Hesaplamalı Arşiv Bilimi ile Görüntü Sınıflandırma ve Dijital Provenans

Yıl 2025, Cilt: 8 Sayı: 2, 244 - 283, 31.12.2025

Mehmet Oytun Cibaroğlu

https://doi.org/10.33721/by.1772464

Öz

Arşiv bilimi; büyük veri ve yapay zekâ odaklı oldukça geniş çaplı bir dönüşümün içinde yer almaya başlamıştır. Bu doğrultuda hesaplamalı arşiv bilimi adı verilen yeni bir paradigma ortaya çıkmıştır. Bu alan, bilgisayar bilimi ile arşiv biliminin kolektif bilgisini birleştirerek dijital arşiv materyallerinin analizi, uzun süreli korunması ve erişimi için hesaplamalı yöntemler sunmaktadır. Bu çalışmada, hesaplamalı arşiv biliminin temel yaklaşımları benimsenerek; yapılandırılmamış (uydu tarafından çekilen yer görüntüleri) dijital arşiv veri seti üzerinde transfer öğrenmesi bazlı sınıflandırma görevi gerçekleştirilmiş, hesaplamalı süreçlere ait provenans verisi oluşturulmuş ve tüm çıktılar, Archivematica programı aracılığıyla uzun süreli dijital korumaya alınmıştır. Transfer öğrenmesi kapsamında ise EfficientNet mimarisinin (B0-B3, V2B0-V2B3) 8 farklı varyantı kullanılmış, öncelikle ağırlıksız olarak eğitilen temel modellerin, sonrasında Keras Tuner RandomSearch tekniği ile en iyi hiperparametre aramaları yapılarak başarımları geliştirilmeye çalışılmıştır. Optimize edilen modellerde B3, V2B2 ve V2B3 varyantları %97,20 doğruluk ve sırasıyla 0,9713, 0,9716 ve 0,9718 F1 skorları ile en iyi sonucu vermiştir. Tüm hesaplamalı süreçler, JSON formatında provenans verisi olarak yapılandırılmış; analizlere dair işlem bilgileri, kullanılan yöntemler, hiperparametreler ve çıktılar zaman damgalı şekilde kayıt altına alınmıştır. Örnek olarak seçilen EfficientNetB3 modelinin analiz süreçleri, BagIt kütüphanesi ile paketlenmiş, orijinal veri setiyle birlikte Archivematica sistemine yüklenmiş ve burada SIP, AIP ve DIP paketlerine dönüştürülerek uzun süreli koruma sağlanmıştır. Çalışmanın özgünlüğü, sadece hesaplamalı modeller oluşturulması ile sınırlı kalmamakta olup aynı zamanda bu süreçlerin arşivsel bağlamda belgelenmesi, versiyonlanması ve korunması hedeflerini de içermesi ile diğer çalışmalardan ayrışmaktadır.

Anahtar Kelimeler

Hesaplamalı Arşiv Bilimi , Derin Öğrenme , Transfer Öğrenmesi

Image Classification and Digital Provenance with Computational Archival Science

Öz

Archival science has begun to take part in a large-scale transformation driven by big data and artificial intelligence. In this regard, a new paradigm called computational archival science has emerged. This field combines the collective knowledge of computer science and archival science to provide computational methods for the analysis, long-term preservation, and accessibility of digital archival materials. In this study, by adopting the fundamental approaches of computational archival science, a transfer learning–based classification task was carried out on an unstructured digital archival dataset (satellite-captured land imagery). Provenance data related to the computational processes were generated, and all outputs were preserved for the long term through the Archivematica platform. Within the scope of transfer learning, eight variants of the EfficientNet architecture (B0-B3, V2B0-V2B3) were employed. Initially, the base models were trained without pre-trained weights, after which Keras Tuner’s RandomSearch technique was applied to optimize hyperparameters and improve performance. Among the optimized models, the B3, V2B2, and V2B3 variants yielded the best results, achieving an accuracy of 97.20% and F1 scores of 0,9713, 0,9716, and 0,9718, respectively. All computational processes were structured as provenance data in JSON format; details of operations, methods used, hyperparameters, and outputs were recorded with time stamps. As a case example, the analysis workflow of the EfficientNetB3 model was packaged with the BagIt library, together with the original and derivative datasets, uploaded into the Archivematica system, and transformed into SIP, AIP, and DIP packages to ensure long-term digital preservation. The originality of the study is not limited to creating computational models only, but also distinguishes it from other studies by including the goals of recording, versioning and preserving these processes in an archival context.

Anahtar Kelimeler

Computational Archival Science , Deep Learning , Transfer Learning

Kaynakça

• Akmon, D., Zimmerman, A. ve Daniels, M. (2011). The application of archival concepts to a data-intensive environment: working with scientists to understand data management and preservation needs. Archival Science, 11, 329-348. [https://doi.org/10.1007/s10502-011-9151-4](https://doi.org/10.1007/s10502-011-9151-4)
• Alhichri, H. vd. (2021). Classification of remote sensing images using Efficientnet-B3 CNN model with attention. IEEE Access, 9, 14078-14094. [https://doi.org/10.1109/ACCESS.2021.3051085](https://doi.org/10.1109/ACCESS.2021.3051085)
• Alvarado, R.C. (2023). Data Science from 1963 to 2012. ArXiv: 2311.03292, 1-48. [https://doi.org/10.48550/arXiv.2311.03292](https://doi.org/10.48550/arXiv.2311.03292)
• Ambacher, B. ve Conrad, M. (2021). Computational archival science is a two-way street. In 2021 IEEE International Conference on Big Data, 2192-2199. [https://doi.org/10.1109/BigData52589.2021.9671873](https://doi.org/10.1109/BigData52589.2021.9671873)
• Anwer, R.M. (2018). Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification. ISPRS Journal of Photogrammetry and Remote Sensing, 138, 74-85. [https://doi.org/10.1016/j.isprsjprs.2018.01.023](https://doi.org/10.1016/j.isprsjprs.2018.01.023)
• Archivematica. (2025). Ingest. [https://www.archivematica.org/en/docs/archivematica-1.12/user-manual/ingest/ingest/#create-sip](https://www.archivematica.org/en/docs/archivematica-1.12/user-manual/ingest/ingest/#create-sip)
• Archivematica Documentation. (2025). Getting started. [https://www.archivematica.org/en/docs/archivematica-1.12/](https://www.archivematica.org/en/docs/archivematica-1.12/)
• Bahri, A. (2020). Remote sensing image classification via improved cross-entropy loss and transfer learning strategy based on deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 17(6), 1087-1091. [https://doi.org/10.1109/LGRS.2019.2937872](https://doi.org/10.1109/LGRS.2019.2937872)
• Bak, G. (2024). Digital provenance. Archival Science, 24, 847-869. [https://doi.org/10.1007/s10502-024-09462-w](https://doi.org/10.1007/s10502-024-09462-w)
• Barclay, I. vd. (2020). Certifying provenance of scientific datasets with self-sovereign identity and verifiable credentials. ArXiv, 1-6. [https://doi.org/10.48550/arXiv.2004.02796](https://doi.org/10.48550/arXiv.2004.02796)
• Bi, Q. vd. (2020). RADC-Net: A residual attention based convolution network for aerial scene classification. Neurocomputing, 377, 345-359. [https://doi.org/10.1016/j.neucom.2019.11.068](https://doi.org/10.1016/j.neucom.2019.11.068)
• Bietti, A. vd. (2019). A kernel perspective for regularizing deep neural networks. ArXiv:1810.00363, 1-20. [https://doi.org/10.48550/arXiv.1810.00363](https://doi.org/10.48550/arXiv.1810.00363)
• Binici, K. (2019). Makine Öğrenmesi Yaklaşımıyla e-Belgelere Standart Dosya Plan Numaralarının Otomatik Olarak Atanması Üzerine Bir Çalışma. Bilgi Yönetimi, 2(2), 116-126, [https://doi.org/10.33721/by.654464](https://doi.org/10.33721/by.654464)
• Bogosavljevic, M. (2018). Digitization in archives - archivematica, the practical review of the software for managing archival records on the example of the personal fonds rista odavic at the archives of serbia. Journal of Archival Theory and Practice, 1(1), 233-248.
• Brenneke, A. (1968). Archivistica: Contributo alla teoria ed alla storia archivistica Europea. Giuffrè.
• Bunn, J. (2016). Archival description and automation: a brief history of going digital. Archives and Records, 37(1), 65-78. [https://doi.org/10.1080/23257962.2016.1145577](https://doi.org/10.1080/23257962.2016.1145577)
• Cao, R. vd. (2021). Self-attention-based deep feature fusion for remote sensing scene classification. IEEE Geoscience and Remote Sensing Letters, 18(1), 43-47. 10.1109/LGRS.2020.2968550
• Carter, K.S. vd. (2022). Using AI and ML to optimize information discovery in under‑utilized, holocaust‑related records. AI & Society, 37, 837-858. [https://doi.org/10.1007/s00146-021-01368-w](https://doi.org/10.1007/s00146-021-01368-w)
• Chapman, A. vd. (2024). Supporting better ınsights of data science pipelines with fine-grained provenance. ACM Transactions on Database Systems, 49(2), 1-42. [https://doi.org/10.1145/3644385](https://doi.org/10.1145/3644385)
• Chen, C., Isa, N.A.M. ve Liu, X. (2025). A review of convolutional neural network based methods for medical image classification. Computers in Biology and Medicine, 185, 1-41. [https://doi.org/10.1016/j.compbiomed.2024.109507](https://doi.org/10.1016/j.compbiomed.2024.109507)
• Cheng, G. vd. (2018). When deep learning meets metric learning: remote sensing image scene classification via learning discriminative cnns. IEEE Transactions on Geoscience and Remote Sensing, 56(5), 2811-2821. 10.1109/TGRS.2017.2783902
• Choi, C. vd. (2022). Big-data-based text mining and social network analysis of landscape response to future environmental change. Land, 11(12), 1-21. [https://doi.org/10.3390/land11122183](https://doi.org/10.3390/land11122183)
• Ciechanowski, H.M. (2021). The principle of provenance as the principle of rationalization of archives. Archiwa, 12(14), 49-65. [https://doi.org/10.12775/AKZ.2021.003](https://doi.org/10.12775/AKZ.2021.003)
• Colavizza, G. vd. (2021). Archives and ai: An overview of current debates and future perspectives. ACM Journal on Computing and Cultural Heritage, 15(1), 1-15. [https://doi.org/10.1145/3479010](https://doi.org/10.1145/3479010)
• Cowan, L.M. (2018). Decolonizing provenance: an examination of types of provenance and their role in archiving indigenous records in canada. [Master Thesis, University of Manitoba].
• Cox, R.J. (2007). Machines in the archives: technology and the coming transformation of archival reference. First Monday, 12(11). [https://doi.org/10.5210/fm.v12i11.2029](https://doi.org/10.5210/fm.v12i11.2029)
• Curcin V. (2016). Embedding data provenance into the learning health system to facilitate reproducible research. Learning Health Systems, 1(2), 1-12. [https://doi.org/10.1002/lrh2.10019](https://doi.org/10.1002/lrh2.10019)
• Çiçek Akgün, A. ve Çiçek, N. (2022). Dijital Çağda değişen belge olgusunun arşivcilikte düzenleme ve tanımlamaya etkisi: literatüre dayalı bir inceleme. Bilgi ve Belge Araştırmaları, 17, 33-58. [https://doi.org/10.26650/bba.2022.17.1127615](https://doi.org/10.26650/bba.2022.17.1127615)
• Datta, A. vd. (2024). Survey on deep learning technique on maize leaves infected by fall armyworms. D.K. Kole, S.R. Chowdhury, S. Basu, D. Plewczynski, D. Bhattacharjee (eds.). Proceedings of 4th International Conference on Frontiers in Computing and Systems, 975 içinde (ss. 521-530). Singapore: Springer. [https://doi.org/10.1007/978-981-97-2614-1_36](https://doi.org/10.1007/978-981-97-2614-1_36)
• Davet, J., Hamidzadeh, B. ve Franks, P. (2023). Archivist in the machine: paradata for ai-based automation in the archives. Archival Science, 23, 275-295. [https://doi.org/10.1007/s10502-023-09408-8](https://doi.org/10.1007/s10502-023-09408-8)
• Delmas, B. (1993). Archival science and information technologies. A. Menne-Haritz (ed.). Information Handling in Offices and Archives içinde (ss. 168-176). München: K.G. Saur. [https://doi.org/10.1515/9783111503363.168](https://doi.org/10.1515/9783111503363.168)
• Delmas, B. (2001). Archival science facing the information society. Archival Science, 1, 25-37. [https://doi.org/10.1007/BF02435637](https://doi.org/10.1007/BF02435637)
• Douglas, J. (2017). Origins: evolving ıdeas about the principle of provenance. T. Eastwood ve H. MacNeil (eds.), Currents of Archival Thinking 2nd ed. içinde (ss. 25-52). Santa Barbara: Libraries Unlimited.
• Duranti, L. (2001). The impact of digital technology on archival science. Archival Science, 1, 39-55. [https://doi.org/10.1007/BF02435638](https://doi.org/10.1007/BF02435638)
• Duranti, L. ve Franks, P.C. (2015). Principle of provenance. Encyclopedia of Archival Science içinde (1. bs., s. 285). New York: Rowman & Littlefield.
• Ellahi, A. vd. (2023). Applying text mining and semantic network analysis to ınvestigate effects of perceived crowding in the service sector. Cogent Business & Management, 10(2), 1-18. [https://doi.org/10.1080/23311975.2023.2215566](https://doi.org/10.1080/23311975.2023.2215566)
• Feinman, R. ve Lake, B.M. (2019). Learning a smooth kernel regularizer for convolutional neural networks. arXiv:1903.01882, 1-7. [https://doi.org/10.48550/arXiv.1903.01882](https://doi.org/10.48550/arXiv.1903.01882)
• Feng, H. vd. (2021). Retrospect and prospect: the research landscape of archival studies. Archival Science, 21, 391-411. [https://doi.org/10.1007/s10502-021-09364-1](https://doi.org/10.1007/s10502-021-09364-1)
• Fuhrmeister, C. ve Hopp, M. (2019). Rethinking provenance research. Getty Research Journal, 11, 213-231.
• Gbeassor, L.A. (2024). Data as the new oil: extractivism in neptune frost. Matatu, 55(2), 249-277. [https://doi.org/10.1163/18757421-bja00011](https://doi.org/10.1163/18757421-bja00011)
• Gedikli, M.E. (2023). Elektronik Belge Yönetim Sistemlerinde Veri Madenciliği ve Makine Öğrenmesi Yöntemlerinin Kullanımı. [Doktora tezi, Marmara Üniversitesi].
• Goynov, M. vd. (2024). CultIS: web-based platform for intelligent cultural content management. Digital Presentation and Preservation of Cultural and Scientific Heritage, 14, 19-36. [https://doi.org/10.55630/dipp.2024.14.1](https://doi.org/10.55630/dipp.2024.14.1)
• Groth, P. vd. (2012). Requirements for provenance on the web. International Journal of Digital Curation, 7(1), 39-56. [https://doi.org/10.2218/ijdc.v7i1.213](https://doi.org/10.2218/ijdc.v7i1.213)
• Guimarães, J.A.C. ve Tognoli, N.B. (2015). Provenance as a domain analysis approach in archival knowledge organization. Knowledge Organization, 42(8), 562-569.
• Gündüz, G. ve Cedimoğlu, İ.H. (2019). Derin öğrenme algoritmalarını kullanarak görüntüden cinsiyet tahmini. Sakarya University Journal of Computer and Information Sciences, 2(1), 9-17. [https://doi.org/10.35377/saucis.02.01.517930](https://doi.org/10.35377/saucis.02.01.517930)
• Hassan, E. vd. (2023). The Effect of choosing optimizer algorithms to ımprove computer vision tasks: a comparative study. Multimedia Tools and Applications, 82, 16591-16633. [https://doi.org/10.1007/s11042-022-13820-0](https://doi.org/10.1007/s11042-022-13820-0)
• He, K. vd. (2015). Deep residual learning for image recognition. ArXiv:1512.03385, 1-12. [https://doi.org/10.48550/arXiv.1512.03385](https://doi.org/10.48550/arXiv.1512.03385)
• Horsman, P. (1994). Taming the Elephant: An Orthodox approach to the principle of provenance. A. Kerstin ve J. Sydbeck (eds.). The Principle of Provenance: Report from the First Stockholm Conference on the Archival of Principle of Provenance içinde (ss. 51-63), Stockholm: Swedish National Archives.
• Hutchinson, T. (2018). Protecting Privacy in the archives: supervised machine learning and born digital records. Proceedings of 2018 IEEE International Conference on Big Data, 2696-2701. 10.1109/BigData.2018.8621929
• Hutchinson, T. (2020). Natural language processing and machine learning as practical toolsets for archival processing. Records Management Journal, 30(2), 155-174. [http://dx.doi.org/10.1108/RMJ-09-2019-0055](http://dx.doi.org/10.1108/RMJ-09-2019-0055)
• IIemobayo, J.A. vd. (2024). Hyperparameter tuning in machine learning: a comprehensive review. Journal of Engineering Research and Reports, 26(6), 388-395. [https://doi.org/10.9734/jerr/2024/v26i61188](https://doi.org/10.9734/jerr/2024/v26i61188)
• İnik, Ö. (2023). Classification of scenes in aerial images with deep learning models. Türk Doğa ve Fen Dergisi, 12(1), 37-43. [https://doi.org/10.46810/tdfd.1225756](https://doi.org/10.46810/tdfd.1225756)
• Jin, P. vd. (2018). AID++: an updated version of aıd on scene classifıcation. ArXiv:1806.00801, 1-4. [https://doi.org/10.48550/arXiv.1806.00801](https://doi.org/10.48550/arXiv.1806.00801)
• Karakaş, H.S., Rukancı, F. ve Anameriç, H. (2009). Organik yöntem (provenance). Belge Yönetimi ve Arşiv Terimleri Sözlüğü içinde (1.bs., s. 35). Ankara: Başbakanlık Basımevi.
• Khatri, S. vd. (2023). A deep learning approach for detection of disease in plant leaves. A.K. Das, J. Nayak, B. Naik, S. Vimal, D. Pelusi (eds.). Computational Intelligence in Pattern Recognition 725 içinde (ss. 169-181). Singapore: Springer. [https://doi.org/10.1007/978-981-99-3734-9_15](https://doi.org/10.1007/978-981-99-3734-9_15)
• Krizhevsky, A., Sutskever, I. ve Hinton, G. (2012). ImageNet classification with deep convolutional neural networks. F. Pereira, C.J. Burges, L. Bottou, K.Q. Weinberger (eds.). Advances in Neural Information Processing Systems 25 içinde (ss. 1097-1105). New York: Morgan Kaufmann Publishers.
• Lee, M. vd. (2017). Heuristics for assessing computational archival science (cas) research: the case of the human face of big data project. 2017 IEEE International Conference on Big Data, 2262-2270. 10.1109/BigData.2017.8258179
• Levine, B.N. ve Liberatore, M. (2009). DEX: digital evidence provenance supporting reproducibility and comparison. Digital Investigation, 6, 48-56. [https://doi.org/10.1016/j.diin.2009.06.011](https://doi.org/10.1016/j.diin.2009.06.011)
• Li, J. (2022). Design of an effective archive management system with a compression approach for network information technology. Wireless Communications and Mobile Computing, 1, 1-10. [https://doi.org/10.1155/2022/3503841](https://doi.org/10.1155/2022/3503841)
• Liang, Y. vd. (2024). Multi-dimensional adaptive learning rate gradient descent optimization algorithm for network training in magneto-optical defect detection. International Journal of Network Dynamics and Intelligence, 3(3), 1-14. [https://doi.org/10.53941/ijndi.2024.100016](https://doi.org/10.53941/ijndi.2024.100016)
• MacNeil, H. (2008). Archivalterity: Rethinking Original Order. Archivaria, 66, 1-24.
• Marciano, R. vd. (2018). Archival records and training in the age of big data. J. Purcell, L.C. Sarin, P.T. Jaeger, J.C. Bertot (eds.), Re-Envisioning the MLS: Perspectives on the Future of Library and Information Science Education Advances in Librarianship, Volume 44B içinde (ss. 179-199). West Yorkshire: Emerald Publishing. [https://doi.org/10.1108/S0065-28302018000044B010](https://doi.org/10.1108/S0065-28302018000044B010)
• Marciano, R., Jansen, G. ve Underwood, W. (2020). Developing a framework to enable collaboration in computational archival science education. [https://www2.archivists.org/sites/all/files/Research_Forum%20_2019_Marciano_final.pdf](https://www2.archivists.org/sites/all/files/Research_Forum%20_2019_Marciano_final.pdf)
• Massari, A. vd. (2023). Representing Provenance and track changes of cultural heritage metadata in RDF: a survey of existing approaches. ArXiv, 1-23. [https://doi.org/10.48550/arXiv.2305.08477](https://doi.org/10.48550/arXiv.2305.08477)
• Meehan, J. (2009). Making the leap from parts to whole: evidence and inference in archival arrangement and description. The American Archivist, 72(1): 72-90. [https://doi.org/10.17723/aarc.72.1.kj672v4907m11x66](https://doi.org/10.17723/aarc.72.1.kj672v4907m11x66)
• Meurers, T. vd. (2021). A Scalable software solution for anonymizing high-dimensional biomedical data. GigaScience, 10(10), 1-13. [https://doi.org/10.1093/gigascience/giab068](https://doi.org/10.1093/gigascience/giab068)
• Michetti, G. (2016). Provenance: An archival perspective. V. Lemieux (ed.). building trust in information içinde (ss. 59-68). Cham: Springer. [https://doi.org/10.1007/978-3-319-40226-0_3](https://doi.org/10.1007/978-3-319-40226-0_3)
• Missier, P. vd. (2013). Provenance and data differencing for workflow reproducibility analysis. Concurrency and Computation: Practice and Experience, 22(17), 2345-2359. [https://doi.org/10.1002/cpe.3035](https://doi.org/10.1002/cpe.3035)
• Moreau, L. (2010). The foundations for provenance on the web. Foundations and Trends in Web Science, 2(2-3), 99-241. [https://doi.org/10.1561/1800000010](https://doi.org/10.1561/1800000010)
• Navale, V. ve McAuliffe, M. (2018). Long-term preservation of biomedical research data. F1000Research, 7, 1-16. [https://doi.org/10.12688/f1000research.16015.1](https://doi.org/10.12688/f1000research.16015.1)
• Nesmith, T. (2006). Reopening Archives: bringing new contextualities into archival theory and practice. Archivaria, 60, 259-274.
• Oyedotun, O.K. vd. (2020). Going deeper with neural networks without skip connections. 2020 IEEE International Conference on Image Processing, 1756-1760. 10.1109/ICIP40778.2020.9191356
• Palmer, B., Bubendorfer, K. ve Welch, I. (2011). Verifying digital provenance in web services. 2011 Fourth IEEE International Conference on Utility and Cloud Computing, Melbourne, 445-450. 10.1109/UCC.2011.73
• Pan, S.J. ve Yang, Q. (2009). A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 22(10). 1345-1359. 10.1109/TKDE.2009.191
• Payne, N. (2018). Stirring the cauldron: redefining computational archival science (CAS) for the big data domain. 2018 IEEE International Conference on Big Data, 2743-2752. 10.1109/BigData.2018.8622594
• Pearce-Moses, R. (2005). A glossary of archives and records terminology. Chicago: Society of American Archivists.
• Peng, C. (2024). Comprehensive analysis of the impact of learning rate and dropout rate on the performance of convolutional neural networks on the CIFAR-10 dataset. Applied and Computational Engineering, 102, 183-192. [https://doi.org/10.54254/2755-2721/102/20241161](https://doi.org/10.54254/2755-2721/102/20241161)
• Possler, D., Bruns, S. ve Niemann-Lenz, J. (2019). Data is the new oil, but how do we drill ıt? - pathways to access and acquire large data sets in communication science. International Journal of Communication, 13, 3894-3911.
• Quigley, E. vd. (2021). Data is the new oil: citizen science and informed consent in an era of researchers handling of an economically valuable resource. Life Sciences, Society and Policy, 17, 1-13. [https://doi.org/10.1186/s40504-021-00118-6](https://doi.org/10.1186/s40504-021-00118-6)
• Randby, T. ve Marciano, R. (2020). Digital curation and machine learning experimentation in archives. 2020 IEEE International Conference on Big Data, 1904-1913. 10.1109/BigData50022.2020.9377788
• Rayward, W.B. (2002). A history of computer applications in libraries: prolegomena. IEEE Annals of the History of Computing, 24(2), 4-15. 10.1109/MAHC.2002.1010066
• Reyad, M., Sarhan, A. ve Arafa, M. (2023). A modified ADAM algorithm for deep neural network optimization. Neural Computing and Applications, 35, 17095-17112. [https://doi.org/10.1007/s00521-023-08568-z](https://doi.org/10.1007/s00521-023-08568-z)
• Roke, E.R. ve Tillman, R.K. (2022). Pragmatic principles for archival linked data. The American Archivist, 85(1), 173-201. [https://doi.org/10.17723/2327-9702-85.1.173](https://doi.org/10.17723/2327-9702-85.1.173)
• Runardotter, M. (2007). Information technology, archives and archivists: an interacting trinity for long-term digital preservation. [Master Thesis, Luleå University of Technology].
• Sağlık. Ö. (2021). Elektronik belge yönetimi uygulamalarındaki koşullar ışığında e-imzalı belgelerin delil değerinin arşivsel güvenilirlik açısından incelenmesi. [Doktora Tezi, İstanbul Üniversitesi].
• Schellenberg, T.R. (1965). The management of archives. New York: Columbia University Press.
• Shah, A. vd. (2016). Deep residual networks with exponential linear unit. ArXiv:1604.04112, 1-7. [https://doi.org/10.48550/arXiv.1604.04112](https://doi.org/10.48550/arXiv.1604.04112)
• Shi, G. vd. (2019). Enhance the performance of deep neural networks via L2 regularization on the ınput of activations. Neural Processing Letters, 50, 57-75. [https://doi.org/10.1007/s11063-018-9883-8](https://doi.org/10.1007/s11063-018-9883-8)
• Shinde, G. vd. (2024). AI in archival Science: a systematic review. ArXiv:2410.09086, 1-24. [https://doi.org/10.48550/arXiv.2410.09086](https://doi.org/10.48550/arXiv.2410.09086)
• Simonyan, K. ve Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. ArXiv:1409.1556, 1-14. [https://doi.org/10.48550/arXiv.1409.1556](https://doi.org/10.48550/arXiv.1409.1556)
• Sohaee, N. (2023). Error and optimism bias regularization. Journal of Big Data, 10, 1-12. [https://doi.org/10.1186/s40537-023-00685-9](https://doi.org/10.1186/s40537-023-00685-9)
• Souai, W. (2024, Haziran 15). Convolutional neural network. [https://medium.com/ubiai-nlp/convolutional-neural-network-updated-2024-130ebb6885ed](https://medium.com/ubiai-nlp/convolutional-neural-network-updated-2024-130ebb6885ed)
• Stach, C. (2023). Data is the new oil - sort of: a view on why this comparison is misleading and ıts ımplications for modern data administration. Future Internet, 15(2), 1-49. [https://doi.org/10.3390/fi15020071](https://doi.org/10.3390/fi15020071)
• Stančić, H. (2018). Computational archival science. Moderna Arhivistika, 1(2), 323-330. [https://doi.org/10.54356/ma/2018/iyln2017](https://doi.org/10.54356/ma/2018/iyln2017)
• Stephano, A.A. (2024). Recontextualization of provenance: records in contexts and the principle of provenance. Archival Science, 24, 783-800. [https://doi.org/10.1007/s10502-024-09460-y](https://doi.org/10.1007/s10502-024-09460-y)
• Sun, S. vd. (2016). On the depth of deep neural networks: a theoretical view. Proceedings of the 13rd AAAI Conference on Artificial Intelligence, 2066-2072. [https://doi.org/10.48550/arXiv.1506.05232](https://doi.org/10.48550/arXiv.1506.05232)
• Tan, M. ve Le, Q.V. (2019). EfficientNet: rethinking model scaling for convolutional neural networks. ArXiv:1905.11946, 1-11. [https://doi.org/10.48550/arXiv.1905.11946](https://doi.org/10.48550/arXiv.1905.11946)
• Thibodeau, K. (2018). Computational archival practice: towards a theory for archival engineering. 2018 IEEE International Conference on Big Data, 2753-2760. 10.1109/BigData.2018.8622174
• Tognoli, N., ve Guimarães, J.A.C. (2019). Provenance as a knowledge organization principle. Knowledge Organization, 46(7), 558-568. [https://doi.org/10.5771/0943-7444-2019-7-558](https://doi.org/10.5771/0943-7444-2019-7-558)
• Tong, W. vd. (2020). Channel-attention-based densenet network for remote sensing image scene classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 4121-4132. 10.1109/JSTARS.2020.3009352
• Trace, C.B. (2020). Maintaining records in context? disrupting the theory and practice of archival classification and arrangement. The American Archivist, 83(2), 322-372.
• Vujovic, Z. (2021). Classification model evaluation metrics. International Journal of Advanced Computer Science and Applications, 12(6), 599-606. 10.14569/IJACSA.2021.0120670
• Wang, D. vd. (2019). Comprehensive eye diagram analysis: a transfer learning approach. IEEE Photonics Journal, 11(6), 1-19. 10.1109/JPHOT.2019.2947705
• Wang, L. vd. (2023). Residual depth feature-extraction network for infrared small-target detection. Electronics, 12(12), 1-20. [https://doi.org/10.3390/electronics12122568](https://doi.org/10.3390/electronics12122568)
• Wang, Q. vd. (2019). Overview of logistic regression model analysis and application. Chinese Journal of Preventive Medicine, 53(9), 955-960. [http://dx.doi.org/10.3760/cma.j.issn.0253-9624.2019.09.018](http://dx.doi.org/10.3760/cma.j.issn.0253-9624.2019.09.018)
• Weiss, K., Khoshgoftaar, T.M. ve Wang, D. (2016). A survey of transfer learning. Journal of Big Data, 3, 1-40. [https://doi.org/10.1186/s40537-016-0043-6](https://doi.org/10.1186/s40537-016-0043-6)
• Wu, Y. ve Liu, L. (2023). Selecting and Composing learning rate policies for deep neural networks. ACM Transactions on Intelligent Systems and Technology, 14(2), 1-25. [https://doi.org/10.1145/3570508](https://doi.org/10.1145/3570508)
• Xia, G.S. vd. (2017). AID: a benchmark dataset for performance evaluation of aerial scene classification. arXiv:1608.05167, 1-25. [https://doi.org/10.48550/arXiv.1608.05167](https://doi.org/10.48550/arXiv.1608.05167)
• Xu, D. (2022). An analysis of archive digitization in the context of big data. Mobile Information Systems, 1, 1-8. [https://doi.org/10.1155/2022/1517824](https://doi.org/10.1155/2022/1517824)
• Xu, D. vd. (2021). Convergence of the RMSProp deep learning method with penalty for nonconvex optimization. Neural Networks, 139, 17-23. [https://doi.org/10.1016/j.neunet.2021.02.011](https://doi.org/10.1016/j.neunet.2021.02.011)
• Yalçınkaya, B. (2017). Elektronik belgelerin geleceği: standartlaşmaya yönelik bir model olarak üstveri. Ö. Külcü, T. Çakmak, Eroğlu, Ş. (eds.), Kamusal Alan Olarak Bilgi Merkezleri ve Yenilikçi Yaklaşımlar içinde (ss. 221-261). İstanbul: Hiperyayın.
• Yalçınkaya, B., Gedikli, M.E. ve Cibaroğlu, M.O. (2019). Elektronik Belge Yönetim Sisteminde Log Analizi: İstatistiksel Bir Değerlendirme. B. Yalçınkaya, M.A. Ünal, B. Yılmaz, F. Özdemirci (eds.). Bilgi Yönetimi ve Bilgi Güvenliği: eBelge-eArşiv-eDevlet-Bulut Bilişim-Büyük Veri-Yapay Zeka içinde (ss. 61-77). Ankara: Ankara Üniversitesi
• Yan, P. vd. (2024). A comprehensive survey of deep transfer learning for anomaly detection in industrial time series: methods, applications and directions. arXiv:2307.05638, 1-27. [https://doi.org/10.48550/arXiv.2307.05638](https://doi.org/10.48550/arXiv.2307.05638)
• Yancheva, G. (2024). A research project for mapping the digital ınitiatives of Bulgarian libraries. Digital Presentation and Preservation of Cultural and Scientific Heritage, 14, 273-280. [https://doi.org/10.55630/dipp.2024.14.26](https://doi.org/10.55630/dipp.2024.14.26)
• Yang M. vd. (2022). News text mining-based business sentiment analysis and its significance in economy. Frontiers in Psychology, 13, 1-7. 10.3389/fpsyg.2022.918447
• Yao, C. (2016). The application of computer science and technology in libraries. P. Fournier-Viger (ed.). Proceedings of the 2016 International Conference on Education, Management, Computer and Society içinde (ss. 1422-1424). 10.2991/emcs-16.2016.355
• Yeo, G. (2024). Artificial intelligence and the future(s) of archival theory and practice. Archeion, 125, 10-32. [https://doi.org/10.4467/26581264ARC.24.008.20572](https://doi.org/10.4467/26581264ARC.24.008.20572)
• Yıldız, A. (2006). Provenans sisteminin amaçları ve uygulanması. Arşiv Dünyası, 8, 7-10.
• Yi, D., Ahn, J. ve Ji, S. (2020). An effective optimization method for machine learning based on ADAM. Applied Sciences, 10(3), 1-20. [https://doi.org/10.3390/app10031073](https://doi.org/10.3390/app10031073)
• Yosinski, J. vd. (2014). How transferable are features in deep neural networks? ArXiv:1411.1792, 1-14. [https://doi.org/10.48550/arXiv.1411.1792](https://doi.org/10.48550/arXiv.1411.1792)
• Zakharov, V. (1998). Developing of a computerized information system on conservation and preservation. J. Whiffin ve J. Havermans (eds.). Library Preservation and Conservation in the ‘90s: Proceedings of the Satellite Meeting of the IFLA Section on Preservation and Conservation içinde (ss. 175-176). Berlin: De Gruyter Saur. [https://doi.org/10.1515/9783110954128.175](https://doi.org/10.1515/9783110954128.175)
• Zhao, Z. vd. (2024). A comparison review of transfer learning and self-supervised learning: definitions, applications advantages and limitations. Expert Systems with Applications, 242, 1-38. [https://doi.org/10.1016/j.eswa.2023.122807](https://doi.org/10.1016/j.eswa.2023.122807)
• Zhuang, F. vd. (2020). A comprehensive survey on transfer learning. arXiv:1911.02685, 1-31. [https://doi.org/10.48550/arXiv.1911.02685](https://doi.org/10.48550/arXiv.1911.02685)
• Zucco, C. vd. (2019). Sentiment analysis for mining texts and social networks data: Methods and tools. WIREs Data Mining and Knowledge Discovery, 10(1), 1-32. [https://doi.org/10.1002/widm.1333](https://doi.org/10.1002/widm.1333)