Klasifikasi Tingkat Kematangan Buah Pisang Raja Menggunakan Metode CNN Berbasis Android

Authors

  • Trissa Noor Aulia Febriana Universitas Stikubank Unisbank Semarang
  • Veronica Lusiana Universitas Stikubank Semarang

DOI:

https://doi.org/10.32493/jtsi.v7i1.37790

Keywords:

classification; plantain; Cnn; Android

Abstract

Raja banana (Musa paradisiaca L.) is a banana cultivar commonly enjoyed in Indonesia. In addition to being consumed as a fresh fruit, Pisang Raja is often processed into various banana-based foods, such as banana chips, fried bananas, banana fritters, and other banana products. For farmers, post-harvest sorting of Pisang Raja requires a significant amount of time and effort. Therefore, a system is needed to assist farmers and the community in general to determine the ripeness level of Pisang Raja fruit more efficiently and clearly. The classification process of Pisang Raja fruit ripeness levels is carried out through precision calculations in a system, using a dataset consisting of 300 images covering 3 types of Pisang Raja ripeness levels. The classification process for the ripeness levels of Pisang Raja fruit utilizes the Convolutional Neural Network (CNN) method with the TensorFlow module for training and testing data. Based on experimental results, the accuracy in classifying the ripeness levels of Pisang Raja fruit reaches a value of 95%."

References

Utami, REZKI NURFADILLAH. "Uji Efektivitas Ekstrak Kulit Pisang Raja (Musa paradisiaca var. Raja) Terhadap Penurunan Kadar Gula Darah Mencit Jantan (Mus musculuss)." (2016).

Hanifah, A. I., & Hermawan, A. (2023). Klasifikasi Kematangan Pisang Menggunakan Metode Convolutional Neural Network. Komputika: Jurnal Sistem Komputer, 12(2), 49-56.

Rusmita, Sylva Alif, et al. "Monitoring of Islamic Finance Activity to Economic Growth: An Indonesia Experience (2009-2023)." Fintech Applications in Islamic Finance: AI, Machine Learning, and Blockchain Techniques. IGI Global, 2024. 191-210.

Khan, S., H. Rahmani, S. Shah, and D.M Bennamoun. (2018). A Guide to Convolutional Neural Networks for Computer Vision. New York: Morgan & Claypool Publishers

Chen, Ruifeng, dkk. "Efektivitas rokok elektrik sebagai alat bantu berhenti merokok: bukti dari kelompok Studi PATH, 2017–2019." Pengendalian Tembakau 32.e2 (2023): e145-e152.

Paliwang, Zainal Arifin, dkk. “Kebijakan Inovatif Pembangunan Sosial Ekonomi Masyarakat Perbatasan Pesisir Nunukan Kalimantan Utara.†Ilmu Sosial KnE (2020): 779-787.

Lee, Chen-Yu, dkk. "Jaring yang diawasi secara mendalam." Kecerdasan buatan dan statistik. Pmlr, 2015.

Wijaya, Dedy Rahman, dkk. "Mengumpulkan pendekatan pembelajaran mesin untuk pemrosesan sinyal hidung elektronik." Penelitian Penginderaan dan Bio-Sensing 36 (2022): 100495.

ARIFIANTO, JULY. "Aplikasi Web Pendeteksi Jerawat Pada Wajah Menggunakan Model Deep Learning Dengan Tensorflow." (2022).

Pang, B., Nijkamp, E., & Wu, YN (2020). Pembelajaran mendalam dengan tensorflow: Sebuah ulasan. Jurnal Statistik Pendidikan dan Perilaku, 45 (2), 227-248.

Tashildar, Aakanksha, dkk. "Pengembangan aplikasi menggunakan flutter." Jurnal Penelitian Internasional Modernisasi dalam Teknologi dan Sains Rekayasa 2.8 (2020): 1262-1266.

Published

2024-01-30

How to Cite

Febriana, T. N. A., & Lusiana, V. (2024). Klasifikasi Tingkat Kematangan Buah Pisang Raja Menggunakan Metode CNN Berbasis Android. Jurnal Teknologi Sistem Informasi Dan Aplikasi, 7(1), 176–184. https://doi.org/10.32493/jtsi.v7i1.37790