Environmental Science and Pollution Research

, Volume 23, Issue 24, pp 24547–24559 | Cite as

Supervised neural computing solutions for fluorescence identification of benzimidazole fungicides. Data and decision fusion strategies

  • Carmen Paz Suárez-Araujo
  • Patricio García Báez
  • Álvaro Sánchez Rodríguez
  • José Juan Santana-Rodrríguez
Global pollution problems, Trends in Detection and Protection

Abstract

Benzimidazole fungicides (BFs) are a type of pesticide of high environmental interest characterized by a heavy fluorescence spectral overlap which complicates its detection in mixtures. In this paper, we present a computational study based on supervised neural networks for a multi-label classification problem. Specifically, backpropagation networks (BPNs) with data fusion and ensemble schemes are used for the simultaneous resolution of difficult multi-fungicide mixtures. We designed, optimized and compared simple BPNs, BPNs with data fusion and BPNs ensembles. The information environment used is made up of synchronous and conventional BF fluorescence spectra. The mixture spectra are not used in the training nor the validation stage. This study allows us to determine the convenience of fusioning the labels of carbendazim and benomyl for the identification of BFs in complex multi-fungicide mixtures.

Keywords

Artificial neural networks Fluorescence spectrometry Fungicides Ensembles Mixture resolution Environment Data fusion 

References

  1. Almhdi KM, Valigi P, Gulbinas V, Westphal R, Reuter R (2007) Classification with artificial neural networks and support vector machines: application to oil fluorescence spectra. EARSeL eProceedings 6(2):115–129Google Scholar
  2. Bordagaray A, Amigo RJ (2015) Modelling highly co-eluted peaks of analytes with high spectral similarity. Trends Anal Chem 68:107–118. doi:10.1016/j.trac.2015.02.010 CrossRefGoogle Scholar
  3. Bro R (1997) PARAFAC. Tutorial and applications, Chemom. Intell. Lab. Syst, chap 38.2, 149–171Google Scholar
  4. Clarke C (2008) Development of an automated identification system for nanocrystal encoded microspheres in flow cytometry. PhD thesis, Cranfield UniversityGoogle Scholar
  5. D’Archivio AA, Maggi MA, Marinelli C, Ruggieri F, Stecca F (2015) Optimisation of temperature-programmed gas chromatographic separation of organochloride pesticides by response surface methodology. J Chromatogr A 1423:15708. doi:10.1016/j.chroma.2015.10.082. http://www.sciencedirect.com/science/article/pii/S00219673150 Google Scholar
  6. Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861–874. doi:10.1016/j.patrec.2005.10.010 CrossRefGoogle Scholar
  7. Fernández-Sánchez J, Carretero AS, Benítez-Sánchez J, Cruces-Blanco C, Fernández-Gutiérrez A (2004) Fluorescence optosensor using an artificial neural network for screening of polycyclic aromatic hydrocarbons. Anal Chim Acta 510(2):183–187. doi:10.1016/j.aca.2004.01.012. http://www.sciencedirect.com/science/article/pii/S0003267004000492 CrossRefGoogle Scholar
  8. Ferrer R, Guiteras J, Beltrán J (1999) Artificial neural networks (ANNs) in the analysis of polycyclic aromatic hydrocarbons in water samples by synchronous fluorescence. Anal Chim Acta 384(3):261–269. doi:10.1016/S0003-2670(98)00778-8, http://www.sciencedirect.com/science/article/pii/S0003267098007788 CrossRefGoogle Scholar
  9. Gallinari P (1995) Training of modular neural net systems. In: Arbib M A (ed) Handbook of brain theory and neural networks, MIT press, pp 582–585Google Scholar
  10. García Báez P (2005) HUMANN: una nueva red neuronal artificial adaptativa, no supervisada, modular y jerárquica aplicaciones en neurociencia y medioambiente. PhD thesis, ULPGCGoogle Scholar
  11. García Báez P, Suárez Araujo C, Fernández López P (2003) A parametric study of HUMANN in relation to the noise: application to the identification of compounds of environmental interest. Syst Anal Model Simul 43(9):1213–28Google Scholar
  12. García Báez P, Suárez Araujo CP, Sánchez Rodríguez A, Santana Rodríguez JJ (2010) Towards an efficient computational method for fluorescence identification of fungicides using data fusion and neural ensemble techniques. Luminescence 25(3):285– 287Google Scholar
  13. García Báez P, lvarez Romero Y, Suárez Araujo CP (2012) A computational study on supervised and unsupervised neural architectures with data fusion for fluorescence detection of fungicides. Luminescence 27:534–572CrossRefGoogle Scholar
  14. Hansen L, Salamon P (1990) Neural network ensembles. IEEE Trans Pattern Anal Mach Intell 12 (10):993–1001. doi:10.1109/34.58871 CrossRefGoogle Scholar
  15. Haykin S (1994) Neural networks: a comprehensive foundation. Macmillan, New YorkGoogle Scholar
  16. He L, Kear-Padilla L, Lieberman S, Andrews J (2003) Rapid in situ determination of total oil concentration in water using ultraviolet fluorescence and light scattering coupled with artificial neural networks. Anal Chim Acta 478(2):245–258. doi:10.1016/S0003-2670(02)01471-X, http://www.sciencedirect.com/science/article/pii/S000326700201471X CrossRefGoogle Scholar
  17. Henry R (2003) Multivariate receptor modeling by N-dimensional edge detection. Chemom. Intell. Lab. Syst, chap 65.2, 179–189Google Scholar
  18. Johansson U, Löfström T (2012) Producing implicit diversity in ann ensembles. In: Neural networks (IJCNN), The 2012 International Joint Conference on, pp 1–8Google Scholar
  19. Jolliffe IT (2002) Principal component analysis 2nd edn. Springer. http://www.amazon.com/exec/obidos/redirect?tag=citeulike07-20&path=ASIN/0387954422
  20. Jones E, Oliphant T, Peterson P, et al. (2001) SciPy: open source scientific tools for Python. http://www.scipy.org/
  21. Liu X, Yao Y, Higuchi T (2003) Designing neural network ensembles by minimising mutual information. In: Mohammadian M, Sarker R. A., Yao X (eds) Computational intelligence in control, Hershey : Idea Group Pub, USA & London (UK), pp 1–21Google Scholar
  22. Loewy R (2000) Plaguicidas en aguas subterráneas del alto valle de ríbo negro neuquén. tesis de maestría en ciencias químicas Master’s thesis, Universidad Nacional de Comahue, ArgentinaGoogle Scholar
  23. Oliphant TE (2007) Python for scientific computing. Comput Sci Eng 9(3):10–20. doi:10.1109/MCSE.2007.58 CrossRefGoogle Scholar
  24. Paatero P, Tapper U (1994) Positive matrix factorization: a non-negative factor model with optimal utilization of error estimates of data values, Environmetrics, chap 5.2, 111–126Google Scholar
  25. Piccirilli GN, Escandar GM (2006) Partial least-squares with residual bilinearization for the spectrofluorimetric determination of pesticides. A solution of the problems of inner-filter effects and matrix interferents. Analyst 131:1012–1020. doi:10.1039/B603823A CrossRefGoogle Scholar
  26. Rumelhart DE, Hinton GE, McClelland JL (1987) A general framework for parallel distributed processing. In: Rumelhart D E, McClelland J L et al. (eds) Parallel distributed processing, vol 1. Foundations, MIT Press, Cambridge, pp 45–76Google Scholar
  27. Sabik H, Jeannot R (1998) Determination of organonitrogen pesticides in large volumes of surface water by liquid-liquid and solid-phase extraction using gas chromatography with nitrogen-phosphorus detection and liquid chromatography with atmospheric pressure chemical ionization mass spectrometry. J Chromatogr A 818 (2):197–207. doi:10.1016/S0021-9673(98)00555-X, http://www.sciencedirect.com/science/article/pii/S002196739800555X CrossRefGoogle Scholar
  28. Sanger TD (1989) Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Netw 2:459–473. doi:10.1.1.128.6893Google Scholar
  29. Santana-Rodríguez JJ, Torres-Padrón ME, Aufartová J, Sosa-Ferrera Z (2010) Fungicides. Benzimidazole fungicides in environmental samples: extraction and determination procedures. Ed:Odile Carisse, InTech, Department of Chemistry. Faculty of Marine Sciences. University of Las Palmas de Gran. Department of Analytical Chemistry, Faculty of Pharmacy, Charles University, chap 15, pp 305–324. 978-953-307-266-1. doi:10.5772/10481
  30. Suarez Araujo CP, García Báez P, Hernández Trujillo Y (2010) Fungicides. Neural computation methods in the determination of fungicides. In: Carisse O (ed) Intech, chap 23Google Scholar
  31. Suárez Araujo CP (1999) Neural computation approach in luminescence spectrometry. Biomed Chromatogr 13(2):187–188 . doi:10.1002/(SICI)1099-0801(199904)13:2%3C187::AID-BMC877%3E3.0.CO;2-E CrossRefGoogle Scholar
  32. Suárez Araujo CP, García Báez P, Sánchez Rodríguez A, Santana Rodríguez JJ (2006) Design of a HUMANN-based method for the determination of benzimidazole fungicides with fluorescence detection. Luminescence 21(6):342–344Google Scholar
  33. Suárez Araujo CP, García Báez P, Sánchez Rodríguez A, Santana Rodríguez JJ (2009) HUMANN-based system to identify benzimidazole fungicides using multi-synchronous fluorescence spectra: an ensemble approach. Anal Bioanal Chem 394(4):1059–1072CrossRefGoogle Scholar
  34. Todeschini R, Galvagni D, Vílchez J, del Olmo M, Navas N (1999) Kohonen artificial neural networks as a tool for wavelength selection in multicomponent spectrofluorimetric {PLS} modelling: application to phenol, o-cresol, m-cresol and p-cresol mixtures. TrAC, Trends Anal Chem 18(2):93–98. doi:10.1016/S0165-9936(98)00097-1, http://www.sciencedirect.com/science/article/pii/S0165993698000971 CrossRefGoogle Scholar
  35. Vasilescu J, Marmureanu L, Carstea E (2011) Analysis of seawater pollution using neural networks and channels relationship algorithms. Rom J Phys 56(3-4):530–539Google Scholar
  36. Vassilakis Y, Tipi D, Scoullos M (1998) Determination of a variety of chemical classes of pesticides in surface and ground waters by off-line solid-phase extraction, gas chromatography with electron-capture and nitrogen-phosphorus detection, and high-performance liquid chromatoagraphy with post-column derivatization and fluorescence detection, J. Chromatogr. A, chap. 823, 49– 58Google Scholar
  37. Yehia AM, Mohamed HM (2016) Chemometrics resolution and quantification power evaluation: application on pharmaceutical quaternary mixture of paracetamol, guaifenesin, phenylephrine and p-aminophenol. Spectrochim Acta A Mol Biomol Spectrosc 152:491–500. doi:10.1016/j.saa.2015.07.101 CrossRefGoogle Scholar
  38. Zhu S, Wu H, Xia A, Ha Q, Zhang Y (2007) Determination of carbendazim in bananas by excitation-emission matrix fluorescence with three second-order calibration methods, Analytical Science, chap 23.10, 1173–1177Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Instituto Universitario de Ciencias y Tecnologías CibernéticasUniversidad de Las Palmas de Gran CanariaLas Palmas de Gran CanariaSpain
  2. 2.Departamento de Ingeniería Informática y de SistemasUniversidad de La LagunaLa LagunaSpain
  3. 3.Instituto de Estudios Ambientales y Recursos NaturalesUniversidad de Las Palmas de Gran CanariaLas Palmas de Gran CanariaSpain

Personalised recommendations