coefficient of determination (R2) of 0.733, and a root-mean-square error (RMSE) of 3.53%. The PLS model was further augmented with an artificial neural network (ANN) to establish a PLS-ANN hybrid model. The established hybrid model was found to give a better prediction of consumer liking scores, based on its R2 (0.875) and RMSE (2.41%).

Comparison of multiple statistical techniques to predict soil phosphorus

Soil scientists have tested various models to predict soil physical, chemical and biological properties over the last few decades. Determination of soil phosphorus (P) in soils is difficult due to the sensitivity of its measurement, especially in developing nations because of lack of sufficient facilities and limitation of financial resources. In this study, advanced statistical methods (intelligent and regression models) were evaluated, such as genetic algorithm (GA), artificial neural network (ANN), fuzzy inference system (FIS), adaptive neuro-fuzzy inference system (ANFIS), partial least squares (PLS), principal components regression (PCR), ordinary least squares (OLS) and multiple regression (MR), to determine the best model to predict P. This research was carried out at Mazandaran Research Center of Agricultural and Natural Resources, Sari, Iran. Four properties of soils, clay, sand, soil organic matter (SOM) and pH were presented to the models as independent parameters to predict soil P. Such advanced quantitative models have never been compared with each other in order to find the best model for prediction. The results revealed that PLS (among regression models) and GA and ANN (among intelligent models) are promising approaches for the estimation of soil P with higher R2 and value account for (VAF) and lower mean absolute percentage error (MAPE) and root mean square error (RMSE) compared to the other models. The ANN model predicted soil P more accurately than the other models with R2=0.912 and RMSE=4.019. The GA and PLS models both provided formulas to predict soil P with good fits. Results of the sensitivity analysis showed that SOM was a more effective factor predicting soil P relative to the other variables and SOM provides an important source of P in soil.

Using Reflectance Spectroscopy and Artificial Neural Network to Assess Water Infiltration Rate into the Soil Profile

We explored the effect of raindrop energy on both water infiltration into soil and the soil's NIR-SWIR spectral reflectance (1200–2400 nm). Seven soils with different physical and morphological properties from Israel and the US were subjected to an artificial rainstorm. The spectral properties of the crust formed on the soil surface were analyzed using an artificial neural network (ANN). Results were compared to a study with the same population in which partial least-squares (PLS) regression was applied. It was concluded that both models (PLS regression and ANN) are generic as they are based on properties that correlate with the physical crust, such as clay content, water content and organic matter. Nonetheless, better results for the connection between infiltration rate and spectral properties were achieved with the non-linear ANN technique in terms of statistical values (RMSE of 17.3% for PLS regression and 10% for ANN). Furthermore, although both models were run at the selected wavelengths and their accuracy was assessed with an independent external group of samples, no pre-processing procedure was applied to the reflectance data when using ANN. As the relationship between infiltration rate and soil reflectance is not linear, ANN methods have the advantage for examining this relationship when many soils are being analyzed.