Advertisement

Classification of Electromagnetic Spectrum in the Visible Range Using Machine Learning

  • Gonzalo VargasEmail author
  • Jose A. González
  • Mauricio Ortiz
Conference paper
Part of the Springer Proceedings in Physics book series (SPPHY, volume 233)

Abstract

Spectrophotometers are instruments that measure parameters of samples as a function of the wavelength and work with a source of broad spectrum light a diffractive element and a detector. Those instruments are widely used in chemistry, physics and medicine labs, among others. The design of a spectrophotometer in the visible range of the electromagnetic spectrum is presented in this work and consists of a white LED, a holographic grating and a Samsung camera as a detector; the spectrum generated by placing a liquid sample in the spectrophotometer is analyzed by three different artificial intelligence algorithms: artificial neural networks (ANNs), convolutional neural networks (CNNs), and support vector machines (SVMs). These types of algorithms are part of the machine learning techniques that are used to solve classification and regression problems, for example, facial and speech recognition, efficient searching engines and medical diagnostic, among others. In this manuscript, these algorithms were implemented to determinate which one is the best to classify the samples, considering the accuracy and execution time.

Notes

Acknowledgements

This research is partially supported by grant CIC-UMSNH-4.23. The authors also thank ABACUS Laboratorio de Matemticas Aplicadas y C´omputo de Alto Rendimiento del CINVESTAV-IPN, grant CONACT-EDOMEX-2011-C01-165873, for providing computer resources.

References

  1. 1.
    J. Luis Sánchez-Milln et al., Espectroscopía Raman: Herramienta rápida y no invasiva para determinar carotenoides en inflorescencias de Tagetes erecta L. Agrociencia 41(8) (2007)Google Scholar
  2. 2.
    C.M. Bishop, Pattern Recognition and Machine Learning (Inc. Secaucus, NJ, USA, 2006)Google Scholar
  3. 3.
    R.J. Schalkoff, Artificial Neural Networks, vol. 1 (McGraw-Hill, New York, 1997)zbMATHGoogle Scholar
  4. 4.
    E. Loewen, C. Palmer, Diffraction Grating Handbook (Newport Corporation, 2005)Google Scholar
  5. 5.
    M. Abadi et al., TensorFlow: large-scale machine learning on heterogeneous systems. Software available from https://www.tensorflow.org (2015)
  6. 6.
    C.-C. Chang, LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3), 1–27 (2011). Article no. 27. http://www.csie.ntu.edu.tw/cjlin/libsvm2
  7. 7.
    D. Michie, D.J. Spiegelhalter, C.C. Taylor (eds.), Machine Learning, Neural and Statistical Classification (Ellis Horwood, 1994)Google Scholar
  8. 8.
    A. Krogh, J. Vedelsby, Neural network ensembles, cross validation, and active learning, in Advances in Neural Information Processing Systems (1995)Google Scholar
  9. 9.
    Y. LeCun, Y. Bengio, Convolutional networks for images, speech, and time series, in The Handbook of Brain Theory and Neural Networks, vol. 3361, no. 10 (1995)Google Scholar
  10. 10.
    S. Abe, Support Vector Machines for Pattern Classification (Springer, London, 2010)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Gonzalo Vargas
    • 1
    Email author
  • Jose A. González
    • 1
  • Mauricio Ortiz
    • 2
  1. 1.Laboratorio de Inteligencia Artificial y SupercomputoInstituto de Física y Matemáticas, Universidad Michoacana de San Nicolás de HidalgoMoreliaMexico
  2. 2.Facultad de Ciencias Físico-MatemáticasUniversidad Michoacana de San Nicolás de HidalgoMoreliaMexico

Personalised recommendations