Pre-processing and pattern recognition methods for artificial olfaction systems: a review

• Autorzy: Di Natale, C. , Martinelli, E. , D'Amico, A.

Warianty tytułu

PL

Przegląd metod obróbki wstępnej i rozpoznawania obrazów w sztucznych systemach olfakcyjnych

• Języki publikacji: EN

Abstrakty

EN

Data analysis is a fundamental part of artificial olfaction systems. Nonetheless, while electrical and mechanical components of electronic noses are deeply investigated and optimised for the specific applications, data analysis is sometimes performed without any critical understanding about hypotheses on which it is founded. Several methodologies were imported into this field and utilised to correlate electronic nose data to the information required for classification purposes. Chemometrics and neural networks are the sources of the most popular methods currently in use. In this paper some of the most used methodologies of data analysis are reviewed and their use for electronic nose data is discussed. Although the discussion is given considering chemical sensor arrays, the conclusions are generic and valid for a broader range of sensor systems.

PL

Analiza danych stanowi podstawową część sztucznych systemów olfakcyjnych. Pomimo tego, podczas gdy elementy elektryczne i mechaniczne nosów elektronicznych są badane dogłębnie i optymalizowane dla potrzeb konkretnych zastosowań, analizę danych przeprowadza się niekiedy bez jakiegokolwiek krytycznego rozpatrywania hipotez, na których jest oparta. W badaniach tej dziedziny wiedzy zastosowano kilka metodologii dla skorelowania danych o nosie elektronicznym z informacją potrzebną dla celów klasyfikacji. Chemometria i sieci neuronowe stanowią źródło najbardziej popularnych metod będących obecnie w użyciu. W niniejszej pracy dokonano przeglądu metod najczęściej stosowanych w analizie danych i omawia się ich stosowanie do danych z nosów elektronicznych. Chociaż omówienie dotyczy zespołów czujników chemicznych, wnioski są ogólne i słuszne dla szerszego zakresu systemów czujników.

Słowa kluczowe

PL

systemy olfakcyjne; nosy elektroniczne; czujniki

EN

olfaction systems; electronic noses; sensors

• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2005
• Tom: Vol. 12, nr 1
• Strony: 3-25
• Opis fizyczny: Bibliogr. 45 poz., rys., tab., wykr.

Twórcy

autor

Di Natale, C.

• University of Rome “Tor Vergata” Department of Electronic Engineering, Roma, Italy
• CNR-IMM, Sezione di Roma, Roma, Italy

autor

Martinelli, E.

• University of Rome “Tor Vergata” Department of Electronic Engineering, Roma, Italy

autor

D'Amico, A.

• University of Rome “Tor Vergata” Department of Electronic Engineering, Roma, Italy
• CNR-IMM, Sezione di Roma, Roma, Italy

Bibliografia

• 1. Persaud K., Dodd G.: Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose. Nature, vol. 299, 1982, pp. 352-355.
• 2. Pearce T.: Computational parallels between the biological olfactory pathway and its analogue the electronic nose. Biosystems vol. 41, 1997, pp. 43-67.
• 3. Di Natale C., Davide F., D’Amico A.: Pattern recognition in gas sensing. Sensors and Actuators B vol. 23, 1995, pp. 111-118.
• 4. Kowalski B.R., Wold S.: In Handbook of statistics vol. 2, P.R. Krishnaiah and L.N. Kanal eds., North Holland Publ., Amsterdam, The Netherlands, 1982, pp. 673- 697.
• 5. Hierlemann A., Schweizer-Berberich M., Weimar U., Pfau A., Göpel W.: Pattern recognition and multicomponent analysis. Sensors update vol. 2, W. Göpel, J. Hesse, H. Baltes (eds.), VCH, Weinheim, Germany, 1995.
• 6. Hines E.L., Llobet E., Gardner J.W.: Electronic noses: a review of signal processing techniques. IEE Proc. Circuits Devices Syst. vol. 146, 1999, pp. 297-310.
• 7. Jurs P.C., Bakken G.A., McClelland H.E.: Computational methods for the analysis of chemical sensor array data from volatile analytes. Chemical Review 2000 100 pp. 2649-2678.
• 8. Eklöv T., Mårtensson P., Lundström I.: Selection of variables for interpreting multivariate gas sensor data. Analytica Chimica Acta vol. 381, 1997, pp. 221-232.
• 9. Martinelli E., Falconi C., D’Amico A., Di Natale C.: Feature extraction chemical sensor phase space. Sensors and Actuators B vol. 95, 2003, pp. 132-139.
• 10. Martinelli E., Pennazza G., Di Natale C., D’Amico A.: Chemical sensors clustering with the dynamic moments approach. Sensors And Actuators B vol. 101, 2004, pp. 346-352.
• 11. Di Natale C., Paolesse R., Macagnano A., Mantini A., D’Amico A., Legin A., Lvova L., Rudnitskaya A., Vlasov Y.: Electronic nose and electronic tongue integration for improved classification of clinical and food samples. Sensors and Actuators B vol. 64, 2000, pp. 15-21.
• 12. Horner G., Hierold C.: Gas analysis by partial model building. Sensors and Actuators B, vol. 2, 1990, pp. 173-184.
• 13. Di Natale C., Paolesse R., Macagnano A., Troitsky V.I., Berzina T.S., D’Amico A.: Pattern recognition approach to the study of the interactions between metalloporphyrin Langmuir-Blodgett films and volatile organic compounds. Analytica Chimica Acta vol. 384, 1999, pp. 249-259.
• 14. Fukunaga K.: Introduction to statistical pattern recognition. Academic Press, New York, USA. 1992.
• 15. Massart D.L., Vandegiste B.G., Deming S.N., Michotte Y., Kaufmann L.; Data handling in science and technology. Chemometrics: a textbook, vol. 2, Elsevier. Amsterdam, The Netherlands. 1988.
• 16. Grossberg R., Procaccia I.: Measuring the strangeness of strange attractors. Physica D, vol. 9, 1983, pp.189-208.
• 17. Oja E.: Principal components, minor components, and linear networks. Neural Networks vol. 5, 1992, pp. 927-935.
• 18. Cardoso J.F.: Blind signal separation: statistical principles. Proc. of IEEE, vol .90, 1998, pp. 2009-2025.
• 19. Di Natale C., Martinelli E., D’Amico A.: Counteraction of environmental disturbances of electronic nose data by Independent Component Analysis. Sensors and Actuators B vol. 82, 2002, pp. 158-165.
• 20. Kvalheim O.M., Oygard K., Grahl-Nielsen O.: SIMCA multivariate data analysis of blue mussel components in environmental pollution studies. Analytica Chimica Acta vol. 150, 1983, pp. 145-152.
• 21. Hastie T., W. Stuetzle: Principal curves. Journal of the American Statistical Association, vol. 84, 1989, pp. 502-516.
• 22. Pardo M., Sberveglieri G., Gardini S., Dalcanale E.: A hierarchical classification scheme for an Electronic Nose, Sensors and Actuators B vol. 69, 2000, pp. 359-365.
• 23. Kramer H., Matthewes M.: A linear coding for transmitting a set of correlated signals. IRE Trans. Inf. Theory, vol. IT-2,1956, pp.41-46.
• 24. Kohonen T.: Self Organising Map. 1995 Springer Verlag, Berlin Germany.
• 25. Davide F., Di Natale C., D’Amico A.: Self organizing multisensor system for odour classification, internal catergorization, adaptation, and drift rejection. Sensors and Actuators B, vol. 18, 1994, pp. 244 4.
• 26. Di Natale C., Davide F., D’Amico A., Hierleman A., Schweizer M., Mitrovics J., Weimar U., Göpel W.: A composed neural network for the recognition of gas mixtures. Sensors and Actuators B, vol. 25, 1995, pp. 808.
• 27. Kraus G., Hierleman A., Gauglitz G., Göpel W.: Analysis of complex gas mixtures by pattern recognition with polymer base quartz m icrobalance sensor arrays. Technical Digest of Transducers ‘95 Conference, Stockholm Sweden. 25-29 Jun. 1995, pp. 675-678.
• 28. Kain A.K. Mao J.: Artificial neural network for nonlinear projection of multivariate data. Proc. Of 11-th Int. Conf. On Pattern Recognition, 1992 IEEE Comp. Soc. Press, Los Alamitos, CA, USA, pp. 41.
• 29. Di Natale C., Macagnano A., D’Amico A., Davide F.: Electronic nose modeling and data analysis by self organizing neural networks. Measurement Science and Technology. Vol. 8, 1997, pp. 1-8.
• 30. Di Natale C., Brunink J.A.J., Bungaro F., Davide F., D’Amico A., Paolesse R., Boschi T., Faccio M., Ferri G.: Recognition of fish storage time by a metalloporphyrins coated QMB sensor array. Measurement Science and Technology vol. 7, 1996, pp. 1103-1114.
• 31. Sammons J.W.: A non linear mapping for data structure analysis. IEEE Trans. Comp. vol. C-18, 1969, pp. 401.
• 32. Dennis J.E., Schnabel R.B.: Numerical methods for unconstrained optimization and non-linear equations. Prentice Hall Series in computational mathematics, New York, USA, 1983.
• 33. Johnson R.A. and Wichern D.W.: Applied multivariate statistical analysis. Prentice Hall, Englewood Cliffs, NJ, USA, 1982.
• 34. Lachenbruck P.A., Mickey R.M.: Estimation of Error Rates In Discriminant Analysis. Technometrics vol. 10, 1968, pp. 1-11.
• 35. Efron B.: Bootstrap methods: another look at the jack-knife. Annals of Statistics, vol. 7, 1979, pp. 1-26.
• 36. Hamamoto Y., Uchimura S., Tomita S.: A bootstrap technique for nearest neighbor classifier design. IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 19, 1997, pp. 73-79.
• 37. Campbell S.L., Meyer C.D.: Generalized inverses of linear transformations, Pitman, London, UK, 1979.
• 38. Maren A.J. (editor): Handbook of neural computing applications, J. Wiley and sons, London, UK, 1991.
• 39. Rumelhart D.E., McClelland J.L.; Parallel Distributed Processing: Explorations in the microstructure of cognition. vol.1: Learning internal representations by error propagation, MIT Press, Cambridge, MA, USA, 1986.
• 40. Hertz J., Krogh A., Palmer R.G.: Introduction to the theory of Neural Computation. vol.1, Addison Wesley, New York, USA, 1991.
• 41. Gardner J.W.,. Hines E.L and Wilkinson M.: Measurement Science and Techn., 1990, pp. 446-451.
• 42. Neural Computing: A technology handbook for Professional II/plus© users, NeuralWare Inc., Pittsburgh, USA, 1993.
• 43. Martin C.E., Rogers S.K., Ruck D.W.: Neural network Bayes error estimation. Proc. IEEE Int. Conf. Neural Network, 1994 pp. 305-308.
• 44. Ueda N., Nakano R.: Mixture density estiamtion via EM algorithm with deterministic annealing, Proc. IEEE Int. Conf. Neural Network, vol. 1, 1995, pp. 101-105.
• 45. Di Natale C., Mantini A., Macagnano A., Antuzzi D., Paolesse R., D’Amico A.: Electronic nose analysis of urine samples containing blood. Physiological measurements vol. 20, 1999, pp. 1-8.