Artificial and Hybrid Fuzzy Linear Neural Network‐Based Estimation of Seed Oil Content of Safflower

Abstract

Keywords Safflower · Oil content · Multiple linear regression · Neural networks · Hybrid fuzzy linear neural network methods of quantitative analysis used by the NIR system are multiple linear regression (MLR), principal component regression (PCR), partial least squares (PLS), and recently artificial neural networks (ANN). The first three methods of MLR, PCR and PLS are suitable for linear analysis, while ANN has advantages when non-linearity exists in the data. Rodriguez-Nogales [2], compared PLS, PCR and MLR to find optimal prediction models for the quantification of Abstract Inexpensive and rapid methods for measurement of seed oil content by near infrared reflectance spectroscopy (NIRS) are useful for developing new oil seed cultivars. Adopting default multiple linear regression (MLR), the predictions of safflower oil content were made by 20-140 samples using a Perten Inframatic 8620 NIR spectrometer. Although the obtained interpolation results of MLR had desired accuracy, the extrapolation was extremely poor. The extrapolation determination coefficient (R 2 ) and standard error (SE) of cross validation for MLR models were 0.63-0.78 and 3.71-4.44, respectively. In order to overcome the accuracy limitation of linear MLR models, a common suggestion is to use a nonlinear artificial neural network (ANN); however, it needs a large number of data to yield significant accurate results. We developed a novel robust hybrid fuzzy linear neural (HFLN) network to capture simultaneously linear and nonlinear patterns of data with a limited number of safflower samples. Empirical extrapolation results showed that the HFLN had higher R 2 (=0.85) and lower SE (=1.83) compared to those obtained by MLR and ANN models. It is concluded that hybrid methodologies could be used to construct efficient and appropriate models for estimation of seed oil content set up on NIR system.

Artificial neural networks and multiple linear regression as potential methods for modelling body surface temperature of pig

“…Additionally, they would not be able to capture the highly non-linear and complex relations between pig's body temperature and other parameters. Unlike linear-based models, artificial neural networks (ANNs), genetic expression (GE), Bayesian classification (BC) or other non-linear models would be appropriate when non-linearity and complex relationships exist among the considered variables (Farjam et al 2014;Sabzalian et al 2014;Mansouri et al 2016;Abdipour et al 2018Abdipour et al , 2019. It has been documented by many studies that non-linear approaches such as ANNs interoperate variable relationships more accurately than other methods and it would be more capable to predict output variables compared to the linearbased methods (Khairunniza-Bejo et al 2014;Safa et al 2016;Abdipour et al 2019).…”

An efficient estimation of crop performance in sheep fescue (Festuca ovina L.) using artificial neural network and regression models

“…Artificial intelligence techniques such as artificial neural networks (ANNs), genetic expression (GE), Bayesian classification (BC), adaptive neuro-fuzzy inference system (ANFIS), and other advanced modeling methods, in opposed to previous modelling techniques such as PA and MLR, have lately gotten a lot of attention from crop researchers, particularly when the relationship among parameters may well be nonlinear 5,[13][14][15] . Artificial Neural Network (ANN) is a multi-networked (multilayer perceptron) system of logically arranged fundamental units that simulate the neuron activity in the human brain.…”

Development of New Correlation Fines Content, NSPT and CPT Using Neural Network Approach and Multilinear Regression to Support Liquefaction Hazard Analysis

“…Researchers also often rely on Bayesian classification (BC), Artificial Neural Networks (ANN), and adaptive neuro-fuzzy inference systems (ANFIS) to predict an independent parameter (Šapina, 2016). These methods are an alternative because it takes into account the non-linearity of the soil (Abdipour et al, 2018);(Farjam et al, 2014); (Mansouri et al, 2016); (Sabzalian et al, 2014). Several researchers have formulated the nonlinear approaches have a higher level of accuracy than other methods.…”