Inverse problem solving in semiconductor photoacoustics by neural networks
No Thumbnail
Article (Published version)

© 2020 Informa UK Limited, trading as Taylor & Francis Group
Metadata
Show full item recordAbstract
We developed a method of inverse problem solving in semiconductor photoacoustics based on neural networks application. Simple structured neural networks, trained on a large set of data obtained by the well–known theoretical models in the 20 Hz–20 kHz modulation frequency range, are applied to determine thermal diffusivity, coefficient of linear expansion and thickness of n–type silicon samples, using undistorted experimental photoacoustic signals. The efficiency of the neural networks was tested depending on the type of input data, showing the best performances in the case when signal amplitudes and phases are simultaneously presented to the network. Real–time parameter prediction is achieved together with high accuracy and reliability allowing one to perform the full characterization of a sample in the frequency domain.
Keywords:
Semiconductors / photothermal / photoacoustic / thermal distribution / artificial neural networks / experimental signal / inverse problem / n - type siliconSource:
Inverse Problems in Science and Engineering, 2021, 29, 2, 248-262Funding / projects:
- Atomic collision processes and photoacoustic spectroscopy of molecules and solids (RS-171016)
- Functional, Functionalized and Advanced Nanomaterials (RS-45005)
DOI: 10.1080/17415977.2020.1787405
ISSN: 1741-5977
WoS: 000547434800001
Scopus: 2-s2.0-85087592228
Institution/Community
VinčaTY - JOUR AU - Đorđević, Katarina Lj. AU - Markushev, Dragan D. AU - Ćojbašić, Žarko M. AU - Galović, Slobodanka PY - 2021 UR - https://vinar.vin.bg.ac.rs/handle/123456789/9075 AB - We developed a method of inverse problem solving in semiconductor photoacoustics based on neural networks application. Simple structured neural networks, trained on a large set of data obtained by the well–known theoretical models in the 20 Hz–20 kHz modulation frequency range, are applied to determine thermal diffusivity, coefficient of linear expansion and thickness of n–type silicon samples, using undistorted experimental photoacoustic signals. The efficiency of the neural networks was tested depending on the type of input data, showing the best performances in the case when signal amplitudes and phases are simultaneously presented to the network. Real–time parameter prediction is achieved together with high accuracy and reliability allowing one to perform the full characterization of a sample in the frequency domain. T2 - Inverse Problems in Science and Engineering T1 - Inverse problem solving in semiconductor photoacoustics by neural networks VL - 29 IS - 2 SP - 248 EP - 262 DO - 10.1080/17415977.2020.1787405 ER -
@article{ author = "Đorđević, Katarina Lj. and Markushev, Dragan D. and Ćojbašić, Žarko M. and Galović, Slobodanka", year = "2021", abstract = "We developed a method of inverse problem solving in semiconductor photoacoustics based on neural networks application. Simple structured neural networks, trained on a large set of data obtained by the well–known theoretical models in the 20 Hz–20 kHz modulation frequency range, are applied to determine thermal diffusivity, coefficient of linear expansion and thickness of n–type silicon samples, using undistorted experimental photoacoustic signals. The efficiency of the neural networks was tested depending on the type of input data, showing the best performances in the case when signal amplitudes and phases are simultaneously presented to the network. Real–time parameter prediction is achieved together with high accuracy and reliability allowing one to perform the full characterization of a sample in the frequency domain.", journal = "Inverse Problems in Science and Engineering", title = "Inverse problem solving in semiconductor photoacoustics by neural networks", volume = "29", number = "2", pages = "248-262", doi = "10.1080/17415977.2020.1787405" }
Đorđević, K. Lj., Markushev, D. D., Ćojbašić, Ž. M.,& Galović, S.. (2021). Inverse problem solving in semiconductor photoacoustics by neural networks. in Inverse Problems in Science and Engineering, 29(2), 248-262. https://doi.org/10.1080/17415977.2020.1787405
Đorđević KL, Markushev DD, Ćojbašić ŽM, Galović S. Inverse problem solving in semiconductor photoacoustics by neural networks. in Inverse Problems in Science and Engineering. 2021;29(2):248-262. doi:10.1080/17415977.2020.1787405 .
Đorđević, Katarina Lj., Markushev, Dragan D., Ćojbašić, Žarko M., Galović, Slobodanka, "Inverse problem solving in semiconductor photoacoustics by neural networks" in Inverse Problems in Science and Engineering, 29, no. 2 (2021):248-262, https://doi.org/10.1080/17415977.2020.1787405 . .