Prediksi Kerusakan Bangunan Pasca Gempa Bumi Menggunakan Metode Deep Neural Network
DOI:
https://doi.org/10.32493/jtsi.v7i1.37181Kata Kunci:
Deep Neural Network, Prediksi Kerusakan Bangunan, Gempa Bumi, Learning Rate, OptimizerAbstrak
Menghadapi tantangan dalam memprediksi kerusakan bangunan akibat gempa bumi, penelitian ini mengusulkan penggunaan Deep Neural Network (DNN) sebagai solusi inovatif. Dengan fokus pada optimisasi model prediktif, penelitian ini mengevaluasi efektivitas berbagai optimizer - ADAM, SGD, RMSprop, dan Adagrad - dengan penyesuaian learning rate untuk menentukan konfigurasi yang paling efektif. Eksperimen dilakukan untuk membandingkan performa setiap optimizer dalam memprediksi tingkat kerusakan bangunan pasca-gempa, yang merupakan masalah kritis dalam mitigasi bencana. Hasilnya menunjukkan bahwa ADAM secara signifikan mengungguli optimizer lain, mencapai akurasi tertinggi hingga 90,50% pada learning rate 0,001, dengan RMSprop sebagai kompetitor terdekat. Meskipun SGD dan Adagrad menghasilkan akurasi yang lebih rendah, SGD menunjukkan peningkatan dengan learning rate yang lebih tinggi. Analisis varians menegaskan bahwa pemilihan optimizer memiliki dampak signifikan terhadap kinerja model, dengan nilai p yang menunjukkan signifikansi statistik yang kuat untuk optimizer (1.23E-09), sementara learning rate tidak berdampak signifikan (p-value 0.56098964). Temuan ini menggarisbawahi pentingnya memilih optimizer yang tepat dalam meningkatkan akurasi model DNN untuk prediksi kerusakan bangunan, suatu aspek krusial dalam perencanaan respons darurat dan upaya mitigasi bencana gempa bumi. Penelitian ini memberikan kontribusi penting dalam pengembangan model prediktif yang lebih akurat, yang sangat dibutuhkan untuk meminimalkan risiko bencana gempa bumi.
Referensi
Caelen, O. (2017). A Bayesian interpretation of the confusion matrix. September, 429–450. https://doi.org/10.1007/s10472-017-9564-8
Chaurasia, K., Kanse, S., Yewale, A., Singh, V. K., Sharma, B., & Dattu, B. R. (2019). Predicting Damage to Buildings Caused by Earthquakes Using Machine Learning Techniques. Proceedings of the 2019 IEEE 9th International Conference on Advanced Computing, IACC 2019, December, 81–86. https://doi.org/10.1109/IACC48062.2019.8971453
Da Poian, V., Theiling, B., Clough, L., McKinney, B., Major, J., Chen, J., & Hörst, S. (2023). Exploratory data analysis (EDA) machine learning approaches for ocean world analog mass spectrometry. Frontiers in Astronomy and Space Sciences, 10(May), 1–17. https://doi.org/10.3389/fspas.2023.1134141
Das, L., Sivaram, A., & Venkatasubramanian, V. (2020). Hidden Representations in Deep Neural Networks : Part 2 . Regression Problems. Computers and Chemical Engineering, 106895. https://doi.org/10.1016/j.compchemeng.2020.106895
Firmansyah, Rusmal, Shidiq, G. F. (2023). Peningkatan Deep Neural Network pada Kasus Prediksi Diabetes Menggunakan PSO. 22(4), 882–892.
Ghenescu, V., Barnoviciu, E., Carata, S., Ghenescu, M., Mihaescu, R., & Chindea, M. (n.d.). Object Recognition on Long Range Thermal Image Using State of the Art DNN. 1–4.
Ghimire, S., Guéguen, P., Giffard-Roisin, S., & Schorlemmer, D. (2022). Testing machine learning models for seismic damage prediction at a regional scale using building-damage dataset compiled after the 2015 Gorkha Nepal earthquake. Earthquake Spectra, 38(4), 2970–2993. https://doi.org/10.1177/87552930221106495
Hu, H., Lei, T., Hu, J., Zhang, S., & Kavan, P. (2018). Disaster-mitigating and general innovative responses to climate disasters: Evidence from modern and historical China. International Journal of Disaster Risk Reduction, 28(August 2017), 664–673. https://doi.org/10.1016/j.ijdrr.2018.01.022
Isnaeni, A. Y., & Prasetyo, S. Y. J. (2022). Klasifikasi Wilayah Potensi Risiko Kerusakan Lahan Akibat Bencana Tsunami Menggunakan Machine Learning. Jurnal Teknik Informatika Dan Sistem Informasi, 8(1), 33–42. https://doi.org/10.28932/jutisi.v8i1.4056
Maryani, E. (2021). The role of education and geography on disaster preparedness. IOP Conference Series: Earth and Environmental Science, 683(1). https://doi.org/10.1088/1755-1315/683/1/012043
Matchev, K. T., Matcheva, K., & Roman, A. (2022). Unsupervised Machine Learning for Exploratory Data Analysis of Exoplanet Transmission Spectra. Planetary Science Journal, 3(9), 205. https://doi.org/10.3847/PSJ/ac880b
Maulana, F. F., & Rochmawati, N. (2020). Klasifikasi Citra Buah Menggunakan Convolutional Neural Network. Journal of Informatics and Computer Science (JINACS), 1(02), 104–108. https://doi.org/10.26740/jinacs.v1n02.p104-108
Mittal, V. (2020). Exploring The Dimension of DNN Techniques For Text Categorization Using NLP.
Randles, B. M., Pasquetto, I. V., Golshan, M. S., & Borgman, C. L. (2017). Using the Jupyter Notebook as a Tool for Open Science: An Empirical Study. Proceedings of the ACM/IEEE Joint Conference on Digital Libraries, 17–18. https://doi.org/10.1109/JCDL.2017.7991618
Retson, T. A., Besser, A. H., Sall, S., Golden, D., & Hsiao, A. (2019). Machine Learning and Deep Neural Networks in Thoracic and Cardiovascular Imaging. 34(3), 192–201. https://doi.org/10.1097/RTI.0000000000000385
Shah, D., & Campbell, W. (2018). A Comparative Study of LSTM and DNN for Stock Market Forecasting. 2018 IEEE International Conference on Big Data (Big Data), 4148–4155. https://doi.org/10.1109/BigData.2018.8622462
Su, Y., Rong, G., Ma, Y., Chi, J., & Liu, X. (2022). Hazard Assessment of Earthquake Disaster Chains Based on Deep Learning — A Case Study of Mao County , Sichuan Province. 9(May), 1–10. https://doi.org/10.3389/feart.2021.683903
Sun, W., Cai, Z., Li, Y., Liu, F., Fang, S., & Wang, G. (2018). Review Article Data Processing and Text Mining Technologies on Electronic Medical Records : A Review. 2018.
Triastari, I., Dwiningrum, S. I. A., & Rahmia, S. H. (2021). Developing Disaster Mitigation Education with Local Wisdom: Exemplified in Indonesia Schools. IOP Conference Series: Earth and Environmental Science, 884(1). https://doi.org/10.1088/1755-1315/884/1/012004
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2024 Fakhrurrozi Fakhrurrozi, Danny Oka Ratmana, Nurul Anisa Sri Winarsih, Galuh Wilujeng Saraswati, Muhammad Syaifur Rohman, Filmada Ocky Saputra, Ricardus Anggi Pramunendar, Guruh Fajar Shidik
Artikel ini berlisensi Creative Commons Attribution-NonCommercial 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Jurnal Teknologi Sistem Informasi dan Aplikasi have CC BY-NC or an equivalent license as the optimal license for the publication, distribution, use, and reuse of scholarly work.
In developing strategy and setting priorities, Jurnal Teknologi Sistem Informasi dan Aplikasi recognize that free access is better than priced access, libre access is better than free access, and libre under CC BY-NC or the equivalent is better than libre under more restrictive open licenses. We should achieve what we can when we can. We should not delay achieving free in order to achieve libre, and we should not stop with free when we can achieve libre.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License
YOU ARE FREE TO:
- Share - copy and redistribute the material in any medium or format
- Adapt - remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms
_2020_-_7(2)_2024_-_Thumbnail.png)
