TY  - CONF
AU  - Đorđević, Katarina Lj.
AU  - Galović, Slobodanka
AU  - Jordović-Pavlović, Miroslava I.
AU  - Markushev, Dragan D.
AU  - Markushev, Dragana K.
AU  - Nešić, Mioljub V.
AU  - Popović, Marica N.
PY  - 2023
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/11938
AB  - The idea of this paper is to develop a method for determination thermal diffusivity, linear expansion coefficient and thickness of a semiconductor sample from photoacoustic phase measurement by using neural network. The neural network has been trained on photoacoustic phases obtained from a theoretical model of measured signal for Si n-type in the range of 20Hz to 20kHz. For the analysis of parameter determination from phases, we trained phase neural networks on a large database obtained from numerical experiments in the expected range of parameter changes. An analysis of a theoretical photoacoustic model with a phase neural network is demonstrated. The advantages of using a phase neural network with high accuracy and precision in prediction depending on the number of epochs are presented, as well as analyzes of the application of random Gaussian noise to the network in order to better predict the experimental photoacoustic signal.
C3  - Proceedings of Science
T1  - Еvaluation of Thermophysical Properties of Semiconductors by Photoacoustic Phase Neural Network
VL  - 427
SP  - 193246
DO  - 10.22323/1.427.0157
ER  - 

@conference{
author = "Đorđević, Katarina Lj. and Galović, Slobodanka and Jordović-Pavlović, Miroslava I. and Markushev, Dragan D. and Markushev, Dragana K. and Nešić, Mioljub V. and Popović, Marica N.",
year = "2023",
abstract = "The idea of this paper is to develop a method for determination thermal diffusivity, linear expansion coefficient and thickness of a semiconductor sample from photoacoustic phase measurement by using neural network. The neural network has been trained on photoacoustic phases obtained from a theoretical model of measured signal for Si n-type in the range of 20Hz to 20kHz. For the analysis of parameter determination from phases, we trained phase neural networks on a large database obtained from numerical experiments in the expected range of parameter changes. An analysis of a theoretical photoacoustic model with a phase neural network is demonstrated. The advantages of using a phase neural network with high accuracy and precision in prediction depending on the number of epochs are presented, as well as analyzes of the application of random Gaussian noise to the network in order to better predict the experimental photoacoustic signal.",
journal = "Proceedings of Science",
title = "Еvaluation of Thermophysical Properties of Semiconductors by Photoacoustic Phase Neural Network",
volume = "427",
pages = "193246",
doi = "10.22323/1.427.0157"
}

Đorđević, K. Lj., Galović, S., Jordović-Pavlović, M. I., Markushev, D. D., Markushev, D. K., Nešić, M. V.,& Popović, M. N.. (2023). Еvaluation of Thermophysical Properties of Semiconductors by Photoacoustic Phase Neural Network. in Proceedings of Science, 427, 193246.
https://doi.org/10.22323/1.427.0157

Đorđević KL, Galović S, Jordović-Pavlović MI, Markushev DD, Markushev DK, Nešić MV, Popović MN. Еvaluation of Thermophysical Properties of Semiconductors by Photoacoustic Phase Neural Network. in Proceedings of Science. 2023;427:193246.
doi:10.22323/1.427.0157 .

Đorđević, Katarina Lj., Galović, Slobodanka, Jordović-Pavlović, Miroslava I., Markushev, Dragan D., Markushev, Dragana K., Nešić, Mioljub V., Popović, Marica N., "Еvaluation of Thermophysical Properties of Semiconductors by Photoacoustic Phase Neural Network" in Proceedings of Science, 427 (2023):193246,
https://doi.org/10.22323/1.427.0157 . .

TY  - JOUR
AU  - Đorđević, Katarina Lj.
AU  - Jordović-Pavlović, Miroslava I.
AU  - Ćojbašić, Ž. M.
AU  - Galović, Slobodanka
AU  - Popović, Marica N.
AU  - Nešić, Mioljub V.
AU  - Markushev, Dragan D.
PY  - 2022
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/10359
AB  - In this paper, the influence of the input and output data scaling and normalization on the neural network overall performances is investigated aimed at inverse problem-solving in photoacoustics of semiconductors. The logarithmic scaling of the photoacoustic signal amplitudes as input data and numerical scaling of the sample thermal parameters as output data are presented as useful tools trying to reach maximal network precision. Max and min–max normalizations to the input data are presented to change their numerical values in the dataset to common scales, without distorting differences. It was demonstrated in theory that the largest network prediction error of all targeted parameters is obtained by a network with non-scaled output data. Also, it was found out that the best network prediction was achieved with min–max normalization of the input data and network predicted output data scale within the range of [1–10]. Network training and prediction performances analyzed with experimental input data show that the benefits and improvements of input and output scaling and normalization are not guaranteed but are strongly dependent on a specific problem to be solved.
T2  - Optical and Quantum Electronics
T1  - Influence of data scaling and normalization on overall neural network performances in photoacoustics
VL  - 54
IS  - 8
SP  - 501
DO  - 10.1007/s11082-022-03799-1
ER  - 

@article{
author = "Đorđević, Katarina Lj. and Jordović-Pavlović, Miroslava I. and Ćojbašić, Ž. M. and Galović, Slobodanka and Popović, Marica N. and Nešić, Mioljub V. and Markushev, Dragan D.",
year = "2022",
abstract = "In this paper, the influence of the input and output data scaling and normalization on the neural network overall performances is investigated aimed at inverse problem-solving in photoacoustics of semiconductors. The logarithmic scaling of the photoacoustic signal amplitudes as input data and numerical scaling of the sample thermal parameters as output data are presented as useful tools trying to reach maximal network precision. Max and min–max normalizations to the input data are presented to change their numerical values in the dataset to common scales, without distorting differences. It was demonstrated in theory that the largest network prediction error of all targeted parameters is obtained by a network with non-scaled output data. Also, it was found out that the best network prediction was achieved with min–max normalization of the input data and network predicted output data scale within the range of [1–10]. Network training and prediction performances analyzed with experimental input data show that the benefits and improvements of input and output scaling and normalization are not guaranteed but are strongly dependent on a specific problem to be solved.",
journal = "Optical and Quantum Electronics",
title = "Influence of data scaling and normalization on overall neural network performances in photoacoustics",
volume = "54",
number = "8",
pages = "501",
doi = "10.1007/s11082-022-03799-1"
}

Đorđević, K. Lj., Jordović-Pavlović, M. I., Ćojbašić, Ž. M., Galović, S., Popović, M. N., Nešić, M. V.,& Markushev, D. D.. (2022). Influence of data scaling and normalization on overall neural network performances in photoacoustics. in Optical and Quantum Electronics, 54(8), 501.
https://doi.org/10.1007/s11082-022-03799-1

Đorđević KL, Jordović-Pavlović MI, Ćojbašić ŽM, Galović S, Popović MN, Nešić MV, Markushev DD. Influence of data scaling and normalization on overall neural network performances in photoacoustics. in Optical and Quantum Electronics. 2022;54(8):501.
doi:10.1007/s11082-022-03799-1 .

Đorđević, Katarina Lj., Jordović-Pavlović, Miroslava I., Ćojbašić, Ž. M., Galović, Slobodanka, Popović, Marica N., Nešić, Mioljub V., Markushev, Dragan D., "Influence of data scaling and normalization on overall neural network performances in photoacoustics" in Optical and Quantum Electronics, 54, no. 8 (2022):501,
https://doi.org/10.1007/s11082-022-03799-1 . .

TY  - CONF
AU  - Đorđević, Katarina Lj.
AU  - Jordović-Pavlović, Miroslava I.
AU  - Ćojbašić, Ž. M.
AU  - Galović, Slobodanka
AU  - Popović, Marica N.
AU  - Nešić, Mioljub V.
AU  - Markushev, Dragan D.
PY  - 2021
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/10918
AB  - In our previous articles [1,2] we have shown that the application of artificial neural networks (ANNs) in photoacoustics could improve experimental procedures in many ways: better accuracy and precision in investigated sample parameters prediction, better control of the experimental conditions together with approaching to the real-time characterization of the investigated sample, etc. Here we will try to show why the different types of scaling and normalization procedures could be beneficial to the accuracy, precision and numerical stability of the network predicted parameters and network training speed. To do that numerical (Fig.1) or logarithmic scaling and min-max and max normalizations are applied on experimental input data used in the ANNs training process. At the same time, specific numerical scaling is used for network output data (predicted sample thermal and geometric parameters such as thermal diffusivity, linear coefficient of thermal expansion, thickness) to find possible benefits to ANNs performances. Our analysis of training, stability, and accuracy of network prediction will rely on the ANNs trained with or without scaling and/or normalization to find their influence on overall network performances.
PB  - Belgrade : Institute of Physics Belgrade
C3  - PHOTONICA2021 : 8th International School and Conference on Photonics and HEMMAGINERO workshop : Abstracts of Tutorial, Keynote, Invited Lectures, Progress Reports and Contributed Papers; August 23-27, 2021; Belgrade
T1  - Influence of data scaling and normalization on overall neural network performances in photoacoustics
SP  - 173
UR  - https://hdl.handle.net/21.15107/rcub_vinar_10918
ER  - 

@conference{
author = "Đorđević, Katarina Lj. and Jordović-Pavlović, Miroslava I. and Ćojbašić, Ž. M. and Galović, Slobodanka and Popović, Marica N. and Nešić, Mioljub V. and Markushev, Dragan D.",
year = "2021",
abstract = "In our previous articles [1,2] we have shown that the application of artificial neural networks (ANNs) in photoacoustics could improve experimental procedures in many ways: better accuracy and precision in investigated sample parameters prediction, better control of the experimental conditions together with approaching to the real-time characterization of the investigated sample, etc. Here we will try to show why the different types of scaling and normalization procedures could be beneficial to the accuracy, precision and numerical stability of the network predicted parameters and network training speed. To do that numerical (Fig.1) or logarithmic scaling and min-max and max normalizations are applied on experimental input data used in the ANNs training process. At the same time, specific numerical scaling is used for network output data (predicted sample thermal and geometric parameters such as thermal diffusivity, linear coefficient of thermal expansion, thickness) to find possible benefits to ANNs performances. Our analysis of training, stability, and accuracy of network prediction will rely on the ANNs trained with or without scaling and/or normalization to find their influence on overall network performances.",
publisher = "Belgrade : Institute of Physics Belgrade",
journal = "PHOTONICA2021 : 8th International School and Conference on Photonics and HEMMAGINERO workshop : Abstracts of Tutorial, Keynote, Invited Lectures, Progress Reports and Contributed Papers; August 23-27, 2021; Belgrade",
title = "Influence of data scaling and normalization on overall neural network performances in photoacoustics",
pages = "173",
url = "https://hdl.handle.net/21.15107/rcub_vinar_10918"
}

Đorđević, K. Lj., Jordović-Pavlović, M. I., Ćojbašić, Ž. M., Galović, S., Popović, M. N., Nešić, M. V.,& Markushev, D. D.. (2021). Influence of data scaling and normalization on overall neural network performances in photoacoustics. in PHOTONICA2021 : 8th International School and Conference on Photonics and HEMMAGINERO workshop : Abstracts of Tutorial, Keynote, Invited Lectures, Progress Reports and Contributed Papers; August 23-27, 2021; Belgrade
Belgrade : Institute of Physics Belgrade., 173.
https://hdl.handle.net/21.15107/rcub_vinar_10918

Đorđević KL, Jordović-Pavlović MI, Ćojbašić ŽM, Galović S, Popović MN, Nešić MV, Markushev DD. Influence of data scaling and normalization on overall neural network performances in photoacoustics. in PHOTONICA2021 : 8th International School and Conference on Photonics and HEMMAGINERO workshop : Abstracts of Tutorial, Keynote, Invited Lectures, Progress Reports and Contributed Papers; August 23-27, 2021; Belgrade. 2021;:173.
https://hdl.handle.net/21.15107/rcub_vinar_10918 .

Đorđević, Katarina Lj., Jordović-Pavlović, Miroslava I., Ćojbašić, Ž. M., Galović, Slobodanka, Popović, Marica N., Nešić, Mioljub V., Markushev, Dragan D., "Influence of data scaling and normalization on overall neural network performances in photoacoustics" in PHOTONICA2021 : 8th International School and Conference on Photonics and HEMMAGINERO workshop : Abstracts of Tutorial, Keynote, Invited Lectures, Progress Reports and Contributed Papers; August 23-27, 2021; Belgrade (2021):173,
https://hdl.handle.net/21.15107/rcub_vinar_10918 .

TY  - JOUR
AU  - Đorđević, Кatarina Lj.
AU  - Galović, Slobodanka
AU  - Jordović-Pavlović, Miroslava I.
AU  - Ćojbašić, Žarko М.
AU  - Markushev, Dragan D.
PY  - 2021
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/9581
AB  - 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. © 2020, Springer Nature B.V.
T2  - Silicon
T1  - Improvement of Neural Networks Applied to Photoacoustic Signals of Semiconductors with Added Noise
VL  - 13
IS  - 9
SP  - 2959
EP  - 2969
DO  - 10.1007/s12633-020-00606-y
ER  - 

@article{
author = "Đorđević, Кatarina Lj. and Galović, Slobodanka and Jordović-Pavlović, Miroslava I. and Ćojbašić, Žarko М. and Markushev, Dragan D.",
year = "2021",
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. © 2020, Springer Nature B.V.",
journal = "Silicon",
title = "Improvement of Neural Networks Applied to Photoacoustic Signals of Semiconductors with Added Noise",
volume = "13",
number = "9",
pages = "2959-2969",
doi = "10.1007/s12633-020-00606-y"
}

Đorđević, К. Lj., Galović, S., Jordović-Pavlović, M. I., Ćojbašić, Ž. М.,& Markushev, D. D.. (2021). Improvement of Neural Networks Applied to Photoacoustic Signals of Semiconductors with Added Noise. in Silicon, 13(9), 2959-2969.
https://doi.org/10.1007/s12633-020-00606-y

Đorđević КL, Galović S, Jordović-Pavlović MI, Ćojbašić ŽМ, Markushev DD. Improvement of Neural Networks Applied to Photoacoustic Signals of Semiconductors with Added Noise. in Silicon. 2021;13(9):2959-2969.
doi:10.1007/s12633-020-00606-y .

Đorđević, Кatarina Lj., Galović, Slobodanka, Jordović-Pavlović, Miroslava I., Ćojbašić, Žarko М., Markushev, Dragan D., "Improvement of Neural Networks Applied to Photoacoustic Signals of Semiconductors with Added Noise" in Silicon, 13, no. 9 (2021):2959-2969,
https://doi.org/10.1007/s12633-020-00606-y . .

TY  - JOUR
AU  - Jordović-Pavlović, Miroslava I.
AU  - Markushev, Dragan D.
AU  - Kupusinac, Aleksandar
AU  - Đorđević, Katarina Lj.
AU  - Nešić, Mioljub V.
AU  - Galović, Slobodanka
AU  - Popović, Marica N.
PY  - 2020
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8912
AB  - In this paper, a methodology for the application of neural networks in phase-match calibration of gas–microphone photoacoustics in frequency domain is developed. A two-layer deep neural network is used to determine, in real-time, reliably and accurately, the phase transfer function of the used microphone, applying the photoacoustic response of aluminum as reference material. This transfer function was used to correct the photoacoustic response of laser-sintered polyamide and to compare it with theoretical predictions. The obtained degree of correlation of the corrected and theoretical signal tells us that our method of phase-match calibration in photoacoustics can be generalized to a photoacoustic response coming from a solid sample made of different materials.
T2  - International Journal of Thermophysics
T1  - Deep Neural Network Application in the Phase-Match Calibration of Gas–Microphone Photoacoustics
VL  - 41
IS  - 6
SP  - 73
DO  - 10.1007/s10765-020-02650-7
ER  - 

@article{
author = "Jordović-Pavlović, Miroslava I. and Markushev, Dragan D. and Kupusinac, Aleksandar and Đorđević, Katarina Lj. and Nešić, Mioljub V. and Galović, Slobodanka and Popović, Marica N.",
year = "2020",
abstract = "In this paper, a methodology for the application of neural networks in phase-match calibration of gas–microphone photoacoustics in frequency domain is developed. A two-layer deep neural network is used to determine, in real-time, reliably and accurately, the phase transfer function of the used microphone, applying the photoacoustic response of aluminum as reference material. This transfer function was used to correct the photoacoustic response of laser-sintered polyamide and to compare it with theoretical predictions. The obtained degree of correlation of the corrected and theoretical signal tells us that our method of phase-match calibration in photoacoustics can be generalized to a photoacoustic response coming from a solid sample made of different materials.",
journal = "International Journal of Thermophysics",
title = "Deep Neural Network Application in the Phase-Match Calibration of Gas–Microphone Photoacoustics",
volume = "41",
number = "6",
pages = "73",
doi = "10.1007/s10765-020-02650-7"
}

Jordović-Pavlović, M. I., Markushev, D. D., Kupusinac, A., Đorđević, K. Lj., Nešić, M. V., Galović, S.,& Popović, M. N.. (2020). Deep Neural Network Application in the Phase-Match Calibration of Gas–Microphone Photoacoustics. in International Journal of Thermophysics, 41(6), 73.
https://doi.org/10.1007/s10765-020-02650-7

Jordović-Pavlović MI, Markushev DD, Kupusinac A, Đorđević KL, Nešić MV, Galović S, Popović MN. Deep Neural Network Application in the Phase-Match Calibration of Gas–Microphone Photoacoustics. in International Journal of Thermophysics. 2020;41(6):73.
doi:10.1007/s10765-020-02650-7 .

Jordović-Pavlović, Miroslava I., Markushev, Dragan D., Kupusinac, Aleksandar, Đorđević, Katarina Lj., Nešić, Mioljub V., Galović, Slobodanka, Popović, Marica N., "Deep Neural Network Application in the Phase-Match Calibration of Gas–Microphone Photoacoustics" in International Journal of Thermophysics, 41, no. 6 (2020):73,
https://doi.org/10.1007/s10765-020-02650-7 . .

TY  - JOUR
AU  - Đorđević, Katarina Lj.
AU  - Galović, Slobodanka
AU  - Jordović-Pavlović, Miroslava I.
AU  - Nešić, Mioljub V.
AU  - Popović, Marica N.
AU  - Ćojbašić, Žarko М.
AU  - Markushev, Dragan D.
PY  - 2020
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8972
AB  - This paper introduces the possibility of the determination of optical absorption and reflexivity coefficient of silicon samples using neural networks and reverse-back procedure based on the photoacoustics response in the frequency domain. Differences between neural network predictions and parameters obtained with standard photoacoustic signal correction procedures are used to adjust our experimental set-up due to the instability of the optical excitation source and the state (contamination) of the illuminated surface. It has been shown that the changes of the optical absorption values correspond to the light source wavelength fluctuations, while changes in the reflexivity coefficient, obtained in this way, correspond to the small effect of the ultrathin layer formation of SiO2 due to the natural process of surface oxidation.
T2  - Optical and Quantum Electronics
T1  - Photoacoustic optical semiconductor characterization based on machine learning and reverse-back procedure
VL  - 52
IS  - 5
SP  - 247
DO  - 10.1007/s11082-020-02373-x
ER  - 

@article{
author = "Đorđević, Katarina Lj. and Galović, Slobodanka and Jordović-Pavlović, Miroslava I. and Nešić, Mioljub V. and Popović, Marica N. and Ćojbašić, Žarko М. and Markushev, Dragan D.",
year = "2020",
abstract = "This paper introduces the possibility of the determination of optical absorption and reflexivity coefficient of silicon samples using neural networks and reverse-back procedure based on the photoacoustics response in the frequency domain. Differences between neural network predictions and parameters obtained with standard photoacoustic signal correction procedures are used to adjust our experimental set-up due to the instability of the optical excitation source and the state (contamination) of the illuminated surface. It has been shown that the changes of the optical absorption values correspond to the light source wavelength fluctuations, while changes in the reflexivity coefficient, obtained in this way, correspond to the small effect of the ultrathin layer formation of SiO2 due to the natural process of surface oxidation.",
journal = "Optical and Quantum Electronics",
title = "Photoacoustic optical semiconductor characterization based on machine learning and reverse-back procedure",
volume = "52",
number = "5",
pages = "247",
doi = "10.1007/s11082-020-02373-x"
}

Đorđević, K. Lj., Galović, S., Jordović-Pavlović, M. I., Nešić, M. V., Popović, M. N., Ćojbašić, Ž. М.,& Markushev, D. D.. (2020). Photoacoustic optical semiconductor characterization based on machine learning and reverse-back procedure. in Optical and Quantum Electronics, 52(5), 247.
https://doi.org/10.1007/s11082-020-02373-x

Đorđević KL, Galović S, Jordović-Pavlović MI, Nešić MV, Popović MN, Ćojbašić ŽМ, Markushev DD. Photoacoustic optical semiconductor characterization based on machine learning and reverse-back procedure. in Optical and Quantum Electronics. 2020;52(5):247.
doi:10.1007/s11082-020-02373-x .

Đorđević, Katarina Lj., Galović, Slobodanka, Jordović-Pavlović, Miroslava I., Nešić, Mioljub V., Popović, Marica N., Ćojbašić, Žarko М., Markushev, Dragan D., "Photoacoustic optical semiconductor characterization based on machine learning and reverse-back procedure" in Optical and Quantum Electronics, 52, no. 5 (2020):247,
https://doi.org/10.1007/s11082-020-02373-x . .

TY  - JOUR
AU  - Jordović-Pavlović, Miroslava I.
AU  - Kupusinac, Aleksandar
AU  - Đorđević, Katarina Lj.
AU  - Galović, Slobodanka
AU  - Markushev, Dragan D.
AU  - Nešić, Mioljub V.
AU  - Popović, Marica N.
PY  - 2020
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/8982
AB  - 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.
T2  - Optical and Quantum Electronics
T1  - Computationally intelligent description of a photoacoustic detector
VL  - 52
IS  - 5
SP  - 246
DO  - 10.1007/s11082-020-02372-y
ER  - 

@article{
author = "Jordović-Pavlović, Miroslava I. and Kupusinac, Aleksandar and Đorđević, Katarina Lj. and Galović, Slobodanka and Markushev, Dragan D. and Nešić, Mioljub V. and Popović, Marica N.",
year = "2020",
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.",
journal = "Optical and Quantum Electronics",
title = "Computationally intelligent description of a photoacoustic detector",
volume = "52",
number = "5",
pages = "246",
doi = "10.1007/s11082-020-02372-y"
}

Jordović-Pavlović, M. I., Kupusinac, A., Đorđević, K. Lj., Galović, S., Markushev, D. D., Nešić, M. V.,& Popović, M. N.. (2020). Computationally intelligent description of a photoacoustic detector. in Optical and Quantum Electronics, 52(5), 246.
https://doi.org/10.1007/s11082-020-02372-y

Jordović-Pavlović MI, Kupusinac A, Đorđević KL, Galović S, Markushev DD, Nešić MV, Popović MN. Computationally intelligent description of a photoacoustic detector. in Optical and Quantum Electronics. 2020;52(5):246.
doi:10.1007/s11082-020-02372-y .

Jordović-Pavlović, Miroslava I., Kupusinac, Aleksandar, Đorđević, Katarina Lj., Galović, Slobodanka, Markushev, Dragan D., Nešić, Mioljub V., Popović, Marica N., "Computationally intelligent description of a photoacoustic detector" in Optical and Quantum Electronics, 52, no. 5 (2020):246,
https://doi.org/10.1007/s11082-020-02372-y . .

TY  - JOUR
AU  - Jordović-Pavlović, Miroslava I.
AU  - Stanković, Milena M.
AU  - Popović, Marica N.
AU  - Ćojbašić, Žarko М.
AU  - Galović, Slobodanka
AU  - Markushev, Dragan D.
PY  - 2020
UR  - https://vinar.vin.bg.ac.rs/handle/123456789/9005
AB  - An analysis of the application of neural networks as a reliable, precise, and fast tool in open-cell photoacoustics setups for the recognition of microphone effects in the frequency domain from 10 Hz to 100 × 104 Hz is presented. The network is trained to achieve simultaneous recognition of microphone characteristics, which are the most important parameters leading to the distortion of photoacoustic signals in both amplitude and phase. The training is carried out using a theoretically obtained database of amplitudes and phases as the input and five microphone characteristics as the output, based on transmission measurements obtained using an open photoacoustic cell setup. The results show that the network can precisely and reliably interpolate the output to recognize microphone characteristics including electronic effects in the low and acoustic effects in the high frequency domain. The simulations reveal that the network is not capable of interpolating an input including modulation frequencies. Consequently, in real applications, the network training must be adapted to the experimental frequencies, or vice versa. The total number of frequencies used in the experiment must also be in accordance with the total number of frequencies used in the network training.
T2  - Journal of Computational Electronics
T1  - The application of artificial neural networks in solid-state photoacoustics for the recognition of microphone response effects in the frequency domain
VL  - 19
IS  - 3
SP  - 1268
EP  - 1280
DO  - 10.1007/s10825-020-01507-4
ER  - 

@article{
author = "Jordović-Pavlović, Miroslava I. and Stanković, Milena M. and Popović, Marica N. and Ćojbašić, Žarko М. and Galović, Slobodanka and Markushev, Dragan D.",
year = "2020",
abstract = "An analysis of the application of neural networks as a reliable, precise, and fast tool in open-cell photoacoustics setups for the recognition of microphone effects in the frequency domain from 10 Hz to 100 × 104 Hz is presented. The network is trained to achieve simultaneous recognition of microphone characteristics, which are the most important parameters leading to the distortion of photoacoustic signals in both amplitude and phase. The training is carried out using a theoretically obtained database of amplitudes and phases as the input and five microphone characteristics as the output, based on transmission measurements obtained using an open photoacoustic cell setup. The results show that the network can precisely and reliably interpolate the output to recognize microphone characteristics including electronic effects in the low and acoustic effects in the high frequency domain. The simulations reveal that the network is not capable of interpolating an input including modulation frequencies. Consequently, in real applications, the network training must be adapted to the experimental frequencies, or vice versa. The total number of frequencies used in the experiment must also be in accordance with the total number of frequencies used in the network training.",
journal = "Journal of Computational Electronics",
title = "The application of artificial neural networks in solid-state photoacoustics for the recognition of microphone response effects in the frequency domain",
volume = "19",
number = "3",
pages = "1268-1280",
doi = "10.1007/s10825-020-01507-4"
}

Jordović-Pavlović, M. I., Stanković, M. M., Popović, M. N., Ćojbašić, Ž. М., Galović, S.,& Markushev, D. D.. (2020). The application of artificial neural networks in solid-state photoacoustics for the recognition of microphone response effects in the frequency domain. in Journal of Computational Electronics, 19(3), 1268-1280.
https://doi.org/10.1007/s10825-020-01507-4

Jordović-Pavlović MI, Stanković MM, Popović MN, Ćojbašić ŽМ, Galović S, Markushev DD. The application of artificial neural networks in solid-state photoacoustics for the recognition of microphone response effects in the frequency domain. in Journal of Computational Electronics. 2020;19(3):1268-1280.
doi:10.1007/s10825-020-01507-4 .

Jordović-Pavlović, Miroslava I., Stanković, Milena M., Popović, Marica N., Ćojbašić, Žarko М., Galović, Slobodanka, Markushev, Dragan D., "The application of artificial neural networks in solid-state photoacoustics for the recognition of microphone response effects in the frequency domain" in Journal of Computational Electronics, 19, no. 3 (2020):1268-1280,
https://doi.org/10.1007/s10825-020-01507-4 . .