Abstract
A development of simulated data and discussion on potential use in processing photoacoustic measurement data, as well as in solving of an inverse problem are presented in the paper. Simulated experimental values are obtained based on theoretical-mathematical model of photoacoustic response, described in the paper. Credibility of the data is acquired due to the experimental measurements. Simulated data validity was proven with the satisfactory accuracy, precision, and reliability of the several machine learning models which were trained on the designed database and are applied in processing photoacoustic measurement data. Presented results show that if a huge dataset of high-quality data is generated, solving issues of inverse photoacoustic problem is successful, computing is cost effective, and process rate of machine learning models is suitable for real time work.
Publisher
Centre for Evaluation in Education and Science (CEON/CEES)
Reference38 articles.
1. Y. S. Abu-Mostafa, M. Magdon-Ismail, and H.-T. Lin, "Learning From Data", AML Book, (2012);
2. D. Allman, A. Reiter and M.A.L. Bell, "Photoacoustic Source Detection and Reflection Artifact Removal Enabled by Deep Learning," IEEE Trans. Med. Imaging, Vol. 37, pp. 1464-1477, https://doi.org/10.1109/TMI.2018.2829662, (2018);
3. M. Lukić, Ž. Ćojbašić, M.D. Rabasović, D.D. Markushev and D.M. Todorović, "Laser Fluence Recognition Using Computationally Intelligent Pulsed Photoacoustics Within the Trace Gases Analysis," Int J Thermophys, Vol. 38, p. 165, https://doi.org/10.1007/s10765-017-2296-5, (2017);
4. M. Lukić, Ž. Ćojbašić, M.D. Rabasović and D.D. Markushev, "Computationally intelligent pulsed photoacoustics," Meas. Sci. Technol, Vol. 25, p.125203. https://doi.org/10.1088/0957-0233/25/12/125203, (2014);
5. M. N. Popovic, D. Furundzic, and S. P. Galovic, "Photothermal Depth Profiling Of Optical Gradient Materials By Neural Network," Publ. Astron. Obs. Belgrade, vol. 89, no. May 2015, 2010;
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献