Photothermal Radiometry Data Analysis by Using Machine Learning
Abstract
:1. Introduction
2. Materials and Methods
2.1. OTTER Apparatus
- Load the OTTER signal;
- Find the starting point and end point of the signal;
- Fit the entire signal with Equation (1) to get an average sample’s emission absorption coefficient β;
- Divide signal into 10 slices;
- Fit the first slice of the signal with Equation (1) to get the first β, then calculate the corresponding detection depth z;
- Fit the first and the second slice of the signal with Equation (1) to get the second β, then calculate the corresponding detection depth z;
- Repeat step 6 until all the slices are used.
2.2. Machine Learning Algorithms
2.3. Measurement Procedure
3. Results and Discussions
3.1. Regression—Homogenous Model
3.2. Regression—Non-Homogenous Model
3.3. Classification—Real OTTER Data
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Tessier, G. Photothermal Techniques. In Thermal Nanosystems and Nanomaterials; Volz, S., Ed.; Topics in Applied Physics; Springer: Berlin/Heidelberg, Germany, 2009; Volume 118. [Google Scholar] [CrossRef]
- Rosencwaig, A.; Gersho, A. Theory of the photoacoustic effect with solids. J. Appl. Phys. 1976, 47, 64. [Google Scholar] [CrossRef]
- Rosencwaig, A.; Opsal, J.; Smith, W.L.; Willenborg, D.L. Willenborg D. L. Detection of thermal waves through optical reflectance. Appl. Phys. Lett. 1985, 46, 1013. [Google Scholar] [CrossRef]
- Tam, A.C.; Sullivan, B. Remote sensing applications of pulsed photothermal radiometry. Appl. Phys. Lett. 1983, 43, 333–335. [Google Scholar] [CrossRef]
- Imhof, R.E.; Birch, D.J.S.; Thornley, F.R.; Gilchrist, J.R.; Strivens, T.A. Opto-thermal transient emission radiometry. J. Phys. E Sci. Instrum. 1984, 17, 521–525. [Google Scholar] [CrossRef]
- Imhof, R.E.; Zhang, B.; Birch, D.J.S. Photothermal Radiometry for NDE. In Progress in Photothermal and Photoacoustic Science and Technology; Mandelis, A., Ed.; PTR Prentice Hall: Englewood Cliffs, NJ, USA, 1994; Volume II, pp. 185–236. [Google Scholar]
- Imhof, R.E.; McKendrick, A.D.; Xiao, P. Thermal emission decay Fourier transform infrared spectroscopy. Rev. Sci. Instrum. 1995, 66, 5203–5213. [Google Scholar] [CrossRef]
- Thapa, D.; Welch, R.; Dabas, R.P.; Salimi, M.; Tavakolian, P.; Sivagurunathan, K.; Ngai, K.; Huang, B.; Finer, Y.; Abrams, S.; et al. Comparison of Long-Wave and Mid-Wave Infrared Imaging Modalities for Photothermal Coherence Tomography of Human Teeth. IEEE Trans. Bio-Med. Eng. 2022, 69, 2755–2766. [Google Scholar] [CrossRef] [PubMed]
- Tavakolian, P.; Mandelis, A. Perspective: Principles and specifications of photothermal imaging methodologies and their applications to non-invasive biomedical and non-destructive materials imaging. J. Appl. Phys. 2018, 124, 160903. [Google Scholar] [CrossRef]
- Sreekumar, K.; Mandelis, A. Ultra-Deep Bone Diagnostics with Fat–Skin Overlayers Using New Pulsed Photothermal Radar. Int. J. Thermophys. 2013, 34, 1481–1488. [Google Scholar] [CrossRef]
- Folorunsho, O.G.; Oloketuyi, S.F.; Mazzega, E.; Budasheva, H.; Beran, A.; Cabrini, M.; Korte, D.; Franko, M.; de Marco, A. Nanobody-Dependent Detection of Microcystis aeruginosa by ELISA and Thermal Lens Spectrometry. Appl. Biochem. Biotechnol. 2021, 193, 2729–2741. [Google Scholar] [CrossRef]
- Cabrera, H.; Goljat, L.; Korte, D.; Marín, E.; Franko, M. A multi-thermal-lens approach to evaluation of multi-pass probe beam configuration in thermal lens spectrometry. Anal. Chim. Acta 2020, 1100, 182–190. [Google Scholar] [CrossRef]
- Proskurnin, M.A.; Zhidkova, T.V.; Volkov, D.S.; Sarimollaoglu, M.; Galanzha, E.I.; Mock, D.; Nedosekin, D.A.; Zharov, V.P. In Vivo Multispectral Photoacoustic and Photothermal Flow Cytometry with Multicolor Dyes: A Potential for Real-Time Assessment of Circulation, Dye-Cell Interaction, and Blood Volume. Cytom. Part A 2011, 79A, 834847. [Google Scholar] [CrossRef] [PubMed]
- Pawlak, M. Photothermal, photocarrier, and photoluminescence phenomena in semiconductors studied using spectrally resolved modulated infrared radiometry: Physics and applications . J. Appl. Phys. 2019, 126, 150902. [Google Scholar] [CrossRef]
- Machine Learning. Available online: https://en.wikipedia.org/wiki/Machine_learning (accessed on 2 September 2023).
- Xiao, P. Artificial Intelligence Programming with Python: From Zero to Hero, 1st ed.; Wiley: Hoboken, NJ, USA, 2022; ISBN-10: 1119820863, ISBN-13: 978-1119820864. [Google Scholar]
- Verdel, N.; Tanevski, J.; Džeroski, S.; Majaron, B. Predictive model for the quantitative analysis of human skin using photothermal radiometry and diffuse reflectance spectroscopy. Biomed. Opt. Express 2020, 11, 1679–1696. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Verdel, N.; Tanevski, J.; Džeroski, S.; Majaron, B. A machine-learning model for quantitative characterization of human skin using photothermal radiometry and diffuse reflectance spectroscopy. In Proceedings of the Photonics in Dermatology and Plastic Surgery 2019, San Francisco, CA, USA, 2–7 February 2019; Volume 10851, p. 1085107. [Google Scholar] [CrossRef]
- Verdel, N.; Tanevski, J.; Džeroski, S.; Majaron, B. Hybrid technique for characterization of human skin by combining machine learning and inverse Monte Carlo approach. In Proceedings of the European Conference on Biomedical Optics 2019, Munich, Germany, 23–25 June 2019. [Google Scholar]
- SkinModel. Available online: https://github.com/jtanevski/SkinModel (accessed on 2 September 2023).
- Ahmadi, S.; Hauffen, J.C.; Ziegler, M. Photothermal-SR-Net: A Customized Deep Unfolding Neural Network for Photothermal Super Resolution Imaging. Available online: https://arxiv.org/pdf/2104.10563v1.pdf (accessed on 2 September 2023).
- Deep Unfolding Network for Image Super-Resolution. Available online: https://github.com/cszn/USRNet (accessed on 2 September 2023).
- Jawa, T.M.; Elhag, A.A.; Aloafi, T.A.; Sayed-Ahmed, N.; Bayones, F.S.; Bouslim, J. Machine Learning and Statistical Methods for Studying Voids and Photothermal Effects of a Semiconductor Rotational Medium with Thermal Relaxation Time. Math. Probl. Eng. 2022, 2022, 7205380. [Google Scholar] [CrossRef]
- Kovács, P.; Lehner, B.; Thummerer, G.; Mayr, G.; Burgholzer, P.; Huemer, M. Deep learning approaches for thermographic imaging. J. Appl. Phys. 2020, 128, 155103. [Google Scholar] [CrossRef]
- Pytorch-unet. Available online: https://github.com/jvanvugt/pytorch-unet (accessed on 2 September 2023).
- Janssens, O.; Van de Walle, R.; Loccufier, M.; Van Hoecke, S. Deep Learning for Infrared Thermal Image Based Machine Health Monitoring. IEEE/ASME Trans. Mechatron. 2018, 23, 151–159. [Google Scholar] [CrossRef]
- Keerthi, M.; Rajavignesh, R. Machine Health Monitoring Using Infrared Thermal Image by Convolution Neural Network. Available online: https://www.ijert.org/research/machine-health-monitoring-using-infrared-thermal-image-by-convolution-neural-network-IJERTCONV6IS07026.pdf (accessed on 2 September 2023).
- Chen, C.; Chandra, S.; Han, Y.; Seo, H. Deep Learning-Based Thermal Image Analysis for Pavement Defect Detection and Classification Considering Complex Pavement Conditions. Remote Sens. 2022, 14, 106. [Google Scholar] [CrossRef]
- Qu, Y.; Meng, Y.; Fan, H.; Xu, R.X. Low-cost thermal imaging with machine learning for non-invasive diagnosis and therapeutic monitoring of pneumonia. Infrared. Phys. Technol. 2022, 123, 104201. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Gajjela, C.C.; Brun, M.; Mankar, R.; Corvigno, S.; Kennedy, N.; Zhong, Y.; Liu, J.; Sood, A.K.; Mayerich, D.; Berisha, S.; et al. Leveraging Mid-Infrared Spectroscopic Imaging and Deep Learning for Tissue Subtype Classification in Ovarian Cancer. Available online: https://arxiv.org/abs/2205.09285 (accessed on 2 September 2023).
- Voti, R.L.; Sibilia, C.; Bertolotti, M. Photothermal depth profiling by Genetic Algorithms and Thermal Wave Backscattering. Int. J. Thermophys. 2005, 26, 1833–1848. [Google Scholar] [CrossRef]
- Xiao, P. The Opto-thermal Mathematical Modelling and Data Analysis in Skin Measurements. Ph.D. Thesis, London South Bank University, London, UK, 3 November 1997. [Google Scholar]
- Xiao, P. Photothermal Radiometry for Skin Research. Cosmetics 2016, 3, 10. [Google Scholar] [CrossRef]
- Zhang, X.; Bontozoglou, C.; Xiao, P. In Vivo Skin Characterizations by Using Opto-Thermal Depth-Resolved Detection Spectra. Cosmetics 2020, 6, 54. [Google Scholar] [CrossRef]
- Xiao, P.; Cowen, J.A.; Imhof, R.E. In-Vivo Transdermal Drug Diffusion Depth Profiling—A New Approach to Opto-Thermal Signal Analysis. Anal. Sci. 2001, 17, s349–s352. [Google Scholar]
- Xiao, P.; Ou, X.; Ciortea, L.I.; Berg, E.P.; Imhof, R.E. In Vivo Skin Solvent Penetration Measurements Using Opto-thermal Radiometry and Fingerprint Sensor. Int. J. Thermophys 2012, 33, 1787–1794. [Google Scholar] [CrossRef]
- Xiao, P.; Imhof, R.E. Data Analysis Technique for Pulsed Opto-Thermal Measurements. UK Patent Application 0004374.5, 25 February 2000. [Google Scholar]
- Xiao, P.; Imhof, R.E. Apparatus for in-vivo Skin Characterization. UK Patent Application GB1014212.3, 26 August 2010. [Google Scholar]
- Deep Learning. Available online: https://developer.nvidia.com/deep-learning (accessed on 2 September 2023).
- Geron, A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems; Oreilly: Sebastopol, CA, USA, 22 April 2019; ISBN 1492032646/978-1492032649. [Google Scholar]
- Lasso (Statistics). Available online: https://en.wikipedia.org/wiki/Lasso_(statistics) (accessed on 2 September 2023).
- Elastic Net Regularization. Available online: https://en.wikipedia.org/wiki/Elastic_net_regularization (accessed on 2 September 2023).
- Decision Tree. Available online: https://en.wikipedia.org/wiki/Decision_tree (accessed on 2 September 2023).
- Support Vector Machine. Available online: https://en.wikipedia.org/wiki/Support-vector_machine (accessed on 2 September 2023).
- Gradient Boosting. Available online: https://en.wikipedia.org/wiki/Gradient_boosting (accessed on 2 September 2023).
- Linear Regression. Available online: https://en.wikipedia.org/wiki/Linear_regression (accessed on 2 September 2023).
- Random Forest. Available online: https://en.wikipedia.org/wiki/Random_forest (accessed on 2 September 2023).
- K Nearest Neighbors. Available online: https://en.wikipedia.org/wiki/K-nearest_neighbors_algorithm (accessed on 2 September 2023).
- Extreme Gradient Boosting. Available online: https://en.wikipedia.org/wiki/XGBoost (accessed on 2 September 2023).
- Partial Least Squares Regression. Available online: https://en.wikipedia.org/wiki/Partial_Least_Squares_Regression (accessed on 2 September 2023).
- Voting Regression. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.VotingRegressor.html (accessed on 2 September 2023).
- RidgeCV. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.RidgeCV.html (accessed on 2 September 2023).
- Deep Learning Neural Networks. Available online: https://en.wikipedia.org/wiki/Deep_learning (accessed on 2 September 2023).
- Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016; ISBN 0262035618. ISBN-13: 978-0262035613. [Google Scholar]
- Lasso and Ridge Regression in Python. Available online: https://www.analyticsvidhya.com/blog/2016/01/ridge-lasso-regression-python-complete-tutorial (accessed on 25 January 2024).
- Gradient Descent. Available online: https://en.wikipedia.org/wiki/Gradient_descent (accessed on 25 January 2024).
- Vanishing Gradient Problem. Available online: https://en.wikipedia.org/wiki/Vanishing_gradient_problem (accessed on 25 January 2024).
- Partial Least Squares Regression (PLS). Available online: https://www.xlstat.com/en/solutions/features/partial-least-squares-regression (accessed on 25 January 2024).
- What Is Partial Least Squares Regression? Available online: https://support.minitab.com/en-us/minitab/21/help-and-how-to/statistical-modeling/regression/supporting-topics/partial-least-squares-regression/what-is-partial-least-squares-regression/ (accessed on 25 January 2024).
- Voting Regressor. Available online: https://www.geeksforgeeks.org/voting-regressor/ (accessed on 25 January 2024).
- Ensemble Learning. Available online: https://en.wikipedia.org/wiki/Ensemble_learning (accessed on 25 January 2024).
- Linear Discriminant Analysis. Available online: https://en.wikipedia.org/wiki/Linear_discriminant_analysis (accessed on 2 September 2023).
- Principal Component Analysis. Available online: https://en.wikipedia.org/wiki/Principal_component_analysis (accessed on 2 September 2023).
- SHAP Document. Available online: https://shap.readthedocs.io/en/latest/ (accessed on 25 January 2024).
- Tuning the Hyper-Parameters of an Estimator. Available online: https://scikit-learn.org/stable/modules/grid_search.html (accessed on 25 January 2024).
- Voting Classifier. Available online: https://scikit-learn.org/stable/modules/generated/sklearn.ensemble.VotingClassifier.html (accessed on 25 January 2024).
Models | Accuracy (Training) [%] | Accuracy (Test) [%] |
---|---|---|
Logistic | 100.0% | 100.0% |
Naive Bayes | 100.0% | 83.3% |
SVC | 82.4% | 83.3% |
Random Forest | 100.0% | 83.3% |
Bagging | 70.6% | 66.7% |
Ada Boost | 100.0% | 100.0% |
Gradient Boost | 100.0% | 100.0% |
Deep Learning | 88.2% | 83.3% |
LDA | 82.4% | 83.3% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Xiao, P.; Chen, D. Photothermal Radiometry Data Analysis by Using Machine Learning. Sensors 2024, 24, 3015. https://doi.org/10.3390/s24103015
Xiao P, Chen D. Photothermal Radiometry Data Analysis by Using Machine Learning. Sensors. 2024; 24(10):3015. https://doi.org/10.3390/s24103015
Chicago/Turabian StyleXiao, Perry, and Daqing Chen. 2024. "Photothermal Radiometry Data Analysis by Using Machine Learning" Sensors 24, no. 10: 3015. https://doi.org/10.3390/s24103015
APA StyleXiao, P., & Chen, D. (2024). Photothermal Radiometry Data Analysis by Using Machine Learning. Sensors, 24(10), 3015. https://doi.org/10.3390/s24103015