[2] I. Fajriaty, I. Fidrianny, N. F. Kurniati, N. M. Fauzi, S. H. Mustafa, and I. K. Adnyana, “In vitro and in silico studies of the potential cytotoxic, antioxidant, and HMG CoA reductase inhibitory effects of chitin from Indonesia mangrove crab (Scylla serrata) shells,” Saudi J. Biol. Sci., vol. 31, no. 5, p. 103964, May 2024, doi: 10.1016/j.sjbs.2024.103964.
[3] X. Zi et al., “A molting chemical cue (N-acetylglucosamine-6-phosphate) contributes to cannibalism of Chinese mitten crab Eriocheir sinensis,” Aquat. Toxicol., vol. 263, p. 106666, Oct. 2023, doi: 10.1016/j.aquatox.2023.106666.
[4] C. Agustiyana, Y. Hadiroseyani, I. Diatin, and I. Effendi, “Optimization of the production of soft shell crab (Scylla sp.) cultivation using the apartment system,” Egypt. J. Aquat. Res., Jul. 2024, doi: 10.1016/j.ejar.2024.05.003.
[5] W. Herwanto, A. Khumaidi and H. P. Putro, "Feature Extraction and Classification of Tissue Mammograms Based on Grayscale and Gray Level Co-occurrence Matrix," 2021 International Seminar on Machine Learning, Optimization, and Data Science (ISMODE), Jakarta, Indonesia, 2022, pp. 131-134, doi: 10.1109/ISMODE53584.2022.9743131.
[6] J. Mei, X. Liang, Y. Yu, Y. Lang, and X. Li, “The comparison and analysis of nutritional qualities of Chinese mitten crabs (Eriocheir sinensis) in rice field and pond culture modes,” Food Chem. X, vol. 20, p. 100937, Dec. 2023, doi: 10.1016/j.fochx.2023.100937.
[7] D. Zhang, W. Xu, F. Wang, J. He, and X. Chai, “Carbon dioxide fluxes from mariculture ponds with swimming crabs and shrimps in eastern China: The effect of adding razor clams,” Aquac. Reports, vol. 22, p. 100917, Feb. 2022, doi: 10.1016/j.aqrep.2021.100917.
[8] W. Ji, J. Peng, B. Xu, and T. Zhang, “Real-time detection of underwater river crab based on multi-scale pyramid fusion image enhancement and MobileCenterNet model,” Comput. Electron. Agric., vol. 204, p. 107522, Jan. 2023, doi: 10.1016/j.compag.2022.107522.
[9] R. R. Baharuddin, M. Niswar, A. A. Ilham, and S. Kashihara, “Crab Molting Identification using Machine Learning Classifiers,” in 2021 International Seminar on Machine Learning, Optimization, and Data Science (ISMODE), 2022, pp. 295–300, doi: 10.1109/ISMODE53584.2022.9743136.
[10] C. Tang, G. Zhang, H. Hu, P. Wei, Z. Duan, and Y. Qian, “An improved YOLOv3 algorithm to detect molting in swimming crabs against a complex background,” Aquac. Eng., vol. 91, p. 102115, Nov. 2020, doi: 10.1016/j.aquaeng.2020.102115.
[11] Z. Zhang, F. Liu, X. He, X. Wu, M. Xu, and S. Feng, “Soft-shell crab detection model based on YOLOF,” Aquac. Int., vol. 32, no. 4, pp. 5269–5298, Aug. 2024, doi: 10.1007/s10499-024-01426-2.
[12] R. M. D. Cesar Ian A. Baluran, Edwin R. Arboleda, Marivic G. Dizon, “Crab Gender Classification Using Image Processing, Fuzzy Logic And K Nearest Neighbor (KNN) Classifier,” Int. J. Sci. Technol. Res., vol. 8, no. 10, pp. 1458–1462, 2019.
[13] X. Chen, Y. Zhang, D. Li, and Q. Duan, “Chinese mitten crab detection and gender classification method based on GMNet-YOLOv4,” Comput. Electron. Agric., vol. 214, p. 108318, Nov. 2023, doi: 10.1016/j.compag.2023.108318.
[14] J. Terven, D.-M. Córdova-Esparza, and J.-A. Romero-González, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Mach. Learn. Knowl. Extr., vol. 5, no. 4, pp. 1680–1716, Nov. 2023, doi: 10.3390/make5040083.
[15] J. Rogelio, E. Dadios, A. Bandala, R. R. Vicerra, and E. Sybingco, “Alignment control using visual servoing and mobilenet single-shot multi-box detection (SSD): a review,” Int. J. Adv. Intell. Informatics, vol. 8, no. 1, p. 97, Mar. 2022, doi: 10.26555/ijain.v8i1.819.
[16] H.-C. Chang, L.-W. Yu, B.-Y. Liu, and P.-C. Chang, “Classification of the implant-ridge relationship utilizing the MobileNet architecture,” J. Dent. Sci., vol. 19, no. 1, pp. 411–418, Jan. 2024, doi: 10.1016/j.jds.2023.08.002.
[17] N. Shome, R. Kashyap, and R. H. Laskar, “Detection of tuberculosis using customized MobileNet and transfer learning from chest X-ray image,” Image Vis. Comput., vol. 147, p. 105063, Jul. 2024, doi: 10.1016/j.imavis.2024.105063.
[18] I. Shafi, A. Mazahir, A. Fatima, and I. Ashraf, “Internal defects detection and classification in hollow cylindrical surfaces using single shot detection and MobileNet,” Measurement, vol. 202, p. 111836, Oct. 2022, doi: 10.1016/j.measurement.2022.111836.
[19] M. Xu, S. Yoon, A. Fuentes, and D. S. Park, “A Comprehensive Survey of Image Augmentation Techniques for Deep Learning,” Pattern Recognit., vol. 137, p. 109347, May 2023, doi: 10.1016/j.patcog.2023.109347.
[20] F. J. M. Shamrat, S. Azam, A. Karim, K. Ahmed, F. M. Bui, and F. De Boer, “High-precision multiclass classification of lung disease through customized MobileNetV2 from chest X-ray images,” Comput. Biol. Med., vol. 155, p. 106646, Mar. 2023, doi: 10.1016/j.compbiomed.2023.106646.
[21] A. Khumaidi, Y. A. Purwanto, H. Sukoco, and S. H. Wijaya, “Using Fuzzy Logic to Increase Accuracy in Mango Maturity Index Classification: Approach for Developing a Portable Near-Infrared Spectroscopy Device,” Sensors, vol. 22, no. 24, p. 9704, Dec. 2022, doi: 10.3390/s22249704.
- Abstract viewed - 36 times
- pdf (Bahasa Indonesia) downloaded - 31 times
Affiliations
Ali Khumaidi
Affiliation not stated
Aini Nurpadilah
Universitas Krisnadwipayana
How to Cite
KLASIFIKASI MOLTING KEPITING SOKA MENGGUNAKAN ALGORITMA CONVOLUSIONAL NEURAL NETWORK
Vol 13 No 2 (2024): Komputa : Jurnal Ilmiah Komputer dan Informatika
Abstract
Kepiting Soka memiliki nilai ekonomi tinggi karena seluruh bagian tubuhnya dapat dimakan selama fase molting, saat cangkangnya lunak. Proses ini berlangsung singkat, hanya sekitar 5 jam sebelum cangkang mengeras kembali. Deteksi molting secara otomatis sangat diperlukan untuk mengoptimalkan waktu panen dan mencegah kehilangan produksi. Teknologi deep learning menggunakan arsitektur MobileNetV2 telah menunjukkan efisiensi dalam klasifikasi gambar. Penelitian ini bertujuan untuk mengklasifikasi kepiting soka dalam kondisi molting menggunakan arsitektur MobileNetV2, berbeda dengan metode pembelajaran mesin sebelumnya. MobileNetV2 dipilih karena kemampuannya dalam klasifikasi citra dengan sumber daya komputasi terbatas. Dataset berisi 260 citra kepiting, dengan fokus pada kepiting soka molting dan tidak molting, diproses melalui augmentasi, resize, dan pembagian data (80% data training, 10% validasi, dan 10% testing). Model ini menghasilkan akurasi tinggi pada pelatihan dan validasi sebesar 100%, membuktikan kemampuannya untuk mendeteksi kepiting molting secara efisien dan model tidak mengalami overfitting. Arsitektur MobileNetV2 berpotensi untuk diaplikasikan dalam sistem klasifikasi kepiting soka berbasis perangkat seluler.