Analisis Performa Model Deep Learning dalam Deteksi Penyakit Mata: Studi CNN, RNN, dan FNN
DOI:
https://doi.org/10.22441/incomtech.v15i2.31261Kata Kunci:
Penyakit Mata, Convolutional Neural Network, Recurrent Neural Network, Feedforward Neural NetworkAbstrak
Penyakit mata menjadi salah satu penyebab utama gangguan penglihatan yang dapat mengarah pada kebutaan permanen jika tidak ditangani dengan baik. Beberapa penyakit mata yang sering terjadi antara lain katarak, glaukoma, dan retinopati diabetik. Penelitian ini bertujuan untuk mengembangkan model klasifikasi penyakit mata berbasis citra menggunakan tiga metode deep learning, yaitu Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), dan Feedforward Neural Network (FNN). Dataset yang digunakan dalam penelitian ini terdiri dari 4.217 citra, yang diproses melalui tahapan preprocessing yang mencakup pembagian data menjadi tiga kelompok: pelatihan (training), validasi, dan pengujian (testing). Selanjutnya, citra tersebut melalui tahap resizing dan normalisasi untuk meningkatkan kualitas data yang digunakan dalam pelatihan model. Model-model yang dikembangkan kemudian dilatih menggunakan teknik Early Stopping untuk mencegah overfitting dan mengoptimalkan performa. Berdasarkan hasil evaluasi, model CNN menunjukkan performa terbaik dengan akurasi uji sebesar 85% dan nilai loss 0, 3841, mengungguli RNN yang memiliki akurasi 83% dan FNN dengan akurasi 78%. Selain itu, analisis menggunakan Confusion Matrix menunjukkan bahwa CNN lebih unggul dalam menangkap fitur spasial pada citra dibandingkan model lainnya. Implementasi model dilakukan dalam aplikasi web berbasis Flask untuk memprediksi penyakit mata berdasarkan citra yang diunggah pengguna. Penelitian lanjutan dapat meningkatkan akurasi model dengan menerapkan transfer learning menggunakan model pretrained yang lebih kompleks.Unduhan
Referensi
WHO, “Kebutaan dan gangguan penglihatan,” https://www.who.int/news-room/fact-sheets/detail/blindness-and-visual-impairment.
F. Nurona Cahya et al., “Klasifikasi Penyakit Mata Menggunakan Convolutional Neural Network ( CNN),” 2021. [Online]. Available: http://sistemasi.ftik.unisi.ac.id
S. J. Emery-Corbin et al., “Eukaryote-conserved methylarginine is absent in diplomonads and functionally compensated in Giardia,” Mol Biol Evol, vol. 37, no. 12, pp. 3525–3549, Dec. 2020, doi: 10.1093/molbev/msaa186.
S. Dutta, B. C. S. Manideep, S. M. Basha, R. D. Caytiles, and N. C. S. N. Iyengar, “Classification of diabetic retinopathy images by using deep learning models,” International Journal of Grid and Distributed Computing, vol. 11, no. 1, pp. 89–106, 2018, doi: 10.14257/ijgdc.2018.11.1.09.
F. Nurona Cahya et al., “Klasifikasi Penyakit Mata Menggunakan Convolutional Neural Network ( CNN),” 2019. [Online]. Available: http://sistemasi.ftik.unisi.ac.id
William and C. Lubis, “KLASIFIKASI PENYAKIT MATA MENGGUNAKAN CNN,” Jurnal Ilmu Komputer dan Sistem Informasi , vol. 10, no. 1, 2022, [Online]. Available: https://www.kaggle.com/nafizimtiazkhan/cataract-
O. Bernabe, E. Acevedo, A. Acevedo, R. Carreno, and S. Gomez, “Classification of Eye Diseases in Fundus Images,” IEEE Access, vol. 9, pp. 101267–101276, 2021, doi: 10.1109/ACCESS.2021.3094649.
M. S. Junayed, M. B. Islam, A. Sadeghzadeh, and S. Rahman, “CataractNet: An automated cataract detection system using deep learning for fundus images,” IEEE Access, vol. 9, pp. 128799–128808, 2021, doi: 10.1109/ACCESS.2021.3112938.
S. Dutta, B. C. S. Manideep, S. M. Basha, R. D. Caytiles, and N. C. S. N. Iyengar, “Classification of diabetic retinopathy images by using deep learning models,” International Journal of Grid and Distributed Computing, vol. 11, no. 1, pp. 89–106, 2018, doi: 10.14257/ijgdc.2018.11.1.09.
Y. Julia Nurriski and Alamsyah, “Optimasi Deep Convolutional Neural Network (Deep CNN) untuk Deteksi Aritmia Melalui Sinyal EKG Menggunakan Arsitektur Conv1D,” Indonesian Journal of Mathematics and Natural Sciences, vol. 46, no. 1, 2023, [Online]. Available: http://journal.unnes.ac.id/nju/index.php/JM
M. Zahir and R. Adi Saputra, “DETEKSI PENYAKIT RETINOPATI DIABETES MENGGUNAKAN CITRA MATA DENGAN IMPLEMENTASI DEEP LEARNING CNN,” 2024. [Online]. Available: https://www.kaggle.com/datasets/gunavenkatdoddi/eye-diseases-classification
K. Azmi, S. Defit, and Sumijan, “Implementasi Convolutional Neural Network (CNN) Untuk Klasifikasi Batik Tanah Liat Sumatera Barat,” Jurnal Unitek, vol. 16, no. 1, 2023.
D. Esterlina Br Jabat, L. Yanti Sipayung, and K. Raih Syahputra Dakhi, “PENERAPAN ALGORITMA RECURRENT NEURAL NETWORKS (RNN) UNTUK KLASIFIKASI ULOS BATAK TOBA,” SNISTIK : Seminar Nasional Inovasi Sains Teknologi Informasi Komputer , vol. 1, no. 2, 2024.
S. Gheisari et al., “A combined convolutional and recurrent neural network for enhanced glaucoma detection,” Sci Rep, vol. 11, no. 1, Dec. 2021, doi: 10.1038/s41598-021-81554-4.
D. Aprillia, T. Rohana, T. Al Mudzakir, and D. Wahiddin, “Deteksi Nominal Mata Uang Rupiah Menggunakan Metode Convolutional Neural Network dan Feedforward Neural Network,” KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 4, no. 4, 2024, doi: 10.30865/klik.v4i4.1711.
F. Maulana and E. B. Setiawan, “Performance of Deep Feed-Forward Neural Network Algorithm Based on Content-Based Filtering Approach,” INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 8, no. 2, pp. 278–294, Aug. 2024, doi: 10.29407/intensif.v8i2.22904.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
The copyright to this article is transferred to Universitas Mercu Buana (UMB) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to UMB. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment.
We declare that:
1. This paper has not been published in the same form elsewhere.
2. It will not be submitted anywhere else for publication prior to acceptance/rejection by this Journal.
3. A copyright permission is obtained for materials published elsewhere and which require this permission for reproduction.
Furthermore, I/We hereby transfer the unlimited rights of publication of the above mentioned paper in whole to UMB. The copyright transfer covers the exclusive right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Retained Rights/Terms and Conditions
1. Authors retain all proprietary rights in any process, procedure, or article of manufacture described in the Work.
2. Authors may reproduce or authorize others to reproduce the Work or derivative works for the authors personal use or for company use, provided that the source and the UMB copyright notice are indicated, the copies are not used in any way that implies UMB endorsement of a product or service of any employer, and the copies themselves are not offered for sale.
3. Although authors are permitted to re-use all or portions of the Work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
