Merge pull request #189 from chhoumann/related-works-ann

[KB-278] Add paper about ANN in related works

report_thesis/src/references.bib

@@ -617,4 +617,18 @@ @book{burkovHundredpageMachineLearning2023
   annotation = {OCLC: 1417057084}
 }
 
-
+@article{el_haddad_ann_2013,
+	title = {Artificial neural network for on-site quantitative analysis of soils using laser induced breakdown spectroscopy},
+	volume = {79-80},
+	issn = {0584-8547},
+	url = {https://www.sciencedirect.com/science/article/pii/S0584854712003679},
+	doi = {10.1016/j.sab.2012.11.007},
+	abstract = {Nowadays, due to environmental concerns, fast on-site quantitative analyses of soils are required. Laser induced breakdown spectroscopy is a serious candidate to address this challenge and is especially well suited for multi-elemental analysis of heavy metals. However, saturation and matrix effects prevent from a simple treatment of the LIBS data, namely through a regular calibration curve. This paper details the limits of this approach and consequently emphasizes the advantage of using artificial neural networks well suited for non-linear and multi-variate calibration. This advanced method of data analysis is evaluated in the case of real soil samples and on-site LIBS measurements. The selection of the LIBS data as input data of the network is particularly detailed and finally, resulting errors of prediction lower than 20\% for aluminum, calcium, copper and iron demonstrate the good efficiency of the artificial neural networks for on-site quantitative LIBS of soils.},
+	urldate = {2024-06-04},
+	journal = {Spectrochimica Acta Part B: Atomic Spectroscopy},
+	author = {El Haddad, J. and Villot-Kadri, M. and Ismaël, A. and Gallou, G. and Michel, K. and Bruyère, D. and Laperche, V. and Canioni, L. and Bousquet, B.},
+	month = jan,
+	year = {2013},
+	keywords = {Artificial neural network, Laser-induced breakdown spectroscopy (LIBS), Quantitative analysis, Soil},
+	pages = {51--57},
+}

report_thesis/src/sections/related_work.tex

@@ -12,6 +12,10 @@ \subsection{Machine Learning Models in LIBS Analysis}
 They demonstrated that blending different models, such as \gls{gbr} and \gls{pls} for \ce{SiO2}, could improve prediction accuracy.
 Their study serves as a benchmark for model performance on LIBS spectra and offers insights into model selection for similar datasets.
 
+\citet{el_haddad_ann_2013} explored the application of \gls{ann} for quantitative analysis of soil samples using \gls{libs}, employing a three-layer perceptron \gls{ann} architecture to address matrix effects and nonlinearities.
+They demonstrated that \gls{ann} is efficient for predicting the concentrations of \ce{Al}, \ce{Ca}, \ce{Cu}, and \ce{Fe}.
+Incorporating additional spectral lines from other chemical elements, thereby increasing the amount of data input to the model, was also shown to significantly improve predictive accuracy.
+
 \citet{yangConvolutionalNeuralNetwork2022} demonstrated the effectiveness of a deep \gls{cnn} for classifying geochemical samples using \gls{libs} spectra collected at varying distances.
 Their model outperformed traditional machine learning approaches, emphasizing the potential of \gls{cnn}s for geochemical sample identification in planetary exploration missions like China's Tianwen-1.