An artificial neural network is capable of predicting odour intensity

• Autorzy: Linder R , Zamelczyk-Pajewska M. , Poppl S.J. , Kosmider J.
• Języki publikacji: EN

Abstrakty

EN

For the first time, an artificial neural network (ANN) has been employed for predicting the intensity of gas mixtures comprising different odour components. Sensory assessments are necessary but they are time-consuming, harmful, and expensive. Therefore, an instrumental quantification of subjective sensory assessments is highly desired. Because of nonlinearities arising in sensory-instrumental relationships, we decided for an ANN that was trained by gas chromatographic signals of gas mixtures. The ANN could be demonstrated to classify odour intensity fairly well.

Słowa kluczowe

EN

odour intensity; artificial neural network; gas chromatographic signal; gas mixture

• Wydawca: -
• Czasopismo: Polish Journal of Environmental Studies
• Rocznik: 2005
• Tom: 14
• Numer: 4
• Opis fizyczny: p.477-481,fig.,ref.

Twórcy

autor

Linder R

• University of Lubeck, Lubeck, Germany

autor

Zamelczyk-Pajewska M.

autor

Poppl S.J.

autor

Kosmider J.

Bibliografia

• 1. LAING D. G., WILLCOX M. E. Perception of components in binary odour mixtures, Chem. Senses. 7, 249, 1983.
• 2. BERGLUND B., OLSSON M. J. A theoretical and empirical evaluation of perceptual and psychophysical models for odour-intensity interaction. Reports from the Department of Psychology, Stockholm University, no. 764, 1993.
• 3. WYSZYŃSKI B. Methods of deodorization effectiveness assessments. Doct. thesis,: Technical University of Stettin, 2001.
• 4. KOŚMIDER J., WYSZYŃSKI B., ZAMELCZYK-PAJEWSKA M. Odour of mixtures of cyclohexane and cyclohexanone. Arch. Environ. Prot. 28 (2), 29, 2002.
• 5. AMERINE M., PANGBORN R. M., ROESSLER E. B. Principles of sensors evaluation of food, Academic Press: New York, 1965.
• 6. HERSCHDOERFER S. M. Quality control in food industry. Academic Press: New-York, Vol. 1, 1967.
• 7. BARYŁKO-PIKIELNA N. An outline of sensoric analysis of food; PWN: Warszawa, 1975.
• 8. ASTM - American Society the handicap Testing and Materials, Committee E-18. Manual sensors testing methods. Philadelphia: ASTM Publ., B.
• 9. ISO 5492, Pr PN-ISO 5492. International Standard Organization: Sensors Analysis. Terminology, 1992.
• 10. EN 13725 (draft 1999). Committee Européen de Normalisation CEN - TC 264. CEN-TC 264/WG2: Air Quality - Determination of odour concentration by dynamic olfactometer.
• 11. KELLER E. P., KOUZES T. R., KANGAS J. L. Three Neural Network Based Sensor Systems for Environmental Monitoring. IEEE Electro/94 International Conference, Boston, USA, 1994.
• 12. KELLER E. P., KANGAS J. L., LIDEN H. L., HASHEM S., KOUZES T. R. Electronic noses and their applications. IEEE Northcon/Technical Applications Conference (TAC'95), Portland, USA, 1995.
• 13. ARNOLD J. W., SENTER S. D., RUSSELL B. R. Use of digital aroma technology and SPME, GC-MS to compare volatile compounds produced by bacteria isolated from processed poultry. J. Sci. Food Agric, 78 (3), 343, 1998.
• 14. KAIPAINEN A., YLISUUTARI S., LUCAS Q., MOY L. A new approach to odor detection. Comparison of thermal desorption GC-MS and electronic nose. Two techniques for the analysis of headspace aroma profiles of sugar. Int. Sugar J. 99 (1184), 403, 1997.
• 15. BOCCORH R. K., PATERSON A. An artificial network model for predicting flavour intensity in blackcurrant concentrates. Food Qual. Pref. 13, 117, 2002.
• 16. LINDER R.. PÖPPL S. J. ACMD: A Practical Tool for Automatic Neural Net Based Learning. In Medical Data Analysis. Proceedings of the Second International Symposium on Medical Data Analysis (ISMDA); Crespo, J., Maojo, V., Martin, F., Eds.; Springer: Berlin; LNCS 2199, pp168-173, 2001.
• 17. GEDDES C. C., FOX J. G., ALLISON M. E. M., BOULTON-JONES J. M., SIMPSON K. An artificial neural network can select patients at high risk of developing progressive IgA nephropathy more accurately than experienced nephrologists. Nephrol. Dial. Transplant. 13, 67, 1998.
• 18. ANAND R., MEHROTRA K., MOHAN C. K., RANKA S. Efficient Classification for Multiclass Problems Using Modular Neural Networks. IEEE Trans. on Neural Networks. 6 (1), 117, 1995.
• 19. LINDER R., WIRTZ S., PÖPPL S. J. Speeding up Backpropagation Learning by the APROP Algorithm. Proc. of the Second International ICSC Symposium on Neural Computation (NC2000); ICSC Academic Press: Millet, Alberta, Canada, pp. 122-128, 2000.
• 20. RUMELHART D. E., HINTON G. E., WILLIAMS R. J. Learning Representations by Back-Propagating Errors. Nature, 323, 533, 1986.
• 21. BISHOP C. M. Neural Networks for Pattern Recognition. Clarendon Press: Oxford, 1995.
• 22. AMARI S., MURATA N., MÜLLER K., FINKE M., YANG H. H. Asymptotic statistical theory of overtraining and cross-validation. IEEE Trans. On Neural Networks, 8 (5), 985, 1997.
• 23. PRECHELT L. Automatic early stopping using cross validation: quantifying the criteria. Neural Networks, 11, 761, 1998.
• 24. TU J. V. Advantages and Disadvantages of Using Artificial Neural Networks versus Logistic Regression for Predicting Medical Outcomes. J. Clin. Epidemiol. 49 (11), 1225, 1996.
• 25. EN 1622 (1997). Committee Européen de Normalisation CEN - TC 230: Water analysis - Determination of the threshold odour number (TON) and threshold flavour number (TFN).
• 26. EN 13725 (2003) Air Quality - Determination of odour concentration by dynamic olfactometer.
• 27. FECHNER G. T.: Elemente der Psychophysik. Leipzig, 1860.
• 28. STEVENS S. S. Psychophysics. Introduction to its perceptual, neural and social prospects. John Wiley & Sons: New York, 1975.
• 29. ZIMBARDO P. G., RUCH F. L. Psychology and Life. Scott, Foresman & Company: Illinois, 1977.
• 30. BERGLUND B., OLSSON M. J. A theoretical and empirical evaluation of perceptual and psychophysical models for odor-intensity interaction, Reports from the Department of Psychology, Stockholm University, p 764, 1993.
• 31. KOŚMIDER J., WYSZYŃSKI B. Relationship between odour intensity and odorant concentration: logarithmic or power equation, Arch. Environ. Prot., 1, 29, 2002.