Research Article
BibTex RIS Cite

BENTİK FORAMİNİFER GÖRÜNTÜ SINIFLAMASI VE TANIMLAMALARINDA EVRİŞİMLİ SİNİR AĞI (CNN) TABANLI YENİ BİR MODEL

Year 2023, Volume: 31 Issue: 1, 481 - 490, 29.04.2023
https://doi.org/10.31796/ogummf.1096951

Abstract

Canlı türlerinin yıllar içindeki değişimini gözlemlemek, gözlemlenen türlerin sağladığı bilgilerden yararlanarak çıkarımlarda bulunmak ve içinde yaşadığımız dünyanın yıllar içinde gelişen ve değişen yapısını anlamak için fosil çalışmaları büyük önem taşımaktadır. Ancak fosil örneklerinin incelenmesi ve yorumlanması karmaşık ve uzun bir süreçtir. Paleontologların çalışma yöntemlerini kolaylaştırmak için yapay zeka çalışmaları bu alana uygulanmaya başlandı. Fosil örneklerinin bilgisayar yardımıyla tespiti ve sınıflandırılması, bu işlemi manuel sınıflandırma işlemlerine kıyasla mümkün olduğunca basitleştirir ve paleontologların uzman olmadığı fosil toplulukları için dışa bağımlılığı azaltır. Bunu başarmak için, seçilen bir veri setinden 9 bentik foraminifer türü ve foraminifer olmayan örnek fotoğrafları kullanıldı. Bu çalışmada, derin evrişimli sinir ağları kullanılarak bentik foraminiferlerin sınıflandırılması için geliştirilen ve literatürdeki sonuçlardan daha yüksek doğruluğa ulaşan yeni bir yöntem sunulmaktadır. Bu yöntemle eğitilen sistemin test sonuçlarında en az %70 doğruluk oranlarına ulaşılmıştır. Yeni bir yöntemle yüksek doğruluk oranlarına ulaşan bu çalışma, mikrofosil tanımlamada yapay zeka kullanımında paleontoloji dalı için başarılı bir gelişme oluşturmuştur.

References

  • Referans1: Carvalho, L. E., Fauth, G., Fauth, S. B., Krahl, G., Moreira, A. C., Fernandes, C. P., & Von Wangenheim, A. (2020). Automated microfossil identification and segmentation using a deep learning approach. Marine Micropaleontology, 158, 101890. doi:https://doi.org/10.1016/j.marmicro.2020.101890
  • Referans2: Ge, Q., Zhong, B., Kanakiya, B., Mitra, R., Marchitto, T., & Lobaton, E. (2017, November). Coarse-to-fine foraminifera image segmentation through 3D and deep features. In 2017 IEEE Symposium series on computational intelligence (SSCI) (pp. 1-8). IEEE. doi: 10.1109/SSCI.2017.8280982
  • Referans3: Gutiérrez Lira, E., Nouboud, F., Chalifour, A., & Voisin, Y. (2018, July). Image Segmentation and Object Extraction for Automatic Diatoms Classification. In International Conference on Image and Signal Processing (pp. 55-62). Springer, Cham. doi: https://doi.org/10.1007/978-3-319-94211-7_7 Referans4: Hu, Y., Limaye, A., & Lu, J. (2020). Three-dimensional segmentation of computed tomography data using Drishti Paint: new tools and developments. Royal Society open science, 7(12), 201033. doi: https://doi.org/10.1098/rsos.201033
  • Referans5:Johansen, T. H., & Sørensen, S. A. (2020). Towards detection and classification of microscopic foraminifera using transfer learning. arXiv preprint arXiv:2001.04782. doi: https://doi.org/10.48550/arXiv.2001.04782
  • Referans6: Marchant, R., Tetard, M., Pratiwi, A., Adebayo, M., & de Garidel-Thoron, T. (2020). Automated analysis of foraminifera fossil records by image classification using a convolutional neural network. Journal of Micropalaeontology, 39(2), 183-202. doi: https://doi.org/10.5194/jm-39-183-2020
  • Referans7: Mitra, R., Marchitto, T. M., Ge, Q., Zhong, B., Kanakiya, B., Cook, M. S., ... & Lobaton, E. (2019). Automated species-level identification of planktic foraminifera using convolutional neural networks, with comparison to human performance. Marine Micropaleontology, 147, 16-24. doi: https://doi.org/10.1016/j.marmicro.2019.01.005
  • Referans8: Pawlowski, J., Esling, P., Lejzerowicz, F., Cedhagen, T., & Wilding, T. A. (2014). Environmental monitoring through protist next‐generation sequencing metabarcoding: Assessing the impact of fish farming on benthic foraminifera communities. Molecular ecology resources, 14(6), 1129-1140. doi: https://doi.org/10.1111/1755-0998.12261
  • Referans9: Platon, E., & Gupta, B. K. S. 2001. Benthic Foraminiferal Communities in Oxygen‐Depleted Environments of the Louisiana Continental Shelf. Coastal hypoxia: consequences for living resources and ecosystems, 58, 147-163. doi: https://doi.org/10.1029/CE058p0147
  • Referans10: Sakınç M. 2008. Marmara Denizi BentikForaminiferleri: Sistemaik ve Otoekoloji [Benthic Foraminifers of the Sea of Marmara: Systemic and Autoecology. Istanbul Technical University] . İstanbul Teknik Üniversitesi. S.
  • Referans11: Saraswati, P. K., & Srinivasan, M. S. 2015. Micropaleontology, Principles and applications. Springer.
  • Referans12: Xu, Y., Dai, Z., Wang, J., Li, Y., & Wang, H. (2020). Automatic recognition of palaeobios images under microscope based on machine learning. IEEE Access, 8, 172972-172981. doi: 10.1109/ACCESS.2020.3024819
  • Referans13: Zhong, B., Ge, Q., Kanakiya, B., Marchitto, R. M. T., & Lobaton, E. (2017, November). A comparative study of image classification algorithms for Foraminifera identification. In 2017 IEEE symposium series on computational intelligence (SSCI) (pp. 1-8). IEEE. doi: 10.1109/SSCI.2017.8285164

A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN)

Year 2023, Volume: 31 Issue: 1, 481 - 490, 29.04.2023
https://doi.org/10.31796/ogummf.1096951

Abstract

Fossil studies are of great importance in order to observe the change of living species over the years, to make inferences by using the information provided by the observed species, and to understand the developing and changing structure of the world we live in over the years. However, the examination and interpretation of fossil specimens is a complex and long process. Artificial intelligence studies have begun to be applied to this field in order to facilitate the working methods of paleontologists. The detection and classification of fossil specimens with the aid of computers simplifies this process as much as possible compared to manual classification processes and reduces foreign dependency for fossil assemblages for which paleontologists are not experts. To achieve this, 9 benthic foraminiferal species and non-foraminiferal sample photographs from a selected dataset were used. In this study, a new method developed for the classification of benthic foraminifera using deep convolutional neural networks, reaching higher accuracy than the results in the literature, is presented. With this method, at least 70% accuracy rates were achieved in the test results of the trained system. This study, which reached high accuracy rates with a new method, has created a successful development for the branch of paleontology in the use of artificial intelligence in microfossil identification.

References

  • Referans1: Carvalho, L. E., Fauth, G., Fauth, S. B., Krahl, G., Moreira, A. C., Fernandes, C. P., & Von Wangenheim, A. (2020). Automated microfossil identification and segmentation using a deep learning approach. Marine Micropaleontology, 158, 101890. doi:https://doi.org/10.1016/j.marmicro.2020.101890
  • Referans2: Ge, Q., Zhong, B., Kanakiya, B., Mitra, R., Marchitto, T., & Lobaton, E. (2017, November). Coarse-to-fine foraminifera image segmentation through 3D and deep features. In 2017 IEEE Symposium series on computational intelligence (SSCI) (pp. 1-8). IEEE. doi: 10.1109/SSCI.2017.8280982
  • Referans3: Gutiérrez Lira, E., Nouboud, F., Chalifour, A., & Voisin, Y. (2018, July). Image Segmentation and Object Extraction for Automatic Diatoms Classification. In International Conference on Image and Signal Processing (pp. 55-62). Springer, Cham. doi: https://doi.org/10.1007/978-3-319-94211-7_7 Referans4: Hu, Y., Limaye, A., & Lu, J. (2020). Three-dimensional segmentation of computed tomography data using Drishti Paint: new tools and developments. Royal Society open science, 7(12), 201033. doi: https://doi.org/10.1098/rsos.201033
  • Referans5:Johansen, T. H., & Sørensen, S. A. (2020). Towards detection and classification of microscopic foraminifera using transfer learning. arXiv preprint arXiv:2001.04782. doi: https://doi.org/10.48550/arXiv.2001.04782
  • Referans6: Marchant, R., Tetard, M., Pratiwi, A., Adebayo, M., & de Garidel-Thoron, T. (2020). Automated analysis of foraminifera fossil records by image classification using a convolutional neural network. Journal of Micropalaeontology, 39(2), 183-202. doi: https://doi.org/10.5194/jm-39-183-2020
  • Referans7: Mitra, R., Marchitto, T. M., Ge, Q., Zhong, B., Kanakiya, B., Cook, M. S., ... & Lobaton, E. (2019). Automated species-level identification of planktic foraminifera using convolutional neural networks, with comparison to human performance. Marine Micropaleontology, 147, 16-24. doi: https://doi.org/10.1016/j.marmicro.2019.01.005
  • Referans8: Pawlowski, J., Esling, P., Lejzerowicz, F., Cedhagen, T., & Wilding, T. A. (2014). Environmental monitoring through protist next‐generation sequencing metabarcoding: Assessing the impact of fish farming on benthic foraminifera communities. Molecular ecology resources, 14(6), 1129-1140. doi: https://doi.org/10.1111/1755-0998.12261
  • Referans9: Platon, E., & Gupta, B. K. S. 2001. Benthic Foraminiferal Communities in Oxygen‐Depleted Environments of the Louisiana Continental Shelf. Coastal hypoxia: consequences for living resources and ecosystems, 58, 147-163. doi: https://doi.org/10.1029/CE058p0147
  • Referans10: Sakınç M. 2008. Marmara Denizi BentikForaminiferleri: Sistemaik ve Otoekoloji [Benthic Foraminifers of the Sea of Marmara: Systemic and Autoecology. Istanbul Technical University] . İstanbul Teknik Üniversitesi. S.
  • Referans11: Saraswati, P. K., & Srinivasan, M. S. 2015. Micropaleontology, Principles and applications. Springer.
  • Referans12: Xu, Y., Dai, Z., Wang, J., Li, Y., & Wang, H. (2020). Automatic recognition of palaeobios images under microscope based on machine learning. IEEE Access, 8, 172972-172981. doi: 10.1109/ACCESS.2020.3024819
  • Referans13: Zhong, B., Ge, Q., Kanakiya, B., Marchitto, R. M. T., & Lobaton, E. (2017, November). A comparative study of image classification algorithms for Foraminifera identification. In 2017 IEEE symposium series on computational intelligence (SSCI) (pp. 1-8). IEEE. doi: 10.1109/SSCI.2017.8285164
There are 12 citations in total.

Details

Primary Language English
Subjects Computer Software, Geological Sciences and Engineering (Other)
Journal Section Research Articles
Authors

Kübra Yayan 0000-0001-7003-6437

Uğur Yayan 0000-0003-1394-5209

Early Pub Date April 27, 2023
Publication Date April 29, 2023
Acceptance Date December 15, 2022
Published in Issue Year 2023 Volume: 31 Issue: 1

Cite

APA Yayan, K., & Yayan, U. (2023). A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN). Eskişehir Osmangazi Üniversitesi Mühendislik Ve Mimarlık Fakültesi Dergisi, 31(1), 481-490. https://doi.org/10.31796/ogummf.1096951
AMA Yayan K, Yayan U. A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN). ESOGÜ Müh Mim Fak Derg. April 2023;31(1):481-490. doi:10.31796/ogummf.1096951
Chicago Yayan, Kübra, and Uğur Yayan. “A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN)”. Eskişehir Osmangazi Üniversitesi Mühendislik Ve Mimarlık Fakültesi Dergisi 31, no. 1 (April 2023): 481-90. https://doi.org/10.31796/ogummf.1096951.
EndNote Yayan K, Yayan U (April 1, 2023) A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN). Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi 31 1 481–490.
IEEE K. Yayan and U. Yayan, “A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN)”, ESOGÜ Müh Mim Fak Derg, vol. 31, no. 1, pp. 481–490, 2023, doi: 10.31796/ogummf.1096951.
ISNAD Yayan, Kübra - Yayan, Uğur. “A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN)”. Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi 31/1 (April 2023), 481-490. https://doi.org/10.31796/ogummf.1096951.
JAMA Yayan K, Yayan U. A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN). ESOGÜ Müh Mim Fak Derg. 2023;31:481–490.
MLA Yayan, Kübra and Uğur Yayan. “A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN)”. Eskişehir Osmangazi Üniversitesi Mühendislik Ve Mimarlık Fakültesi Dergisi, vol. 31, no. 1, 2023, pp. 481-90, doi:10.31796/ogummf.1096951.
Vancouver Yayan K, Yayan U. A NEW MODEL ON BENTHIC FORAMINIFER IMAGE CLASSIFICATION AND DEFINITIONS BASED ON CONVENTIONAL NEURAL NETWORK (CNN). ESOGÜ Müh Mim Fak Derg. 2023;31(1):481-90.

20873  13565  13566 15461  13568    14913