Robust boosting neural networks with random weights for multivariate calibration of complex samples.

Neural networks with random weights (NNRW) has been used for regression due to its excellent performance. However, NNRW is sensitive to outliers and unstable to some extent in dealing with the real-world complex samples. To overcome these drawbacks, a new method called robust boosting NNRW (RBNNRW) is proposed by integrating a robust version of boosting with NNRW. The method builds a large number of NNRW sub-models sequentially by robustly reweighted sampling from the original training set and then aggregates these predictions by weighted median. The performance of RBNNRW is tested with three spectral datasets of wheat, light gas oil and diesel fuel samples. As comparisons to RBNNRW, the conventional PLS, NNRW and boosting NNRW (BNNRW) have also been investigated. The results demonstrate that the introduction of robust boosting greatly enhances the stability and accuracy of NNRW. Moreover, RBNNRW is superior to BNNRW particularly when outliers exist.

[1]  Qi Zhang,et al.  Improvement on enhanced Monte-Carlo outlier detection method , 2016 .

[2]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[3]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[4]  Xueguang Shao,et al.  Variable space boosting partial least squares for multivariate calibration of near-infrared spectroscopy ☆ , 2016 .

[5]  Yanjie Li,et al.  Rapid classification of Chinese quince (Chaenomeles speciosa Nakai) fruit provenance by near-infrared spectroscopy and multivariate calibration , 2016, Analytical and Bioanalytical Chemistry.

[6]  Ke Wang,et al.  Bagging for robust non-linear multivariate calibration of spectroscopy , 2011 .

[7]  Min Liu,et al.  A new robust ELM method based on a Bayesian framework with heavy-tailed distribution and weighted likelihood function , 2015, Neurocomputing.

[8]  Li Yan-kun,et al.  Determination of diesel cetane number by consensus modeling based on uninformative variable elimination , 2012 .

[9]  J. Castillo,et al.  Detection, characterization and quantification of inorganic engineered nanomaterials: A review of techniques and methodological approaches for the analysis of complex samples. , 2016, Analytica chimica acta.

[10]  Jiewen Zhao,et al.  Intelligent sensing sensory quality of Chinese rice wine using near infrared spectroscopy and nonlinear tools. , 2016, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[11]  Olivier D. Faugeras,et al.  A Constructive Mean-Field Analysis of Multi-Population Neural Networks with Random Synaptic Weights and Stochastic Inputs , 2008, Front. Comput. Neurosci..

[12]  Shi-Miao Tan,et al.  Quantitative analysis of tea using ytterbium‐based internal standard near‐infrared spectroscopy coupled with boosting least‐squares support vector regression , 2013 .

[13]  Xueguang Shao,et al.  Detecting influential observations by cluster analysis and Monte Carlo cross-validation. , 2010, The Analyst.

[14]  L. Buydens,et al.  Comparing support vector machines to PLS for spectral regression applications , 2004 .

[15]  André van Schaik,et al.  A comparison of extreme learning machines and back-propagation trained feed-forward networks processing the mnist database , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[16]  Dianhui Wang,et al.  A probabilistic learning algorithm for robust modeling using neural networks with random weights , 2015, Inf. Sci..

[17]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[18]  Olusola O. Soyemi,et al.  Multivariate Analysis of Near-Infrared Spectra Using the G-Programming Language , 2000, J. Chem. Inf. Comput. Sci..

[19]  Werner A. Stahel,et al.  Robust Statistics: The Approach Based on Influence Functions , 1987 .

[20]  Dong-Sheng Cao,et al.  The boosting: A new idea of building models , 2010 .

[21]  Xihui Bian,et al.  High and low frequency unfolded partial least squares regression based on empirical mode decomposition for quantitative analysis of fuel oil samples. , 2016, Analytica chimica acta.

[22]  D L Massart,et al.  Boosting partial least squares. , 2005, Analytical chemistry.

[23]  Peter D. Wentzell,et al.  Estimation of hydrocarbon types in light gas oils and diesel fuels by ultraviolet absorption spectroscopy and multivariate calibration , 1999 .

[24]  Menglong Li,et al.  Determination of nicotine in tobacco samples by near-infrared spectroscopy and boosting partial least squares , 2010 .

[25]  Jian-hui Jiang,et al.  QSAR study of angiotensin II antagonists using robust boosting partial least squares regression. , 2007, Analytica chimica acta.

[26]  Robert P. W. Duin,et al.  Feedforward neural networks with random weights , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[27]  C. Roychaudhuri,et al.  Quantitative differentiation of multiple virus in blood using nanoporous silicon oxide immunosensor and artificial neural network. , 2017, Biosensors & bioelectronics.

[28]  Wei Liu,et al.  Subagging for the improvement of predictive stability of extreme learning machine for spectral quantitative analysis of complex samples , 2017 .

[29]  Yan-Lin He,et al.  Soft sensor development for the key variables of complex chemical processes using a novel robust bagging nonlinear model integrating improved extreme learning machine with partial least square , 2016 .

[30]  Daniel Peña,et al.  A robust partial least squares regression method with applications , 2009 .

[31]  Fan Zhang,et al.  Tensorial Biometric Signal Recognition Based on Feed Forward Neural Networks with Random Weights , 2015, BIC-TA.

[32]  Guilherme De A. Barreto,et al.  A Robust Extreme Learning Machine for pattern classification with outliers , 2016, Neurocomputing.

[33]  Xihui Bian,et al.  A boosting extreme learning machine for near-infrared spectral quantitative analysis of diesel fuel and edible blend oil samples , 2017 .

[34]  W. Cai,et al.  An improved boosting partial least squares method for near-infrared spectroscopic quantitative analysis. , 2010, Analytica chimica acta.

[35]  Jian Jiao,et al.  A Robust Boosting Regression Tree with Applications in Quantitative Structure-Activity Relationship Studies of Organic Compounds , 2011, J. Chem. Inf. Model..

[36]  Dong-Sheng Cao,et al.  The model adaptive space shrinkage (MASS) approach: a new method for simultaneous variable selection and outlier detection based on model population analysis. , 2016, The Analyst.

[37]  Minxia Luo,et al.  Outlier-robust extreme learning machine for regression problems , 2015, Neurocomputing.

[38]  Wei-Qi Lin,et al.  Boosting support vector regression in QSAR studies of bioactivities of chemical compounds. , 2006, European journal of pharmaceutical sciences : official journal of the European Federation for Pharmaceutical Sciences.

[39]  D. Rutledge,et al.  Multi-block data analysis using ComDim for the evaluation of complex samples: Characterization of edible oils. , 2017, Analytica chimica acta.

[40]  Xueguang Shao,et al.  Multivariate calibration methods in near infrared spectroscopic analysis , 2010 .

[41]  Xueguang Shao,et al.  A consensus least squares support vector regression (LS-SVR) for analysis of near-infrared spectra of plant samples. , 2007, Talanta.

[42]  Wang Jiangjiang,et al.  Spectral quantitative analysis of complex samples based on the extreme learning machine , 2016 .

[43]  Yi-Zeng Liang,et al.  Monte Carlo cross validation , 2001 .