Application of artificial neural networks to X‐ray fluorescence spectrum analysis

Li, Fēi; Gu, Zhixing; Ge, Liangquan; Sun, Di; Deng, Xutao; Wang, Shun; Hu, Bo; Xu, Jingru

doi:10.1002/xrs.2996

Cited by 12 publications

(6 citation statements)

References 95 publications

(134 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A variety of machine learning methods are applied to regression analysis, such as partial least squares regression (PLSR) ( Peng et al., 2016 ; Yu et al., 2020 ), extreme learning machine (ELM), and artificial neural networks (ANNs). ( Melgani and Bruzzone, 2004 ; Li et al., 2018 ).…”

Section: Basic Steps Of Spectroscopic Detectionmentioning

confidence: 99%

Optical imaging spectroscopy coupled with machine learning for detecting heavy metal of plants: A review

Ren

Cui

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

Heavy metal elements, which inhibit plant development by destroying cell structure and wilting leaves, are easily absorbed by plants and eventually threaten human health via the food chain. Recently, with the increasing precision and refinement of optical instruments, optical imaging spectroscopy has gradually been applied to the detection and reaction of heavy metals in plants due to its in-situ, real-time, and simple operation compared with traditional chemical analysis methods. Moreover, the emergence of machine learning helps improve detection accuracy, making optical imaging spectroscopy comparable to conventional chemical analysis methods in some situations. This review (a): summarizes the progress of advanced optical imaging spectroscopy techniques coupled with artificial neural network algorithms for plant heavy metal detection over ten years from 2012-2022; (b) briefly describes and compares the principles and characteristics of spectroscopy and traditional chemical techniques applied to plants heavy metal detection, and the advantages of artificial neural network techniques including machine learning and deep learning techniques in combination with spectroscopy; (c) proposes the solutions such as coupling with other analytical and detection methods, portability, to address the challenges of unsatisfactory sensitivity of optical imaging spectroscopy and expensive instruments.

show abstract

Section: Basic Steps Of Spectroscopic Detectionmentioning

confidence: 99%

Optical imaging spectroscopy coupled with machine learning for detecting heavy metal of plants: A review

Ren

Cui

et al. 2022

Front. Plant Sci.

View full text Add to dashboard Cite

show abstract

“…There may also be other factors not accounted for (such as dust) which are difficult to model. Neural networks have been used as an alternative [4][5][6] to the fundamental parameters method. However, neural networks require labeled data but obtaining spectra with corresponding elemental composition is often expensive.…”

Section: Introductionmentioning

confidence: 99%

“…The notation "name : a, b,c 7 ! x" denotes a function named "name" with three arguments (a, b, c) that returns x 5. A Lorentzian has a similar shape to a Gaussian but is narrower around the peak with longer tails.…”

mentioning

confidence: 99%

Auto‐encoder neural network incorporating x‐ray fluorescence fundamental parameters with machine learning

Dirks

Poole

2023

X-Ray Spectrometry

View full text Add to dashboard Cite

We consider energy‐dispersive x‐ray fluorescence (XRF) applications where the fundamental parameters method is impractical such as when instrument parameters are unavailable. For example, on a mining shovel or conveyor belt, rocks are constantly moving (leading to varying angles of incidence and distances) and there may be other factors not accounted for (like dust). Neural networks do not require instrument and fundamental parameters but training neural networks requires XRF spectra labeled with elemental composition, which is often limited because of its expense. We develop a neural network model that learns from limited labeled data and also benefits from domain knowledge by learning to invert a forward model. The forward model uses transition energies and probabilities of all elements and parameterized distributions to approximate other fundamental and instrument parameters. We evaluate the model and baseline models on a rock dataset from a lithium mineral exploration project. Our model works particularly well for some low‐Z elements (Li, Mg, Al, and K) as well as some high‐Z elements (Sn and Pb) despite these elements being outside the suitable range for common spectrometers to directly measure, likely owing to the ability of neural networks to learn correlations and nonlinear relationships.

show abstract

“…Another method for the evaluation of the spectral data involves the use of artificial neural networks (ANN), which can be used to model a nonlinear correlation of the spectra with the variables [13]. ANN models generally contain two or more layers, each having a number of neurons.…”

Section: Introductionmentioning

confidence: 99%

Application of Two-Dimensional Fluorescence Spectroscopy for the On-Line Monitoring of Teff-Based Substrate Fermentation Inoculated with Certain Probiotic Bacteria

Alemneh

Emire

Jekle

et al. 2022

Foods

View full text Add to dashboard Cite

There is increasing demand for cereal-based probiotic fermented beverages as an alternative to dairy-based products due to their limitations. However, analyzing and monitoring the fermentation process is usually time consuming, costly, and labor intensive. This research therefore aims to apply two-dimensional (2D)-fluorescence spectroscopy coupled with partial least-squares regression (PLSR) and artificial neural networks (ANN) for the on-line quantitative analysis of cell growth and concentrations of lactic acid and glucose during the fermentation of a teff-based substrate. This substrate was inoculated with mixed strains of Lactiplantibacillus plantarum A6 (LPA6) and Lacticaseibacillus rhamnosus GG (LCGG). The fermentation was performed under two different conditions: condition 1 (7 g/100 mL substrate inoculated with 6 log cfu/mL) and condition 2 (4 g/100 mL substrate inoculated with 6 log cfu/mL). For the prediction of LPA6 and LCGG cell growth, the relative root mean square error of prediction (pRMSEP) was measured between 2.5 and 4.5%. The highest pRMSEP (4.5%) was observed for the prediction of LPA6 cell growth under condition 2 using ANN, but the lowest pRMSEP (2.5%) was observed for the prediction of LCGG cell growth under condition 1 with ANN. A slightly more accurate prediction was found with ANN under condition 1. However, under condition 2, a superior prediction was observed with PLSR as compared to ANN. Moreover, for the prediction of lactic acid concentration, the observed values of pRMSEP were 7.6 and 7.7% using PLSR and ANN, respectively. The highest error rates of 13 and 14% were observed for the prediction of glucose concentration using PLSR and ANN, respectively. Most of the predicted values had a coefficient of determination (R2) of more than 0.85. In conclusion, a 2D-fluorescence spectroscopy combined with PLSR and ANN can be used to accurately monitor LPA6 and LCGG cell counts and lactic acid concentration in the fermentation process of a teff-based substrate. The prediction of glucose concentration, however, showed a rather high error rate.

show abstract

Application of artificial neural networks to X‐ray fluorescence spectrum analysis

Cited by 12 publications

References 95 publications

Optical imaging spectroscopy coupled with machine learning for detecting heavy metal of plants: A review

Optical imaging spectroscopy coupled with machine learning for detecting heavy metal of plants: A review

Auto‐encoder neural network incorporating x‐ray fluorescence fundamental parameters with machine learning

Application of Two-Dimensional Fluorescence Spectroscopy for the On-Line Monitoring of Teff-Based Substrate Fermentation Inoculated with Certain Probiotic Bacteria

Contact Info

Product

Resources

About