Artificial Intelligence and Archive Management on Malaysia National Archive’s Uncaptioned Photos Collection: Accuracy findings comparison based on clustering algorithms

W.A. Malek; Safawi A. Jalil; A. Rahman; Irwan Kamarudin; Roziya  Abu; Saidatul Akmar Ismail; Mazlifah Mansoor; Mokhtarudin Mokhtarudin; Norsuriati Norsuriati; N Safuan; R, N. Hakim Roslan

doi:10.21834/e-bpj.v9iSI18.5478

Authors

W.A. Malek College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam and 40150, Malaysia
Safawi A. Jalil College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam and 40150, Malaysia
A. Rahman College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam and 40150, Malaysia
Irwan Kamarudin College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam and 40150, Malaysia
Roziya Abu College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam and 40150, Malaysia
Saidatul Akmar Ismail College of Computing, Informatics and Mathematics, Universiti Teknologi MARA Shah Alam and 40150, Malaysia
Mazlifah Mansoor Faculty of Law, UiTM, Shah Alam, 40150, Malaysia
Mokhtarudin Mokhtarudin National Archive of Malaysia, Kuala Lumpur, 50480, Malaysia.
Norsuriati Norsuriati National Archive of Malaysia, Kuala Lumpur, 50480, Malaysia.
N Safuan National Archive of Malaysia, Kuala Lumpur, 50480, Malaysia.
R, N. Hakim Roslan Academy of Contemporary Islamic Studies (ACIS), UiTM Raub, Pahang

DOI:

https://doi.org/10.21834/e-bpj.v9iSI18.5478

Keywords:

Malaysia National Archive (NAM), Machine Learning, Unsupervised Algorithms, Historical Photos

Abstract

In the realm of Artificial Intelligence (AI) and archive management, the central objective revolves around the autonomous extraction of valuable insights, patterns, and actionable information from extensive datasets. The AI technologies play a pivotal role in this context, leveraging advanced algorithms and computational capabilities to efficiently analyze and interpret archived data. The integration of AI within archive management systems enhances the organization, retrieval, and preservation of historical records, while also offering the capability to uncover hidden knowledge and trends. These advancements underscore the vital synergy between AI and archive management, revolutionising how National archive of Malaysia could harness their uncaptioned photos to provide some insight out of the photos for improved decision-making and historical preservation. The findings show that that the accuracy of adopted algorithms K-Means at 83.3%, Mean Shift at 78.0%, and Gaussian Mixture stood at 80.3% accuracy rate respectively.

References

Abualigah, L. M. Q. (2019). Feature selection and enhanced krill herd algorithm for text document clustering (pp. 1-165). Berlin: Springer. DOI: https://doi.org/10.1007/978-3-030-10674-4

Chen, J., Frey, E. C., He, Y., Segars, W. P., Li, Y., & Du, Y. (2022). TransMorph: Transformer for unsupervised medical image registration. Medical Image Analysis, 82, 102615. https://doi.org/10.1016/j.media.2022.102615 DOI: https://doi.org/10.1016/j.media.2022.102615

Colavizza, G., Blanke, T., Jeurgens, C., & Noordegraaf, J. (2021). Archives and AI: An overview of current debates and future perspectives. Journal on Computing and Cultural Heritage, 15(1), 1–15. https://doi.org/10.1145/3479010 DOI: https://doi.org/10.1145/3479010

Cushing, A. L., & Osti, G. (2022). “so how do we balance all of these needs?”: How the concept of AI technology impacts digital archival expertise. Journal of Documentation, 79(7), 12–29. https://doi.org/10.1108/jd-08-2022-0170 DOI: https://doi.org/10.1108/JD-08-2022-0170

Cushing, M. H., Sarmadi, H., & Yuen, K.-V. (2023). A locally unsupervised hybrid learning method for removing environmental effects under different measurement periods. Measurement, 208, 112465. https://doi.org/10.1016/j.measurement.2023.112465 DOI: https://doi.org/10.1016/j.measurement.2023.112465

Das, R., Jain, K. K., & Mishra, S. K. (2018). Archival research: A neglected method in organization studies. Benchmarking: An International Journal, 25(1), 138–155. https://doi.org/10.1108/bij-08-2016-0123 DOI: https://doi.org/10.1108/BIJ-08-2016-0123

Ezugwu, A. E., Shukla, A. K., Agbaje, M. B., Oyelade, O. N., José-García, A., & Agushaka, J. O. (2020). Automatic clustering algorithms: A systematic review and bibliometric analysis of relevant literature. Neural Computing and Applications, 33(11), 6247–6306. https://doi.org/10.1007/s00521-020-05395-4 DOI: https://doi.org/10.1007/s00521-020-05395-4

Hettich, Q. Retraction Note: Motion video tracking technology in sports training based on Mean-Shift algorithm. J Supercomput (2022). https://doi.org/10.1007/s11227-022-04863-z DOI: https://doi.org/10.1007/s11227-022-04863-z

ILi, S., Guo, Z., Lin, J., & Ying, S. (2022). Artificial Intelligence for classifying and archiving orthodontic images. BioMed Research International, 2022, 1–11. https://doi.org/10.1155/2022/1473977 DOI: https://doi.org/10.1155/2022/1473977

Joshi, M. R., Nkenyereye, L., Joshi, G. P., Islam, S. M., Abdullah-Al-Wadud, M., & Shrestha, S. (2020). Auto-colorization of historical images using deep convolutional neural networks. Mathematics, 8(12), 2258. https://doi.org/10.3390/math8122258 DOI: https://doi.org/10.3390/math8122258

Ma, J., Jiang, X., Jiang, J., & Gao, Y. (2019). Feature-guided gaussian mixture model for image matching. Pattern Recognition, 92, 231–245. https://doi.org/10.1016/j.patcog.2019.04.001 DOI: https://doi.org/10.1016/j.patcog.2019.04.001

Rolan, G., Humphries, G., Jeffrey, L., Samaras, E., Antsoupova, T., & Stuart, K. (2018). More human than human? Artificial Intelligence in the archive. Archives and Manuscripts, 47(2), 179–203. https://doi.org/10.1080/01576895.2018.1502088 DOI: https://doi.org/10.1080/01576895.2018.1502088