IMPLEMENTASI MODEL KLASIFIKASI KEMATANGAN PISANG MENGGUNAKAN ARSITEKTUR CNN INCEPTION V3 DAN VGG16
Main Article Content
Abstract
Banana ripeness level is a crucial factor in determining the quality and freshness of agricultural products. This research aims to develop a Convolutional Neural Network (CNN) model to classify the ripeness levels of bananas—from unripe to overripe—with the goal of assisting farmers in the sorting process more consistently and efficiently. Two CNN architectures, InceptionV3 and VGG16, were utilized to evaluate their respective performances. This research employed the CRISP-DM methodology, which consists of business understanding, data understanding, data preparation, modeling, and evaluation. The dataset used was obtained from Dataverse Telkom University and consists of four classes: unripe, semi-ripe, ripe, and overripe. The results showed that the VGG16 model achieved the highest accuracy of 92%, while InceptionV3 achieved an accuracy of 87%. However, both models struggled with classifying the "Ripe" and "Overripe" categories, which could be attributed to data imbalance, lighting variations, and color variations in the "Semi-ripe" class. Therefore, the test results indicate that VGG16 performed better compared to InceptionV3, but improvements in dataset quality are necessary to enhance the overall model performance.
Tingkat kematangan pisang merupakan faktor penting dalam menentukan kualitas dan kesegaran produk pertanian. Penelitian ini bertujuan mengembangkan model Convolutional Neural Network (CNN) untuk mengklasifikasikan tingkat kematangan pisang—dari mentah hingga terlalu matang—dengan harapan dapat membantu petani dalam proses penyortiran secara lebih konsisten dan efisien. Dua arsitektur CNN, yaitu InceptionV3 dan VGG16, digunakan untuk mengevaluasi performa masing-masing. Penelitian ini menggunakan metode CRISP-DM yang terdiri dari business understanding, data understanding, data preparation, modeling, dan evaluation. Dataset yang digunakan diperoleh dari Dataverse Telkom University dan terdiri dari empat kelas: mentah, setengah matang, matang, dan terlalu matang. Hasil penelitian menunjukkan bahwa model VGG16 mencapai akurasi tertinggi sebesar 92%, sementara InceptionV3 mencapai akurasi 87%. Namun, kedua model mengalami kesulitan dalam mengklasifikasikan kategori "Matang" dan "Terlalu matang," yang dapat disebabkan oleh ketidakseimbangan data, variasi pencahayaan, dan variasi warna pada kelas “setengah-matang.” Maka, dari hasil pengujian VGG16 menunjukkan performa lebih baik dibandingkan dengan InceptionV3, akan tetapi peningkatan kualitas dataset diperlukan untuk meningkatkan kinerja model secara keseluruhan.
Article Details

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
References
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00444-8
Amelia Dertta Irjayanti, S. AP. , M. SE., Agung Setyo Wibowo, S., Hanik Stiyaningsih, S. M. Sc., Ike Mahlida Putri, S., Oktya Putri Gitaningtyas, S. M. S. E., Satria Kurnia Areka, S. Tr. S., Wati Suprapti, S. Pd., & Zelani Nurfalah, S. (2022). Statistik Hortikultura 2022. BPS RI/BPS-Statistics Indonesia.
Andanu, O., Udin, F., & Titi Candra Sunarti. (2021). STRATEGI PENINGKATAN KUALITAS PRODUK DALAM RANTAI PASOK KOMODITI PISANG DI PROVINSI BENGKULU. Jurnal Teknologi Industri Pertanian, 220–231. https://doi.org/10.24961/j.tek.ind.pert.2021.31.2.220
Badan Pusat Statistik. (2021, December 18). Mencatat Pertanian Indonesia. https://www.bps.go.id/id/news/2021/12/18/446/mencatat-pertanian-indonesia.html
Dwivany, F. M. Et. al. (2021). Pisang Indonesia. In ITB Press (Vols. 978-623–29, Issue March).
Hilman Ferdinandus Pardede. (2023). Penerapan Pembelajaran Mesin (Machine Learning) dan Pembelajaran Dalam (Deep Learning) Berkinerja Tinggi untuk Mendukung Sektor Pertanian di Indonesia. In Penerapan Pembelajaran Mesin (Machine Learning) dan Pembelajaran Dalam (Deep Learning) Berkinerja Tinggi untuk Mendukung Sektor Pertanian di Indonesia. Penerbit BRIN. https://doi.org/10.55981/brin.872
Kangune, K., Kulkarni, V., & Kosamkar, P. (2019). Grapes Ripeness Estimation using Convolutional Neural network and Support Vector Machine. 2019 Global Conference for Advancement in Technology (GCAT), 1–5. https://doi.org/10.1109/GCAT47503.2019.8978341
Khan, S., & Yairi, T. (2018). A review on the application of deep learning in system health management. In Mechanical Systems and Signal Processing (Vol. 107, pp. 241–265). Academic Press. https://doi.org/10.1016/j.ymssp.2017.11.024
Meshram, V., Patil, K., Meshram, V., Hanchate, D., & Ramkteke, S. D. (2021). Machine learning in agriculture domain: A state-of-art survey. Artificial Intelligence in the Life Sciences, 1(October), 100010. https://doi.org/10.1016/j.ailsci.2021.100010
Saranya, N., Srinivasan, K., & Kumar, S. K. P. (2022). Banana ripeness stage identification: a deep learning approach. Journal of Ambient Intelligence and Humanized Computing, 13(8), 4033–4039. https://doi.org/10.1007/s12652-021-03267-w
Shorif, M., Jagdish, U., & Bansal, C. (2021). Computer Vision and Machine Learning in Agriculture. http://www.springer.com/series/16171
Shuprajhaa, T., Mathav Raj, J., Paramasivam, S. K., Sheeba, K. N., & Uma, S. (2023). Deep learning based intelligent identification system for ripening stages of banana. Postharvest Biology and Technology, 203, 112410. https://doi.org/https://doi.org/10.1016/j.postharvbio.2023.112410
Tapia-Mendez, E., Cruz-Albarran, I. A., Tovar-Arriaga, S., & Morales-Hernandez, L. A. (2023). Deep Learning-Based Method for Classification and Ripeness Assessment of Fruits and Vegetables. Applied Sciences, 13(22), 12504. https://doi.org/10.3390/app132212504
Wisjnu, S. S., Wardhani, Ismunandar, Michael A, Purwoadi, & Anto S. (2020). STRATEGI NASIONAL KECERDASAN ARTIFISIAL INDONESIA. In Strategi nasional kecerdasan artifisial Indonesia 2020-2045. https://karya.brin.go.id/id/eprint/13918/