Classification of Chinese Herbal Medicine by Laser-Induced Breakdown Spectroscopy with Principal Component Analysis and Artificial Neural Network

Wang, Jinmei; Liao, Xi; Zheng, Peichao; Xue, Shuwen; Peng, Rui

doi:10.1080/00032719.2017.1340949

Cited by 70 publications

(42 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In relation to herbal products, Wang et al 81 used LIBS combined with PCA and BP-ANN to classify Chinese herbal medicine with 99.9% classification accuracy of three types of herbal products, roots of Angelica pubescens, Codonopsis pilosula, and Ligusticum wallichii. The authors stablished 82 quality control markers for Chinese herbal medicines using BP-ANN; and the study of Ding et al 83 developed a method to improve the markers to Q-markers in Chinese herbal medicines quality management, using PLS-DA for screening analysis of the chemical markers and identification of herbal origin.…”

Section: Artificial Intelligence Methods For Multiple Questionsmentioning

confidence: 99%

Chemometrics in analytical chemistry – an overview of applications from 2014 to 2018

et al. 2019

View full text Add to dashboard Cite

A compilation of papers published between 2014 and 2018 was evaluated. Many papers related to multivariate calibration and classification have been reported, as well as, design of experiments applications and artificial intelligence methods. Some applications were highlighted, as medical and pharmaceutical, food analysis, fuels, biological and forensic for the chemometric techniques on this review. Most studies are related to developing methods for practical solutions in industry or routine analysis. A promising scenario is shown considering the number of published papers: a total of 832 for this period using the keywords, multivariate classification, multivariate calibration, analysis, chemometrics, prediction, analytical chemistry, artificial neural networks (ANN), design of experiments (DoE) and factorial design. An useful overview for Analytical Chemistry researchers´ combined with Chemometrics is presented in this review.

show abstract

Section: Artificial Intelligence Methods For Multiple Questionsmentioning

confidence: 99%

Chemometrics in analytical chemistry – an overview of applications from 2014 to 2018

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Therefore, it is the one that permits emulsion maintenance, in order to create nanoparticles and release the compound at the required rate [34]. Another explanation for this sensitivity is given by authors including [35,36] who have proven that there is a connection between principal component analysis and neural networks. These authors suggest that, when a multi-layered perceptron network that learns from a retropropagation algorithm and monitored by a self-associative mode is used to train a neural network, it is possible to obtain a selforganized system, with feed-forward synaptic connections from the factors to the response variables.…”

Section: Sensitivity Analysismentioning

confidence: 99%

Prediction of in vitro release of nanoencapsulated phenolic compounds using Artificial Neural Networks

Espinosa-Sandoval

Ochoa-Martínez

Ayala-Aponte

2020

DYNA

View full text Add to dashboard Cite

In Vitro Release modeling (IVR) of nanoencapsulated phenolic compounds (PC) is complex, due to the number of factors involved in the process. Artificial Neural Networks (ANN) are useful tools for its prediction because they consider the effect of all factors on the response. The release at 5h is crucial in kinetics because, in most cases, it is an equilibrium point leading to a constant phase. The objective of this investigation was to predict the IVR of nanoencapsulated PC at 5h using ANN. A database with information from the scientific literature was used. This model permits mathematical correlation of the IVR at 5h with eleven factors. The optimal network configuration consisted of one hidden layer with one neuron. A mathematical model was obtained with a Mean Square Error (MSE) of 0.0516 and a correlation coefficient (r) of 0.8413.

show abstract

“…Classification of LIBS data has been an active area of research. Automatic classification has been attempted on a variety of domains including mineralogy (classification of sedimentary ores [40], quartz samples [41], material science [42], botany [43], homeland security [44], and planetology [45]) The optimal classifier presented in the paper is relatively simple. (Classification is performed by computing a quadratic function of observed discrete spectral components.)…”

Section: Applicability Of the Optimal Classifiermentioning

confidence: 99%

Modeling of laser-induced breakdown spectroscopic data analysis by an automatic classifier

Pokrajac

Sivakumar

Markushin

et al. 2019

Int J Data Sci Anal

View full text Add to dashboard Cite

Laser-induced breakdown spectroscopy (LIBS) is a multi-elemental and real-time analytical technique with simultaneous detection of all the elements in any type of sample matrix including solid, liquid, gas, and aerosol. LIBS produces vast amount of data which contains information on elemental composition of the material among others. Classification and discrimination of spectra produced during the LIBS process are crucial to analyze the elements for both qualitative and quantitative analysis. This work reports the design and modeling of optimal classifier for LIBS data classification and discrimination using the apparatus of statistical theory of detection. We analyzed the noise sources associated during the LIBS process and created a linear model of an echelle spectrograph system. We validated our model based on assumptions through statistical analysis of "dark signal" and laser-induced breakdown spectra from the database of National Institute of Science and Technology. The results obtained from our model suggested that the quadratic classifier provides optimal performance if the spectroscopy signal and noise can be considered Gaussian.

show abstract

Classification of Chinese Herbal Medicine by Laser-Induced Breakdown Spectroscopy with Principal Component Analysis and Artificial Neural Network

Cited by 70 publications

References 30 publications

Chemometrics in analytical chemistry – an overview of applications from 2014 to 2018

Chemometrics in analytical chemistry – an overview of applications from 2014 to 2018

Prediction of in vitro release of nanoencapsulated phenolic compounds using Artificial Neural Networks

Modeling of laser-induced breakdown spectroscopic data analysis by an automatic classifier

Contact Info

Product

Resources

About