Teknik Random Undersampling untuk Mengatasi Ketidakseimbangan Kelas pada CT Scan Kista Ginjal
DOI:
https://doi.org/10.62411/tc.v23i1.9738Keywords:
Kidney Cyst, Deep Learning, CNN, Random Undersampling, CT ScanAbstract
Kista ginjal adalah pertumbuhan jaringan berbentuk kantong yang berisi carian pada sekitar ginjal. Seringkali kista ginjal tidak menimbulkan gejala, sehingga memerlukan pantauan reguler dokter. Dokter dapat melakukan pemeriksaan dan merencanakan tindakan penelitian lebih lanjut. Penelitiaan ini fokus pada model klasifikasi kista menggunakan model Deep Learning dengan arsitektur Convolution Neural Network (CNN), jenis jaringan syaraf tiruan untuk analisis gambar CT scan kista ginjal. Selain itu, penggunaan teknik pre-processing untuk meningkatkan performa model dengan memperbanyak varisasi data. Dalam membuat model klasifikasi perlu memperhatikan pemahaman data, tingkat interpretabilitas model, dan penanganan overfitting. Overfitting terjadi ketika model terlalu fokus pada data latih, sehingga tidak dapat memproses data uji dengan baik. Solusi untuk menangani masalah distribusi kelas adalah dengan penyeimbang kelas (resampling). Resampling dibagi menjadi dua jenis yaitu, undersampling dan oversampling. Undersampling merupakan metode sampling secara acak memilih di kelas mayoritas dan menambahkannya di kelas minoritas. Dan oversampling merupakan menggandakan sampel di kelas minoritas secara acak. Pada hasil pengujian model yang dilakukan dapat ditarik kesimpulan bahwa penggunaan teknik undersampling RUS memiliki tingkat akurasi tertinggi dengan nilai 30,82% untuk klasifikasi kista ginjal pada dataset tidak seimbang.References
A. Ariani and S. , "Klasifikasi Penyakit Ginjal Kronis menggunakan K-Nearest Neighbor," Annual Research Seminar, p. 4, 2019.
D. A. Bashar, "Survey on Envolving Deep Learning Neural Network Achitectures," Journal of Artificial Intelligence and Capsule Networks, vol. 01, no. 02, pp. 78-82, 2019.
S. S. and M. P. , "Heart Diseases Prediction using Deep Learning Neural Network Model," International Journal of Innovative Technology and Exploring Engineering (IJTEE), vol. 9, no. 3, 2020.
V. N. S. S. Chimakurthi, "Application of Convolution Neural Network for Digital Image Processing," Engineering International, vol. 8, 2020.
A. F. Suahati, A. A. Nurrahman and O. Rukmana, "Penggunaan Jaringan Syaraf Tiruan - Backpropagation dalam Memprediksi Jumlah Mahasiswa Baru," Jurnal Media Teknik & Sistem Industri, vol. 6, pp. 21-29, 2022.
K. N. Abd Halim, A. S. Mohamad Jaya and A. F. Ahmad Fadzil, "Data Preprocessing for Neural Network Binary Classification Model in Bank Tele-Marketing," International Journal of Innovative Technology and Exploring Engineering (IJTEE), vol. 9, no. 3, 2020.
Z. Li, K. Kamnitsas and B. Glocker, "Analyzing Overfitting under Class Imbalance in Neural Networks for Image Segmentation," Intitute of Electrical and Electronics Engineers, vol. 40, no. 3, 2020.
S. Bagui and K. Li, "Resampling Imbalanced Data for Network Intrusion Detection Datasets," Journal of Big Data, 2021.
J. H. Osorio, A. A. Meza, G. D. Santacoloma, A. O. Gutierrez and G. C. Dominguez, "Relevant Information Undersampling to Support Imbalanced data Classification," Neurocomputing, vol. 436, pp. 136-146, 2021.
H. A. Ahmed, A. Hameed and N. Z. Bawany, "Network Intrusion Detection using Oversampling Technique and Machine Learning Algorithms," PeerJ Computer Science, 2022.
M. C. Untoro and M. A. N. Maulana Yusuf, "Evaluate of Random Undersampling Method and Majority Weighted Minority Oversampling Technique in Resolve Imbalanced Dataset," IT Journal Research & Development, vol. 8, 2023.
E. Sutoyo and M. A. Fadlurrahman, "Penerapan SMOTE untuk Mengatasi Imbalance Class dalam Klasifikasi Television Advertisement Performance Ratting Menggunakan Artificial Neural Network," Jurnal Edukasi dan Penelitian Indonesia, vol. 6, 2020.
P. Liang, W. Li and J. Hu, "Oversampling the Minority Class in A Multi-Linear Feature Space for Imbalance Data Classification," IEEJ Transaction on Electrical and Electronic Engineering , 2018.
F. Thabtah, S. Hammoud, F. Kamalov and A. Gonsalves, "Data Imbalance in Classification : Experimental Evaluation," Information Sciences, vol. 513, pp. 429-441, 2020.
T. Wongvorachan, S. He and O. Bulut, "A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Clasification in Educational Data Mining," MDPI, 2023.
R. Wardoyo, I. M. A. Wirawan and I. G. A. Pradipta, "Oversampling Approach Using Radius-SMOTE for Imbalance Electroencephalography Datasets," Emerging Science Journal, vol. 6, 2022.
H. Mukherjee, S. Ghosh, A. Dhar, S. M. Obaidullah, K. C. Santosh and K. Roy, "Deep Neural Network to Detect Covid-19: One Architecture for Both CT Scans and Chest X-Rays," Applied Intelligence, 2021.
T. Wongvorachan, S. He and O. Bulut, "A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining," MDPI, 2022.
L. Alzubaidi, J. Zhang, A. J. Humaidi, A. Al-Dujaili, Y. Duan, O. Al-Shamma, J. Santamaria, M. A. Fadhel, M. Al-Amidie and L. Farhan, "Review of deep learning: concepts, CNN architectures, challenges, applications, future directions," Journal of Big Data, 2021.
R. R. Putra, I. G. Tofik Isa, A. B. Joni Malyan, E. Laila and A. T. Wardhana, "Level Optimum Hyperparameter Tuning Epoch dalam Klasifikasi Citra Bencana Kebakaran," Jurnal Teknologi Rekayasa (JTERA), vol. 7, 2022.
Downloads
Published
Issue
Section
License
License Terms
All articles published in Techno.COM Journal are licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). This means:
1. Attribution
Readers and users are free to:
-
Share – Copy and redistribute the material in any medium or format.
-
Adapt – Remix, transform, and build upon the material.
As long as proper credit is given to the original work by citing the author(s) and the journal.
2. Non-Commercial Use
-
The material cannot be used for commercial purposes.
-
Commercial use includes selling the content, using it in commercial advertising, or integrating it into products/services for profit.
3. Rights of Authors
-
Authors retain copyright and grant Techno.COM Journal the right to publish the article.
-
Authors can distribute their work (e.g., in institutional repositories or personal websites) with proper acknowledgment of the journal.
4. No Additional Restrictions
-
The journal cannot apply legal terms or technological measures that restrict others from using the material in ways allowed by the license.
5. Disclaimer
-
The journal is not responsible for how the published content is used by third parties.
-
The opinions expressed in the articles are solely those of the authors.
For more details, visit the Creative Commons License Page:
? https://creativecommons.org/licenses/by-nc/4.0/