Abstract
In this article, a method for determination of photoacoustic detector transfer function as an accurate representation of microphone frequency response is presented. The method is based on supervised machine learning techniques, classification and regression, performed by two artificial neural networks. The transfer function is obtained by determining the microphone type and characteristic parameters closely related to its filtering properties. This knowledge is crucial within the signal correction procedure. The method is carefully designed in order to maintain requirements of photoacoustic experiment accuracy, reliability and real-time performance. The networks training is performed using large base of theoretical signals simulating frequency response of three types of commercial electret microphones frequently used in photoacoustic measurements extended with possible flat response of the so-called ideal microphone. The method test is performed with simulated and experimental signals assuming the usage of open-cell photoacoustic set-up. Experimental testing leads to the microphone transfer function determination used to correct the experimental signals, targeting the “true” undistorted photoacoustic response which can be further used in material characterization process.
Similar content being viewed by others
References
Aleksic, S., Markushev, D., Pantic, D., Rabasovic, M., Markushev, D., Todorovic, D.: Electro-acoustic influence of the measuring system on the photoacoustic signal amplitude and phase in frequency domain. Facta Univ. Ser. Phys. Chem. Technol. 14(1), 9–20 (2016). https://doi.org/10.2298/FUPCT1601009AM
Avati, A., Jung, K., Harman, S., Downing, L., Ng, A., Shah, N.H.: Improving palliative care with deep learning. BMC Med. Inform. Decis. Mak. 18(4), 122 (2018). https://doi.org/10.1186/s12911-018-0677-8
Bengio, Y.: Practical recommendations for gradient-based training of deep architectures. In: Montavon, G., Orr, G.B., Müller, K.R. (eds.) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, vol. 7700. Springer, Berlin (2012). https://doi.org/10.1007/978-3-642-35289-8_26
Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012)
Deng, L., Yu, D.: Deep learning: methods and applications. Found. Trends® Signal Process. 7(3–4), 197–387 (2014). https://doi.org/10.1561/2000000039
Djordjevic, K.L., Markushev, D.D., et al.: Photoacoustic measurements of the thermal and elastic properties of n-type silicon using neural networks. Silicon (2019). https://doi.org/10.1007/s12633-019-00213-6
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006). https://doi.org/10.1162/neco.2006.18.7.1527
Kawaguchi, K., Kaelbling, L.P., Bengio, Y.: Generalization in Deep Learning. (2017). arXiv:1710.05468
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539
Li, Y., Huang, C., Ding, L., Li, Z., Pan, Y., Gao, X.: Deep learning in bioinformatics: introduction, application, and perspective in big data era. Methods 166, 4–21 (2019). https://doi.org/10.1101/563601
Lukić, M., Ćojbašić, Ž., Rabasović, M.D., Markushev, D.D.: Computationally intelligent pulsed photoacoustics. Meas. Sci. Technol. 25(12), 125203 (2014). https://doi.org/10.1088/0957-0233/25/12/125203
Markushev, D.D., Rabasovic, M.D., Todorovic, D.M., Galovic, S., Bialkowski, S.E.: Photoacoustic signal and noise analysis for Si thin plate: signal correction in frequency domain. Rev. Sci. Instrum. 86(3), 035110 (2015). https://doi.org/10.1063/1.4914894
Markushev, D.D., et al.: Thermal and elastic characterization of glassy carbon thin films by photoacoustic measurements. Eur. Phys. J. Plus 132(33), 1–9 (2017). https://doi.org/10.1140/epjp/i2017-11307-2
Ollivier, S., Salze, E., Averiyanov, M., Yuldashev, P.V., Khokhlova, V.: Calibration method for high frequency microphones. French Society of Acoustics, pp. 3503–3507 (2012) Nantes, France. https://hal.archives-ouvertes.fr/hal-00811138. Accessed 16 Oct 2019
Pavlovic, M.J., Kupusinac, A., Popovic, M.: Classification model for microphone type recognition. In: Proceedings of 11th International Scientific Conference Science and Higher Education in Function of Sustainable Development—SED, ISBN 978-86-83573-95-0 (2019). http://arxiv.org/abs/1906.09958. Accessed on 1 March 2020
Pavlovic, M.J., Markushev, D., Popovic, M., Galovic, S.: Deep learning in development of model- dependent diagnostic: recognition of detector characteristics in measured responses. In: Proceedings of 6th International Conference on Electrical, Electronic, and Computing Engineering (IcETRAN) ISBN 978-86-7466-785-9 (2019)
Pavlovic, M.J., Stankovic, M., Popovic, M., Cojbasic, Z., Galovic, S., Markushev, D.: Artificial neural networks application in solid state photoacoustics based on microphone response recognition in the frequency domain. J. Comput. Electron. accepted for publication (2020)
Perondi, L.F., Miranda, L.C.M.: Minimal-volume photoacoustic cell measurement of thermal diffusivity: effect of the thermoelastic sample bending. J. Appl. Phys. 62(7), 2955–2959 (1987). https://doi.org/10.1063/1.339380
Popovic, M.N., et al.: Helmholtz resonances in photoacoustic experiment with laser-sintered polyamide including thermal memory of samples. Int. J. Thermophys. 37(12), 1–9 (2016). https://doi.org/10.1007/s10765-016-2124-3
Rabasovic, M.D., Nikolic, M.G., Dramicanin, M.D., Franko, M., Markushev, D.D.: Low-cost, portable photoacoustic setup for solid samples. Meas. Sci. Technol. 20(9), 95902 (2009). https://doi.org/10.1088/0957-0233/20/9/095902
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015). https://doi.org/10.1016/j.neunet.2014.09.003
Acknowledgements
This work has been supported by the Ministry of Education and Science of the Republic of Serbia throughout the research projects: III 45005, OI 171016, ON 174026 and III 044006. The authors are grateful to M.D. Rabasovic and D.M. Todorovic for useful discussion and help during the experiment.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the Topical Collection on Advanced Photonics Meets Machine Learning.
Guest edited by Goran Gligoric, Jelena Radovanovic and Aleksandra Maluckov.
Rights and permissions
About this article
Cite this article
Jordovic-Pavlovic, M.I., Kupusinac, A.D., Djordjevic, K.L. et al. Computationally intelligent description of a photoacoustic detector. Opt Quant Electron 52, 246 (2020). https://doi.org/10.1007/s11082-020-02372-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11082-020-02372-y