Classification of washing powder brands using near-infrared spectroscopy combined with chemometric calibrations

Zhang, Honggang; Qinmin, Yang; Lu, Jiangang

doi:10.1016/j.saa.2013.11.057

Cited by 10 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…17 To optimize the performance of the BP-NN classier, parameters (i.e., number of hidden neurons, learning rate) were determined by a trial and error method. It minimizes the global error of the systems by adjusting node weights in the supervised learning procedure.…”

Section: Bp-nn Classiermentioning

confidence: 99%

“…A three layer (i.e., an input layer, a hidden layer, and an output layer) BP-NN classier was used to construct the monitoring model. 17 To optimize the performance of the BP-NN classier, parameters (i.e., number of hidden neurons, learning rate) were determined by a trial and error method. In this study, the BP-NN classier had two inputs, one hidden layer of 28 neurons and one output.…”

Section: Bp-nn Classiermentioning

confidence: 99%

See 1 more Smart Citation

Monitoring the wheat straw fermentation process using an electronic nose with pattern recognition methods

2015

View full text Add to dashboard Cite

To monitor the wheat straw solid-state fermentation process in real time, an electronic nose (e-nose) was attempted in this study. The e-nose was designed to detect gas changes in the fermentation process and was equipped with a sensor array composed of eleven selected commercially available metal oxide semiconductor (MOS) gas sensors. Using the e-nose data, an appropriate monitoring model can be constructed to determine process states. Therefore, selecting the optimal pattern recognition method was crucial. For the simplicity of monitoring models, principal component analysis was used to extract features (i.e. principal components or latent variables) of the e-nose data as inputs of monitoring models.For comparison, three representative methods (i.e. Gaussian process, support vector machine and back propagation neural networks) were assessed. The results sufficiently demonstrated excellent promise for the e-nose technique and the Gaussian process performed better than the other two pattern recognition methods.

show abstract

Section: Bp-nn Classiermentioning

confidence: 99%

Section: Bp-nn Classiermentioning

confidence: 99%

Monitoring the wheat straw fermentation process using an electronic nose with pattern recognition methods

2015

View full text Add to dashboard Cite

show abstract

“…Filling the silos, bins, and hoppers with granular materials of different properties are typical examples of the processes where segregation could occur. In detergent powder formulations, inhomogeneity of components particularly minor ingredients could lead to significant economic and health issues [6,7]. A typical laundry detergent powder product is a complex formulation containing the surfactants, bleaching agents, and auxiliaries such as enzymes.…”

Section: Introductionmentioning

confidence: 99%

Tailoring particle shape for enhancing the homogeneity of powder mixtures: Experimental study and DEM modelling

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[2][3][4][5][6] One pivotal task of spectral quantitative analysis is to build up a model that takes the spectral data on different wavelengths as inputs and consequently predict the amount of chemical species according to regression results. [2][3][4][5][6] One pivotal task of spectral quantitative analysis is to build up a model that takes the spectral data on different wavelengths as inputs and consequently predict the amount of chemical species according to regression results.…”

Section: Introductionmentioning

confidence: 99%

“…Spectroscopy studies the spectral data to nd out related information precisely and swily and is used in a wide range of applications, such as colorimetric thermometer 1 and quantitative analysis, etc. [2][3][4][5][6] One pivotal task of spectral quantitative analysis is to build up a model that takes the spectral data on different wavelengths as inputs and consequently predict the amount of chemical species according to regression results. 7,8 The most commonly used regression modelling method for spectroscopy is partial least squares (PLS) as it can solve the multicollinearity problem between the variables to a certain extent.…”

Section: Introductionmentioning

confidence: 99%

Variable selection based on information tree for spectroscopy quantitative analysis

Cao

Yan

et al. 2015

Anal. Methods

View full text Add to dashboard Cite

Spectroscopy is a fast and efficient component analysis method, and full spectrum prediction model may be redundant and inaccurate. This paper proposes a variable selection method based on an information tree for spectroscopy quantitative analysis. Firstly, a feature training set that indicates the information of the selected variables is generated. Then, partial least squares (PLS) is performed on the spectral calibration set, and the root-mean-square error of cross-validation is used to evaluate the feature training set. According to the corresponding evaluation results, the information gain of each wavelength is calculated. The wavelength with maximum information gain is defined as the root node, and an information tree is built based on the information gain where each leaf node represents a wavelength. The final selection result is a conjunction path of the leaf nodes that has bigger information gain. The full spectrum PLS, the uninformative variable elimination with the PLS method, the genetic algorithm with the PLS method and the proposed method are conducted on a real spectral data set of flue gas, and the effectiveness of the methods are compared and discussed. The experimental results verify that the prediction precision and the compression ability of the proposed method is higher.

show abstract

Classification of washing powder brands using near-infrared spectroscopy combined with chemometric calibrations

Cited by 10 publications

References 26 publications

Monitoring the wheat straw fermentation process using an electronic nose with pattern recognition methods

Monitoring the wheat straw fermentation process using an electronic nose with pattern recognition methods

Tailoring particle shape for enhancing the homogeneity of powder mixtures: Experimental study and DEM modelling

Variable selection based on information tree for spectroscopy quantitative analysis

Contact Info

Product

Resources

About