Jewelry rock discrimination as interpretable data using laser-induced breakdown spectroscopy and a convolutional LSTM deep learning algorithm.
Chemometrics
Convolutional LSTM
Deep learning
Jewelry rock
LIBS spectroscopy
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
02 Mar 2024
02 Mar 2024
Historique:
received:
26
09
2023
accepted:
24
02
2024
medline:
3
3
2024
pubmed:
3
3
2024
entrez:
2
3
2024
Statut:
epublish
Résumé
In this study, the deep learning algorithm of Convolutional Neural Network long short-term memory (CNN-LSTM) is used to classify various jewelry rocks such as agate, turquoise, calcites, and azure from various historical periods and styles related to Shahr-e Sokhteh. Here, the CNN-LSTM architecture includes utilizing CNN layers for the extraction of features from input data mixed with LSTMs for supporting sequence forecasting. It should be mentioned that interpretable deep learning-assisted laser induced breakdown spectroscopy helped achieve excellent performance. For the first time, this paper interprets the Convolutional LSTM effectiveness layer by layer in self-adaptively obtaining LIBS features and the quantitative data of major chemical elements in jewelry rocks. Moreover, Lasso method is applied on data as a factor for investigation of interoperability. The results demonstrated that LIBS can be essentially combined with a deep learning algorithm for the classification of different jewelry songs. The proposed methodology yielded high accuracy, confirming the effectiveness and suitability of the approach in the discrimination process.
Identifiants
pubmed: 38431680
doi: 10.1038/s41598-024-55502-x
pii: 10.1038/s41598-024-55502-x
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
5169Informations de copyright
© 2024. The Author(s).
Références
Markiewicz-Keszycka, M. et al. Laser-induced breakdown spectroscopy (LIBS) for food analysis: A review. Trends. Food. Sci. Technol. 65, 80–93 (2017).
doi: 10.1016/j.tifs.2017.05.005
Modlitbová, P., Pořízka, P. & Kaiser, J. Laser-induced breakdown spectroscopy as a promising tool in the elemental bioimaging of plant tissues, TrAC. Trends Anal. Chem. 122, 115729 (2020).
doi: 10.1016/j.trac.2019.115729
Motto-Ros, V., Koujelev, A. S., Osinski, G. R. & Dudelzak, A. E. Quantitative multi-elemental laser-induced breakdown spectroscopy using artificial neural networks. J. Eur. Opt. Soc. 3, 08011 (2008).
doi: 10.2971/jeos..08011
El Haddad, J. et al. Artificial neural network for on-site quantitative analysis of soils using laser induced breakdown spectroscopy. Spectrochim. Acta B 78, 51–57 (2013).
doi: 10.1016/j.sab.2012.11.007
Miziolek, A. W. & Palleschi, V. Laser-induced breakdown spectroscopy (LIBS) (Cambridge University Press, 2006).
doi: 10.1017/CBO9780511541261
De Giacomo, A., Gaudiuso, R., Koral, C., Dell’Aglio, M. & De Pascale, O. Nanoparticle-enhanced laser-induced breakdown spectroscopy of metallic samples. Anal. Chem. 85, 10180–10187 (2013).
doi: 10.1021/ac4016165
pubmed: 24090397
Safi, A., Bahreini, M. & Tavassoli, S. H. Comparative study of two methods of orthogonal double-pulse laser-induced breakdown spectroscopy of aluminum. Opt. Spectrosc. 120, 367–378 (2016).
doi: 10.1134/S0030400X16030024
Ciucci, A. et al. New procedure for quantitative elemental analysis by laser-induced plasma spectroscopy. Appl. Spectrosc. 53, 960–964 (1999).
doi: 10.1366/0003702991947612
Markushin, Y., Sivakumar, P., Connolly, D. & Melikechi, N. Tag-femtosecond laser-induced breakdown spectroscopy for the sensitive detection of cancer antigen 125 in blood plasma. Anal. Bioanal. Chem. 407, 1849–1855 (2015).
doi: 10.1007/s00216-014-8433-0
pubmed: 25577361
Zhao, W. et al. Interpretable deep learning-assisted laser-induced breakdown spectroscopy for brand classification of iron ores. Anal. Chim. Acta. 1166, 338574 (2021).
doi: 10.1016/j.aca.2021.338574
pubmed: 34022994
Amador-Hernández, J., Fernández-Romero, J. M. & Luque de Castro, M. D. In-depth characterization of screen-printed electrodes by laser-induced breakdown spectrometry and pattern recognition. Surf. Interface Anal. 31, 313–320 (2001).
doi: 10.1002/sia.979
Jurado-López, A. & Luque de Castro, M. D. Rank correlation of laser-induced breakdown spectroscopic data for the identification of alloys used in jewelry manufacture. Spectrochim. Acta Part B 58, 1291–1299 (2003).
doi: 10.1016/S0584-8547(03)00052-1
Hybl, J. D., Lithgow, G. A. & Buckley, S. G. Laser-induced breakdown spectroscopy detection and classification of biological aerosols. Appl. Spectrosc. 57, 1207–1215 (2003).
doi: 10.1366/000370203769699054
pubmed: 14639747
Samsek, O., Telle, H. H. & Beddows, D. C. S. Laser-induced breakdown spectroscopy: A tool for real-time, in vitro and in vivo identification of carious teeth. BMC Oral Health 1, 1–9 (2001).
doi: 10.1186/1472-6831-1-1
Sjostrom, S. & Mauchien, P. Laser atomic spectroscopic techniques—The analytical performance for trace element analysis of solid and liquid samples. Spectrochim. Acta Part B 15, 153–180 (1991).
Fangqi Ruan, T. Z. & Li, H. Laser-induced breakdown spectroscopy in archeological science: A review of its application and future perspectives. Appl. Spectrosc. Rev. 54, 573–601 (2019).
doi: 10.1080/05704928.2018.1491857
Botto, A. et al. Applications of laser-induced breakdown spectroscopy in cultural heritage and archaeology: A critical review. J. Anal. At. Spectrom. 34, 81–103 (2019).
doi: 10.1039/C8JA00319J
Gupta, R. et al. Artificial intelligence to deep learning: Machine intelligence approach for drug discovery. Mol. Divers. 25, 1315–1360 (2021).
doi: 10.1007/s11030-021-10217-3
pubmed: 33844136
pmcid: 8040371
Yang, J. et al. Deep learning for vibrational spectral analysis: Recent progress and a practical guide. Anal. Chim. Acta 1081, 6–17 (2019).
doi: 10.1016/j.aca.2019.06.012
pubmed: 31446965
Pierdicca, R. et al. Point cloud semantic segmentation using a deep learning framework for cultural heritage. Remote Sens. 12(6), 1005 (2020).
doi: 10.3390/rs12061005
Llamas, J., Lerones, P. M., Medina, R., Zalama, E. & Gómez-García-Bermejo, J. Classification of architectural heritage images using deep learning techniques. Appl. Sci. 7(10), 992 (2017).
doi: 10.3390/app7100992
Chen, T. et al. Deep learning with laser-induced breakdown spectroscopy (LIBS) for the classification of rocks based on elemental imaging. Appl. Geochem. 136, 105135 (2022).
doi: 10.1016/j.apgeochem.2021.105135
Ibrahimzadeh, I. Introduction to the historical geography of Sistan, Master thesis, Faculty of Literature and Humanities. University of Sistan and Baluchestan. Zahedan, MS thesis (1990).
Tosi, M. The cultural sequence at Shahr-i Sokhta. Bull. Asia Inst. Pahlavi Univ. 3, 64–80 (1973).
Vidale, M. & Salvatori, S. Shahr-i Sokhta, 1975–1978: Central Quarters Excavations: Preliminary Report: IsIAO (1997).
Tosi, M. Excavation at shahr-i sokhta 1969–1970. In tosi 76–126 (1983).
Seyed Sajjadi, S. M. et al. Gozaresh- ha-ye-shahr-e-sokht-e: kavoosh dar gorestan Reports of Burnt City: Excavation in Cemetery, Tehran: General Office of Cultural Affairs (2007).
Biscione, R., Bulgarelli, G. M., Costantini, L., Piperno, M. & Tosi, M. Archaeological discoveries and methdological problems in the excavations of Shahr-i Sokhta, Sitan. In South Asian Archaeology (eds van Lohuizen-De Leeun, J. E. & Ubaghs, J. M. M.) (Brill, 1974).
Tosi, M. Excavations at Shahr-i Sokhta. A chalcolithic settlement in the Iranian Sistan, preliminary report on the first campaign, October–December 1967amprdquosemicolon. East West XVIII, 9–66 (1968).
Piperno, M. & Tosi, M. The Graveyard of Shahr i sokhta, Iran. Archaeology 28, 186–197 (1975).
Piperno, M. & Salvatori, S. The Shahr-i Sokhta Graveyard (Sistan, Iran) (2007).
https://www.persiantouring.com/things-to-do/shahr-e-sukhteh .
Foglini, L. L’area di lavorazione del lapislazzuli nei quadrati EWK-EWP. In Perle orientali. Tradizione antica e artigianato moderno nella lavorazione delle pietre semipreziose in Medio Oriente, Rome (ed. Lombardo, G.) 71–75 (1998).
Nozari, H., Rezaei, F. & Tavassoli, S. H. Analysis of organic vapors with laser induced breakdown spectroscopy. Phys. Plasmas. 22, 093302 (2015).
doi: 10.1063/1.4931174
Rezaei, F. Two-lines method for estimation of plasma temperature and characterization of plasma parameters in optically thick plasma conditions. Appl. Opt. 59, 3002 (2020).
doi: 10.1364/AO.384949
pubmed: 32400582
Rezaei, F. Plasma Science and Technology: Progress in Physical States and Chemical Reactions Vol. 363 (BoD—Books on Demand, 2016).
Rezaei, F., Karimi, P. & Tavassoli, S. H. Effect of self-absorption correction on LIBS measurements by calibration curve and artificial neural network. Appl. Phys. B Lasers Opt. 114, 591–600 (2014).
doi: 10.1007/s00340-013-5566-3
Rezaei, F. & Tavassoli, S. H. Developing the model of laser ablation by considering the interplay between emission and expansion of aluminum plasma. Phys. Plasmas 20, 013301 (2013).
doi: 10.1063/1.4773036
Messaoud Aberkane, S. et al. Laser-induced breakdown spectroscopy for determination of spectral fundamental parameters. Appl. Sci. 10, 4973 (2020).
doi: 10.3390/app10144973
Bouvrie, J. Notes on Convolutional Neural Networks (Massachusetts Institute of Technology Cambridge, 2006).
Liang, M. & Hu, X. Recurrent convolutional neural network for object recognition. In IEEE Conference on Computer Vision and Pattern Recognition (2015).
Ma, L. & Tian, S. A hybrid CNN–LSTM model for aircraft 4D trajectory prediction. IEEE Access 8, 134668–134680 (2020).
doi: 10.1109/ACCESS.2020.3010963
Han, S., Mao, H. & Dally, W. J. Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding, arXiv preprint http://arxiv.org/abs/1510.00149 (2015).
Sharma, S. & Athaiya, A. Activation functions in neural networks. IJASE 4, 310–316 (2020).
Huang, Ch.-J. & Kuo, P.-H. A deep CNN–LSTM model for particulate matter (PM2.5) forecasting in smart cities. Sensors 18, 2220 (2018).
doi: 10.3390/s18072220
pubmed: 29996546
pmcid: 6069282
Graves, A. Long short-term memory. In Studies in Computational Intelligence (2012).
Malhotra, P., Vig, L., Shroff, G. & Agarwal, P. Long short term memory networks for anomaly detection in time series. In Proceedings: ESANN (2015).
Khalilian, P., Azizi, S., Amiri, M. H. & Firouzjaee, J. T. Design interpretable experience of dynamical feed forward machine learning model for forecasting NASDAQ. http://arxiv.org/abs/2212.12044v1 (2022).
Miao, H. & Ramchander, S. Influential factors in crude oil price forecasting. Energy Econ. 68, 77–88 (2017).
doi: 10.1016/j.eneco.2017.09.010
Perez, L. & Wang, J. The effectiveness of data augmentation in image classification using deep learning, arXiv preprint http://arxiv.org/abs/1712.04621 (2017).
Alex, V., KP, M. S., Chennamsetty, S. S. & Krishnamurthi, G. Generative adversarial networks for brain lesion detection. In Medical Imaging 2017: Image Processing, IJOP, Vol. 10133, 101330G (2017).
Hurtik, P., Vajgl, M. & Burda, M. Jewelry stones classification: Case study. In Conference Paper (2015).
Yan Chow, B. H. & Carlos Reyes-Aldasoro, C. Automatic gemstone classification using computer vision. Minerals 12(1), 60 (2022).
doi: 10.3390/min12010060
Singh, V. & Kaewprapha, P. A comparative experiment in classifying jewelry images using convolutional neural networks. Sci. Technol. Asia 23(4), 7–17 (2018).
Mohamad Saufi, N., Nadia Adnan, N., Rizvi, S. Z. H., Roslan, M. S., Razak, S. N., Hasim, N. & Mansor, N. I. Element identification of different gemstones by using LIBS-PCA method. In Book cover Proceedings of the 7th International Conference on the Applications of Science and Mathematics 155–163 (2021).
Zamira, A., Rizvi, S. Z. B. H., Roslan, M. S., Adnan, N. N., Razak, S. N. A. & Arif Jalil, M. A. Discrimination of precious and semi-precious gemstones using laser-induced breakdown spectroscopy and machine learning approaches. In Proceedings of the 7th International Conference on the Applications of Science and Mathematics 165–174 (2021).