Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

Abstract

<p>Predictive models is crucial in near-infrared (NIR) spectroscopic analysis. Partial least square - artificial neural network (PLS-ANN) is a hybrid method that may improve the performance of prediction in NIR spectroscopic analysis. This study investigates the advantage of PLS-ANN over the well-known modelling in spectroscopy analysis that is partial least square (PLS) and artificial neural network (ANN). The results show that ANN that coupled with first order SG derivatives achieved the best prediction with root mean square error of prediction (RMSEP) of 0.3517 gd/L and coefficient of determination ( ) of 0.9849 followed by PLS-ANN with RMSEP of 0.4368 gd/L and of 0.9787, and PLS with RMSEP of 0.4669 gd/L and of 0.9727. This suggests that the spectrum information may unable to be totally represented by the first few latent variables of PLS and a nonlinear model is crucial to model these nonlinear information in NIR spectroscopic analysis.</p>

Comparison study between NPWM and NSVPWM strategy in FSMC control of stator reactive and active powers control of a DFIG-based wind turbine system

“…Recent years, ANN controller has found many applications such as control AC machines. ANN as one of the nonlinear methods proved their superiority over linear method for making a calibration model [32]. The principle of the two-level NSVPWM technique is similar to two-level SVPWM strategy.…”

Using the extract of pomegranate peel as a natural indicator for colorimetric detection and simultaneous determination of Fe3+ and Fe2+ by partial least squares–artificial neural network

“…PLS modeling is one of the most powerful multivariate modeling methods used in the quantitative analysis. 19,38,40,41 The theory of this method is briefly explained here. This method is based on the analysis of latent variables to establish a relationship between two matrices, X and Y, including spectral and concentration information, respectively.…”

“…In order to reduce the training time of the main network, the dimensions of the input space are reduced by PLS before ANN model fitting. PLS modeling is one of the most powerful multivariate modeling methods used in the quantitative analysis 19,38,40,41 . The theory of this method is briefly explained here.…”