Skip to main content
SpringerLink
Log in

Improvement of Neural Networks Applied to Photoacoustic Signals of Semiconductors with Added Noise

  • Original Paper
  • Published:
Silicon Aims and scope Submit manuscript

Abstract

This paper provides an overview of the characteristics of different neural networks trained on the same theoretical database of n-type silicon photoacoustic signals. By adding different levels of random Gaussian noise to the training input signals, two important goals were achieved. First, the optimal level of noise was found which significantly shortens the training networks with minimal loss of accuracy of its predictions. Second, the termination criteria of networks training were activated to avoid overtraining, i.e., networks generalization was performed. A networks efficiency analysis was performed on both theoretical and experimental photoacoustic signals, resulting in a selection of one neural network that is optimal to the performance requirements of the real experiment. It is indicated that the application of such trained networks is more reliable on thicker semiconductors, whose thickness is greater than the value of the carrier diffusion length in the investigated sample.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Hinton G, Deng L, Yu D, Dahl G, Mohamed A, Jaitly N, Senior A, Vanhoucke V, Nguyen P, Sainath T, Kingsbury B (2012) Deep Neural Networks for Acoustic Modeling in Speech Recognition. Signal Process Magazine. https://doi.org/10.1109/MSP.2012.2205597

  2. Dorschky E, Krüger D, Kurfess N, Schlarb H, Wartzack S, Eskofier B, van den Bogert AJ (2019) Optimal control simulation predicts effects of midsole materials on energy cost of running In: Computer Methods Biomech Biomed Eng ISSN:1025-5842 https://doi.org/10.1080/10255842.2019.1601179

  3. Bialkowski S (1996) Photothermal spectroscopy methods for chemical analysis. John Wiley, New York ISBN: 978-0-471-57467-5

    Book  Google Scholar 

  4. Vasquez-Correa JC, Orozco-Arroyave JR, Arora R et al. (2017) Multi-view representation learning via gcca for multimodal analysis of Parkinson's disease. In: ICASSP, IEEE Int Conf Acoustics, Speech Signal Process – Proc, 2966–2970. https://doi.org/10.1109/ICASSP.2017.7952700

  5. Zibar D, Piels M, Jones RT, Schaeffer CG (2016) Machine learning techniques in optical communication. J Lightwave Technol 34(6):1442–1452. https://doi.org/10.1109/JLT.2015.2508502

    Article  Google Scholar 

  6. Lokhov AY, Saad D (2017) Optimal deployment of resources for maximizing impact in spreading processes. Proc Natl Acad Scie USA 114(39):E8138–E8146. https://doi.org/10.1073/pnas.1614694114

    Article  CAS  Google Scholar 

  7. Pierangeli D, Palmieri V, Marcucci G, Moriconi C, Perini G, De Spirito M, Papi M, Conti C (2019) Optical neural network for cancer morphodynamics sensing. OSA Tech Digest Optical Soci Am. https://doi.org/10.1364/NLO.2019.NTh1A3

  8. Albu A, Precup R-E, Teban T-E (2019) Results and Challenges of Artificial Neural Networks Used for Decision-Making and Control in Medical Applications. Facta Universitatis J - Series Mech Eng. https://doi.org/10.22190/FUME190327035A

  9. Glorieux C, Li VR, Thoen J, Bertolotti M, Sibilia C (1999) Depth profiling of thermally inhomogeneous materials by neural network recognition of photothermal time domain data. J Appl Phys 85(10):7059–7063. https://doi.org/10.1063/1.370512

    Article  CAS  Google Scholar 

  10. Lukić M, Čojbašić Ž, Rabasović MD, Markushev DD, Todorović DM (2013) Neural networks-based real-time determination of laser beam spatial profile and vibrational-to-translational relaxation time within pulsed photoacoustics. Int J Thermophys 34: 8–9. 1795–1802. https://doi.org/10.1007/s10765-013-1507-y

  11. Lukić M, Čojbašić Ž, Rabasović MD, Markushev DD (2014) Computationally intelligent pulsed photoacoustics Meas. Sci Technol 25(12):125203–125209. https://doi.org/10.1088/0957-0233/25/12/125203

    Article  CAS  Google Scholar 

  12. Djordjevic KLj, Markushev DD, Ćojbašić ŽМ, Galović SP (2019) Photoacoustic measurements of the thermal and elastic properties of n-type silicon using neural networks. Silicon, Springer. https://doi.org/10.1007/s12633-019-00213-6

  13. Rabasović MD, Nikolić MG, Dramićanin MD, Franko M, Markushev DD (2009) Low-cost, portable photoacoustic setup for solid state. Measurement Sci Technol 20:9. https://doi.org/10.1088/0957-0233/20/9/095902

    Article  CAS  Google Scholar 

  14. Guozhong AN (1996) The effects of adding noise during backpropagation training on a generalization performance. Neural Computation 8(3):643–674 Massachusetts Institute of Technology. https://doi.org/10.1162/neco.1996.8.3.643

    Article  Google Scholar 

  15. Chuan Wang JC (1999) Principe “Training neural networks with additive noise in the desired signal”, Neural Networks IEEE Trans on 10 6 1511–1517 https://doi.org/10.1109/72.809097

  16. Isaev I, Dolenko S (2018) Training with noise addition in neural network solution of inverse problems: procedures for selection of the optimal network. Procedia Comput Sci 123:171–176. https://doi.org/10.1016/j.procs.2018.01.028

    Article  Google Scholar 

  17. Markushev DK, Markushev DD, Galović SP, Aleksić S, Pantić DS, Todorović DM (2018) The surface recombination velocity and bulk lifetime influences on photogenerated excess carrier density and temperature distributions in n-type silicon excited by a frequency-modulated light source, Facta Universitatis. Series: Electronics and Energetics 31(2):313–328. https://doi.org/10.2298/FUEE1802313M

    Article  Google Scholar 

  18. Markushev DK, Markushev DD, Aleksić S, Pantić DS, Galović S, Todorović DM and Ordoney-Miranda J (2019) Effects of the photogenerated excess carriers on the thermal and elastic properties of n-type silicon excited with a modulated light source: Theoretical Anal J Appl Phys 126(18) https://doi.org/10.1063/1.5100837

  19. Todorović DM, Nikolić PM, Dramićanin MD, Vasiljević DG, Ristovski ZD (1995) Photoacoustic frequency heat-transmission technique: Thermal and carrier transport parameters measurements in silicon. J Appl Phys 78(9):5750. https://doi.org/10.1063/1.359637

    Article  Google Scholar 

  20. Todorović DM, Nikolić PM (2000) Semiconductors and Electronic Materials Progress in Photothermal and Photoacoustic Science and Technology Chap. 9. Optical Engineering Press, New York, pp 273–318 ISBN: 9780819435064

    Google Scholar 

  21. Markushev DD, Ordonez-Miranda J, Rabasović MD, Chirtoc M, Todorović DM, Bialkowski SE, Korte D, Franko M (2017) Thermal and elastic characterization of glassy carbon thin films by photoacoustic measurements. Eur Phys J Plus 132(1):33. https://doi.org/10.1140/epjp/i2017-11307-2

    Article  CAS  Google Scholar 

  22. Markushev DD, Rabasović MD, Todorović DM, Galović S, Bialkowski SE (2015) Photoacoustic signal and noise analysis for Si thin plate: Signal correction in frequency domain. Rev Sci Instruments 86:035110. https://doi.org/10.1063/1.4914894

    Article  CAS  Google Scholar 

  23. Rockett A (2008) The Materials Science of Semiconductors 13 ISBN 978-0-387-25653-5

  24. Levy RA (1989) Microelectronic Materials and Processes 6–7 13 ISBN 978-0-7923-0154-7 Retrieved 2008-02-23.

  25. Laplante PA (2005) Wafer. Comprehensive dictionary of electrical engineering (2nd ed.). Boca Raton: CRC Press 739 ISBN 978-0-8493-3086-5

  26. Aleksić SM, Markushev DK, Pantić DS, Rabasović MD, Markushev DD, Todorović DM (2016) Electro-acoustic influence of measuring system on the photoacoustic signal amplitude and phase in frequency domain. FU PhysChem Tech 14(1):9–20. https://doi.org/10.2298/FUPCT1601009A

    Article  Google Scholar 

  27. Popović MN, Nešić MV, Cirić-Kostić S, Živanov M, Markushev DD, Rabasović MD, Galović SP (2016) Helmholtz resonances in photoacoustic experiment with laser-sintered polyamide including thermal memory of samples. Int J Thermophys 37:116. https://doi.org/10.1007/s10765-016-2124-3

    Article  CAS  Google Scholar 

  28. Todorovic DM, Rabasovic MD, Markushev DD, Sarajlic M (2014). J Appl Phys 116:053506. https://doi.org/10.1063/1.4890346

    Article  CAS  Google Scholar 

Download references

Acknowledgments

This work was supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia under the projects No. ON171016 and III45005.

Author information

Authors and Affiliations

  1. Faculty of Physics, University of Belgrade, Belgrade, Serbia

    К. Lj Djordjevic

  2. Vinca Institute of Nuclear Sciences, University of Belgrade, Belgrade, Serbia

    S. P. Galovic

  3. College of Applied Sciences Uzice, Trg Svetog Save 34, Uzice, Serbia

    M. I. Jordovic-Pavlovic

  4. Mechanical Engineering Faculty, University of Nis, Nis, Serbia

    Z. М. Cojbasic

  5. Institute of Physics, University of Belgrade, Belgrade-Zemun, Serbia

    D. D. Markushev

Authors
  1. К. Lj Djordjevic
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. S. P. Galovic
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. M. I. Jordovic-Pavlovic
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Z. М. Cojbasic
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. D. D. Markushev
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to К. Lj Djordjevic.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Djordjevic, К.L., Galovic, S.P., Jordovic-Pavlovic, M.I. et al. Improvement of Neural Networks Applied to Photoacoustic Signals of Semiconductors with Added Noise. Silicon 13, 2959–2969 (2021). https://doi.org/10.1007/s12633-020-00606-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12633-020-00606-y

Keywords

Search

Navigation