An artificial neural network model for predicting flavour intensity in blackcurrant concentrates

Abstract Artificial neural networks (ANNs)—machine learning acquiring knowledge in training and using deduced relationships to predict responses—were studied to rationalise concentrate use in fruit drinks production. Sets of ANNs were developed for predicting flavour intensity in blackcurrant concentrates from gas chromatographic data on flavour components (37) in 133 sorbent extracts from blackcurrant concentrates varying in season, geographical origin and processing technology. Sensory data was collected using ratio scaling on flavour intensities in drinks from concentrates. Relationships between chromatographic and sensory data for concentrates of three seasons (1989, 1990 and 1992) were modelled by ANNs with back propagation using principal component regression scores as input. Predictions were compared with a global model from random concentrates from all three seasons. In predicting overall flavour intensity, ANN models were better fitted than partial least square regression. Ability of artificial neural networks to simulate non-linear relationships observed in human perceptions could explain such improvements.

[1]  J. H Maindonald,et al.  New approaches to using scientific data - statistics, data mining and related technologies in research and research training , 1998 .

[2]  Dogan Yuksel,et al.  Using artificial neural networks to develop prediction models for sensory-instrumental relationships; an overview , 1997 .

[3]  J. Piggott,et al.  QUANTIFYING FLAVOR CHARACTER IN BLACKCURRANT DRINKS FROM FRUIT CONCENTRATES , 2001 .

[4]  Peter C. Cheeseman,et al.  Bayesian Classification (AutoClass): Theory and Results , 1996, Advances in Knowledge Discovery and Data Mining.

[5]  Harry E. Nursten,et al.  Progress in flavour research , 1979 .

[6]  Bruce R. Kowalski,et al.  Nonlinear Multivariate Calibration Methods in Analytical Chemistry , 1993 .

[7]  Sundaram Gunasekaran,et al.  Food quality prediction with neural networks , 1998 .

[8]  H. Macfie,et al.  DESIGNS TO BALANCE THE EFFECT OF ORDER OF PRESENTATION AND FIRST-ORDER CARRY-OVER EFFECTS IN HALL TESTS , 1989 .

[9]  J. Piggott.  Statistical procedures in food research , 1986 .

[10]  E. V. Sydow,et al.  A QUALITY COMPARISON OF FROZEN AND REFRIGERATED COOKED SLICED BEEF.: 2. Relationships between Gas Chromatographic Data and Flavor Scores , 1972 .

[11]  M. Lipp.  Determination of the adulteration of butter fat by its triglyceride composition obtained by GC. A comparison of the suitability of PLS and neural networks , 1996 .

[12]  R. Shepherd,et al.  Handbook of the psychophysiology of human eating , 1989 .

[13]  James H. Dwinnell,et al.  Principles of aerodynamics , 1949 .

[14]  H. H. Thodberg,et al.  Optimal minimal neural interpretation of spectra , 1992 .

[15]  J. Piggott,et al.  Sources of variations in aroma-active volatiles, or flavour components, of blackcurrant concentrates , 1999 .

[16]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[17]  Brian D. Ripley,et al.  Pattern Recognition and Neural Networks , 1996 .

[18]  Harry T. Lawless,et al.  Sensory science theory and applications in foods , 1991 .

[19]  G. Birch,et al.  Sensory Properties of Foods , 1977 .

[20]  G. E. Arteaga,et al.  Predicting Protein Functionality with Artificial Neural Networks: Foaming and Emulsifying Properties , 1993 .

[21]  Svante Wold,et al.  Preference of cauliflower related to sensory descriptive variables by partial least squares (PLS) regression , 1983 .

[22]  D. M. Titterington,et al.  Neural Networks: A Review from a Statistical Perspective , 1994 .

[23]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[24]  David J. Spiegelhalter,et al.  Machine Learning, Neural and Statistical Classification , 2009 .

[25]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery: An Overview , 1996, Advances in Knowledge Discovery and Data Mining.

[26]  M. Lipp.  Comparison of PLS, PCR and MLR for the quantitative determination of foreign oils and fats in butter fats of several European countries by their triglyceride composition , 1996 .

[27]  James A. Anderson,et al.  Neurocomputing: Foundations of Research , 1988 .

[28]  A. A. Williams.  Flavour quality — Understanding the relationship between sensory responses and chemical stimuli. What are we trying to do? The data, approaches and problems , 1994 .

[29]  Rolf Isermann,et al.  Adaptive control systems , 1991 .

[30]  G. Smith,et al.  Food research and data analysis , 1983 .

[31]  A. A. Williams,et al.  Relating chemical/physical and sensory data in food acceptance studies , 1988 .

[32]  Wray L. Buntine,et al.  Graphical models for discovering knowledge , 1996, KDD 1996.

[33]  John R. Piggott,et al.  Extraction of aroma components to quantify overall sensory character in a processed blackcurrant (Ribes nigrum L.) concentrate , 2002 .

[34]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[35]  L. Bochereau,et al.  Sensory-instrumental correlations by combining data analysis and neural network techniques , 1993 .