Open AccessCoupling Backpropagation Neural Network and AdaBoost Algorithm for Quantitative Analysis of Nickel via Laser-Induced Breakdown Spectroscopy
Author(s) -
Edward Harefa,
Weidong Zhou
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2049/1/012017
Subject(s) - laser induced breakdown spectroscopy , calibration , adaboost , artificial intelligence , algorithm , backpropagation , mean squared error , correlation coefficient , artificial neural network , materials science , analytical chemistry (journal) , machine learning , spectroscopy , computer science , mathematics , chemistry , support vector machine , physics , statistics , chromatography , quantum mechanics
A wide area of cropland or soil might well be contaminated with heavy metals, contaminating agricultural goods and posing a risk to human health. As a result, it is required to evaluate the concentration of heavy metals in soil. The combination between laser-induced breakdown spectroscopy (LIBS) and multivariate chemometrics methods was employed to determine heavy metal Ni concentration in twelve soil samples. The comparison between univariate calibration curve, traditional backpropagation neural network (BPNN), and hybrid BPNN-AdaBoost was presented. The result revealed that BPNN-AdaBoost outperformed other models with the coefficient determination calibration ( R G 2 ) , coefficient determination prediction ( R P 2 ) , root mean square error calibration (RMSEC), root mean square error prediction (RMSEP) are 0.985, 0.977, 2.04, 3.18, respectively. This study indicates that BPNN-AdaBoost can be adopted as a reliable chemometric technique to enhance the quantitative analysis of heavy metals based on LIBS.