Kajian Analisis Variasi Jumlah Epoch Terhadap Persentase Kesesuaian Peta Batas Kampung dan Rupa Bumi Indonesia dengan Data Kartometrik Menggunakan Metode Deep Learning: Study of Variation Analysis of Epoch Number on the Percentage of Conformity of Village Boundary Maps and Indonesian Topography with Cartometric Data Using Deep Learning Methods

Ilyas Ilyas; Ratna Mustika Sari; Ade Tri Sucipto

doi:10.57152/malcom.v6i1.2021

Authors

Ilyas Ilyas Institut Teknologi Sumatera
Ratna Mustika Sari Institut Teknologi Sumatera
Ade Tri Sucipto Institut Teknologi Sumatera

DOI:

https://doi.org/10.57152/malcom.v6i1.2021

Keywords:

Batas Wilayah, Convolutional Neural Network, Deep Learning, Kartometrik, Rupa Bumi

Abstract

Kepastian batas wilayah merupakan aspek fundamental dalam mendukung kewenangan daerah dan perencanaan pembangunan. Namun, inkonsistensi data batas di Kecamatan Rumbia, khususnya antara metode kartometrik, data Peta Batas Wilayah dari Badan Informasi Geospasial (PPBW BIG), dan Rupa Bumi Indonesia (RBI), sering menghambat pengelolaan sumber daya. Penelitian ini bertujuan menganalisis pengaruh variasi jumlah epoch pada model Deep Learning terhadap akurasi deteksi kesesuaian batas kampung. Metode penelitian mengintegrasikan Sistem Informasi Geografis (SIG) dan Convolutional Neural Network (CNN) dengan arsitektur tiga lapisan konvolusi. Data latih mencakup integrasi data kartometrik, PPBW BIG, RBI, dan Citra Tegak Satelit Resolusi Tinggi (CTSRT). Pengujian dilakukan dengan variasi epoch 100 hingga 500 menggunakan optimasi Stochastic Gradient Descent (SGD). Hasil menunjukkan bahwa peningkatan epoch berbanding lurus dengan performa model, di mana akurasi validasi mencapai 100% pada epoch 500 dengan tingkat kesesuaian data sebesar 98% berdasarkan Intersection over Union (IoU). Temuan ini menegaskan efektivitas CNN dalam analisis spasial presisi guna mendukung percepatan Kebijakan Satu Peta dan meminimalkan konflik batas wilayah.

Downloads

Download data is not yet available.

References

E. Setiawan, A. Maryudi, R. Purwanto, and G. Lele, “Opposing interests in the legalization of non-procedural forest conversion to oil palm in Central Kalimantan, Indonesia,” Land use policy, vol. 58, pp. 472–481, 2016, doi: 10.1016/J.LANDUSEPOL.2016.08.003.

A. Sasikumar, M. Sathyanarayanan, A. N. Sriayapppan, R. Santhosh, and R. Reshma, “A CNN-based Canny Edge Detection Approach for Car Scratch Detection,” in 6th International Conference on Inventive Computation Technologies, ICICT 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 404–409. doi: 10.1109/ICICT57646.2023.10134444.

M. Bansal, M. Kumar, and M. Kumar, “2D object recognition: a comparative analysis of SIFT, SURF and ORB feature descriptors,” Multimed Tools Appl, vol. 80, pp. 18839–18857, 2021, doi: 10.1007/s11042-021-10646-0.

A. Maxwell, T. Warner, and L. Guillén, “Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies - Part 2: Recommendations and Best Practices,” Remote. Sens., vol. 13, p. 2591, 2021, doi: 10.3390/rs13132591.

S. S. Kusuma, S. Arjasakusuma, R. Rafif, S. Saringatin, P. Wicaksono, and A. A. Aziz, “Assessment of image segmentation and deep learning for mapping paddy fields using Worldview-3 in Magelang, Central Java Provinces, Indonesia,” vol. 12082, p. 1208207, 2021, doi: 10.1117/12.2619502.

B. Priambodo, W. Mahmudy, and Muh. A. Rahman, “Earthquake Magnitude and Grid-Based Location Prediction using Backpropagation Neural Network,” Knowl. Eng. Data Sci., vol. 3, pp. 28–39, 2020, doi: 10.17977/um018v3i12020p28-39.

C. A. Indriyani, C. R. Wijaya, and N. Qomariyah, “Forecasting COVID-19 Total Daily Cases in Indonesia Using LSTM Networks,” 2022 5th International Conference on Computing and Informatics (ICCI), pp. 385–391, 2022, doi: 10.1109/icci54321.2022.9756062.

V. Jadeja, A. Srivastava, P. Chaturvedi, and G. Bhardwaj, “Convolutional Neural Networks: A Comprehensive Review of Architectures and Application,” vol. 6, pp. 460–467, 2023, doi: 10.1109/ic3i59117.2023.10397695.

C. Y, P. Kiran, and M. P. B, “The Novel Method for Data Preprocessing CLI,” pp. 117–120, 2022, doi: 10.53759/aist/978-9914-9946-1-2_21.

A. Ziaee and E. Çano, “Batch Layer Normalization, A new normalization layer for CNNs and RNN,” Sep. 2022, doi: 10.1145/3571560.3571566.

P. Barbiero, G. Squillero, and A. Tonda, “Modeling Generalization in Machine Learning: A Methodological and Computational Study,” arXiv: Learning, 2020, [Online]. Available: https://arxiv.org/pdf/2006.15680v1

M. T. Mustapha, I. Ozsahin, and D. U. Ozsahin, “Convolution neural network and deep learning,” Elsevier BV, 2024, pp. 21–50. doi: 10.1016/b978-0-323-95462-4.00002-9.

D. Noël and S. Mukherjee, “An Investigation of Methods for Improving Spatial Invariance of Convolutional Neural Networks for Image Classification,” 2023, doi: 10.2139/ssrn.4548826.

J. Yu, S. Du, Z. Xin, L. Huang, and J. Zhao, “Application of a convolutional neural network to land use classification based on GF-2 remote sensing imagery,” Arabian Journal of Geosciences, vol. 14, no. 21, pp. 1–14, 2021, doi: 10.1007/S12517-021-08555-5.

L. Chen et al., “Field Patch Extraction Based on High-Resolution Imaging and U2-Net++ Convolutional Neural Networks,” Remote Sens (Basel), 2023, doi: 10.3390/rs15204900.

Monica and P. Agrawal, “A Survey on Hyperparameter Optimization of Machine Learning Models,” pp. 11–15, 2024, doi: 10.1109/icdt61202.2024.10489732.

R. Waghmare and N. Safika, “Geo-Spatial Data Analysis for Disaster Impact Forecasting,” International Journal For Multidisciplinary Research, vol. 7, no. 3, 2025, doi: 10.36948/ijfmr.2025.v07i03.44274.

E. Sahragard, H. Farsi, and S. Mohamadzadeh, “Semantic Segmentation of Aerial Imagery: A Novel Approach Leveraging Hierarchical Multi-scale Features and Channel-based Attention for Drone Applications,” International journal of engineering. Transactions B: Applications, vol. 37, no. 5, pp. 1022–1035, 2024, doi: 10.5829/ije.2024.37.05b.18.

A. Zohrevand and Z. Imani, “An Empirical Study of the Performance of Different Optimizers in the Deep Neural Networks,” Iranian Conference on Machine Vision and Image Processing, pp. 1–5, 2022, doi: 10.1109/MVIP53647.2022.9738743.

S. Ahmad, G. Trahan, and A. Islam, “When do Convolutional Neural Networks Stop Learning?,” arXiv.org, vol. abs/2403.02473, 2024, doi: 10.48550/arxiv.2403.02473.

J. M. Cohen et al., “Adaptive Gradient Methods at the Edge of Stability,” arXiv.org, vol. abs/2207.14484, 2022, doi: 10.48550/arXiv.2207.14484.

B. Wang and Q. Ye, “Improving Deep Neural Networks’ Training for Image Classification With Nonlinear Conjugate Gradient-Style Adaptive Momentum.,” IEEE Trans Neural Netw Learn Syst, vol. PP, pp. 1–13, 2023, doi: 10.1109/tnnls.2023.3255783.

M. Owusu-Adjei, T. Frimpong, and G. Abdul-Salaam, “A systematic review of prediction accuracy as an evaluation measure for determining machine learning model performance in healthcare systems.,” medRxiv, 2023, doi: 10.1101/2023.06.01.23290837.

B. Cheng, R. Girshick, P. Dollár, A. C. Berg, and A. Kirillov, “Boundary IoU: Improving Object-Centric Image Segmentation Evaluation,” Computer Vision and Pattern Recognition, pp. 15334–15342, 2021, doi: 10.1109/CVPR46437.2021.01508.

A. Eka, P. Wicaksono, and R. Mahenra, “Utilization of Generative Pre-trained Transformer Model for Automatic Evaluation and Feedback on Scientific Manuscripts,” Jurnal Media Computer Science, vol. 4, no. 2, pp. 227–236, 2025, doi: 10.37676/jmcs.v4i2.

K. Prasetyo and R. Mahenra, “Analisis Kinerja Convolutional Neural Networks Baseline untuk Identifikasi Jenis Jenis Penyakit Kentang,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 5, no. 2, pp. 609–615, Mar. 2025, doi: 10.57152/malcom.v5i2.1722.

F. Furizal, A. Ma’arif, D. Rifaldi, and A. A. Firdaus, “Comparison of Convolutional Neural Networks and Support Vector Machines on Medical Data: A Review,” International Journal of Robotics and Control Systems, 2024, doi: 10.31763/ijrcs.v4i1.1375.

Q. Qiao, “Image Processing Technology Based on Machine Learning,” IEEE Consumer Electronics Magazine, p. 1, 2022, doi: 10.1109/mce.2022.3150659.