Development of a partial least squares-artificial neural network (PLS-ANN) hybrid model for the prediction of consumer liking scores of ready-to-drink green tea beverages.

In order to develop products that would be preferred by consumers, the effects of the chemical compositions of ready-to-drink green tea beverages on consumer liking were studied through regression analyses. Green tea model systems were prepared by dosing solutions of 0.1% green tea extract with differing concentrations of eight flavour keys deemed to be important for green tea aroma and taste, based on a D-optimal experimental design, before undergoing commercial sterilisation. Sensory evaluation of the green tea model system was carried out using an untrained consumer panel to obtain hedonic liking scores of the samples. Regression models were subsequently trained to objectively predict the consumer liking scores of the green tea model systems. A linear partial least squares (PLS) regression model was developed to describe the effects of the eight flavour keys on consumer liking, with a coefficient of determination (R2) of 0.733, and a root-mean-square error (RMSE) of 3.53%. The PLS model was further augmented with an artificial neural network (ANN) to establish a PLS-ANN hybrid model. The established hybrid model was found to give a better prediction of consumer liking scores, based on its R2 (0.875) and RMSE (2.41%).

[1]  J. Durand,et al.  Local polynomial additive regression through PLS and splines: PLSS , 2001 .

[2]  Robert Hurling,et al.  Eating with your eyes: effect of appearance on expectations of liking , 2003, Appetite.

[3]  George-Christopher Vosniakos,et al.  Optimizing feedforward artificial neural network architecture , 2007, Eng. Appl. Artif. Intell..

[4]  J. E. Paton,et al.  Prediction of consumer liking from trained sensory panel information: Evaluation of neural networks , 2007 .

[5]  H. Martens,et al.  Modified Jack-knife estimation of parameter uncertainty in bilinear modelling by partial least squares regression (PLSR) , 2000 .

[6]  R. Sabatier,et al.  Comparison between linear and nonlinear PLS methods to explain overall liking from sensory characteristics , 1997 .

[7]  Soh-Min Lee,et al.  Age and gender differences in the influence of extrinsic product information on acceptability for RTD green tea beverages. , 2016, Journal of the science of food and agriculture.

[8]  Mohd Azlan Hussain,et al.  Prediction of pores formation (porosity) in foods during drying: generic models by the use of hybrid neural network , 2002 .

[9]  H. Shiratsuchi,et al.  Comparison of Volatile Compounds among Different Grades of Green Tea and Their Relations to Odor Attributes , 1995 .

[10]  Mehdi Khashei,et al.  A novel hybrid classification model of artificial neural networks and multiple linear regression models , 2012, Expert Syst. Appl..

[11]  Kunbo Wang,et al.  Analysis of chemical components in green tea in relation with perceived quality, a case study with Longjing teas , 2009 .

[12]  E. Fukusaki,et al.  Predication of Japanese green tea (Sen-cha) ranking by volatile profiling using gas chromatography mass spectrometry and multivariate analysis. , 2011, Journal of bioscience and bioengineering.

[13]  Federico Marini,et al.  Artificial neural networks in foodstuff analyses: Trends and perspectives A review. , 2009, Analytica chimica acta.

[14]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[15]  S. D. Jong.  SIMPLS: an alternative approach to partial least squares regression , 1993 .

[16]  Hajime Nagai,et al.  Development of Food Kansei Model and Its Application for Designing Tastes and Flavors of Green Tea Beverage , 2004 .

[17]  Elaine B. Martin,et al.  Box–Tidwell transformation based partial least squares regression , 2001 .

[18]  Hak-Keung Lam,et al.  Tuning of the structure and parameters of a neural network using an improved genetic algorithm , 2003, IEEE Trans. Neural Networks.

[19]  R. Lombardo.  The analysis of sensory and chemical–physical variables via multivariate additive PLS splines , 2011 .

[20]  Nantawan Therdthai,et al.  HYBRID NEURAL MODELING OF THE ELECTRICAL CONDUCTIVITY PROPERTY OF RECOMBINED MILK , 2002 .

[21]  Fang Liu,et al.  Analysis of chemical components in oolong tea in relation to perceived quality. , 2010 .

[22]  T. J. Shankar,et al.  Optimization of Extrusion Process Variables Using a Genetic Algorithm , 2004 .

[23]  Ya-nan Guo,et al.  Volatile profile analysis and quality prediction of Longjing tea (Camellia sinensis) by HS-SPME/GC-MS , 2012, Journal of Zhejiang University SCIENCE B.

[24]  Peigen Yu,et al.  Identifying key non-volatile compounds in ready-to-drink green tea and their impact on taste profile. , 2014, Food chemistry.

[25]  Lena Ekelund,et al.  Credence and the effect on consumer liking of food – A review , 2014 .

[26]  Athakorn Kengpol,et al.  An Assessment of Customer Contentment for Ready-to-Drink Tea Flavor Notes Using Artificial Neural Networks , 2015 .

[27]  M. S. Butt,et al.  Green Tea: Nature's Defense against Malignancies , 2009, Critical reviews in food science and nutrition.