Klasifikasi Kualitas dan Kematangan Pisang Cavendish Menggunakan Convolutional Neural Network

Authors

  • Arya Widya Hastungkoro Telkom University
  • Aditya Dwi Putro Wicaksono Telkom University
  • Yesy Diah Rosita Telkom University

DOI:

https://doi.org/10.33020/saintekom.v14i2.686

Keywords:

deep learning, classification, cavendish banana, CNN

Abstract

This research aims to develop a classification model using Convolutional Neural Networks (CNN) to determine the ripeness and quality of Cavendish bananas. The model classifies bananas into four categories: good quality unripe (MHBS), poor quality unripe (MHBK), good quality ripe (MGBS), and poor quality ripe (MGBK), using a total of 1,000 images. In this study, the classification process of the ripeness and quality of Cavendish bananas was carried out based on automatic feature extraction using CNN,after which an evaluation was carried out using a confusion matrix to assess model performance. The research developed 36 models with variations in parameters such as the number of epochs, batch size, and dataset split. The analysis results indicate that the number of epochs significantly affects the model's accuracy, with an increase in the number of epochs leading to higher accuracy. However, the dataset split scenario and batch size do not have a significant impact on the model's overall accuracy. Evaluation shows that the highest accuracy of 95% was achieved by the model with a 90:10 dataset split, a batch size of 16, and 20 epochs.

Downloads

Download data is not yet available.

References

Alzubaidi, L., Zhang, J., J. Humaidi, A., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., A. Fadhel, M., Al-Amidie, M., & Farhan, L. (2021, December). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(1). 10.1186/s40537-021-00444-8

Annur, C. M. (2023, June 22). Jawa Timur Jadi Produsen Pisang Terbesar Nasional 2022, Berapa Jumlahnya? Databoks. Retrieved May 13, 2024, from https://databoks.katadata.co.id/datapublish/2023/06/22/jawa-timur-jadi-produsen-pisang-terbesar-nasional-2022-berapa-jumlahnya

Barburiceanu, S., Meza, S., Orza, B., Malutan, R., & Terebes, R. (2021, November). Convolutional Neural Networks for Texture Feature Extraction. Applications to Leaf Disease Classification in Precision Agriculture. IEEE Access, 9, 160085-160103. 10.1109/ACCESS.2021.3131002

Fuadi, A., & Suharso, A. (2022). Perbandingan Arsitektur Mobilenet Dan Nasnetmobile Untuk Klasifikasi Penyakit Pada Citra Daun Kentang. JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), 7(3). https://doi.org/10.29100/jipi.v7i3.3026

Gampur, G., Ordiyasa, I. W., & Mulyani, S. H. (2022, Agustus). Klasifikasi Jenis Pisang Menggunakan Convolutional Neural Network. Prosiding Seminar Nasional Teknik Elektro, Informatika & Sistem Informasi (SINTaKS), 1(1). https://doi.org/10.35842/sintaks.v1i1.5

Iswantoro, D., & Handayani, D. (2022, July). Klasifikasi Penyakit Tanaman Jagung Menggunakan Metode Convolutional Neural Network (CNN). Jurnal Ilmiah Universitas Batanghari Jambi, 22(2), 900-905. 10.33087/jiubj.v22i2.2065

Mehenag, K., Julker, N., Forhad, A. M., Pritom, S., & Nakib, T. (2020, July). Fruits Classification using Convolutional Neural Network. GRD Journals- Global Research and Development Journal for Engineering, 5(8). ISSN- 2455-5703.

Molnar, C. (2022). Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. Christoph Molnar.

Muktianto, A., & Indriyani, V. (2022). Segmentasi Tingkat Kematangan Buah Pisang Cavendish Sangat Matang Berdasarkan Warna Menggunakan Watershed. JURIKOM (Jurnal Riset Komputer), 9(1). http://dx.doi.org/10.30865/jurikom.v9i1.3828

Putro Wicaksono, A. D. (2023, November). Klasifikasi Tingkat Kematangan, Kualitas dan Jenis Buah Pisang Berdasarkan Ciri Warna dan Bentuk Menggunakan Artificial Neural Networks. Jurnal Teknologi Informasi Indonesia (JTII), 7(2), 91-98. https://doi.org/10.30869/jtii.v7iNo 2.955

Pusporani, E., Qomariyah, S., & Irhamah, I. (2019, March). Klasifikasi Pasien Penderita Penyakit Liver dengan Pendekatan Machine Learning. Inferensi, 2(1), 25-32. https://doi.org/10.12962/j27213862.v2i1.6810

Downloads

PlumX Metrics

Published

30-09-2024

How to Cite

Hastungkoro, Arya Widya, Aditya Dwi Putro Wicaksono, and Yesy Diah Rosita. 2024. “Klasifikasi Kualitas Dan Kematangan Pisang Cavendish Menggunakan Convolutional Neural Network”. Jurnal Saintekom : Sains, Teknologi, Komputer Dan Manajemen 14 (2):185-94. https://doi.org/10.33020/saintekom.v14i2.686.

Issue

Vol. 14 No. 2 (2024): September 2024

Section

Articles

License

Copyright (c) 2024 Arya Widya Hastungkoro; Aditya Dwi Putro Wicaksono, Yesy Diah Rosita

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright :
By submitting manuscripts to Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen, the author agrees with this policy. No specific document approval is required.

  1. The copyright in each article belongs to the author.
  2. Authors retain all their rights to the published work, not limited to the rights set forth in this page.
  3. Authors acknowledge that Saintekom Journal: Science, Technology, Computers and Management as the first to publish under the Creative Commons Attribution 4.0 International license (CC BY-SA).
  4. The author may submit the paper separately, arrange for non-exclusive distribution of the manuscript that has been published in this journal into other versions (e.g. sent to the author's institutional respository, publication into a book, etc.), by acknowledging that the manuscript has been first published Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen;
  5. The author warrants that the article is original, written by the named author, has not been previously published, contains no unlawful statements, does not infringe the rights of others, is subject to copyright exclusively held by the author.
  6. If the article is jointly prepared by more than one author, each author submitting the manuscript warrants that he or she has been authorized by all co-authors to agree to copyright and license notices (agreements) on their behalf, and agrees to inform co-authors of the terms of this policy. Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen will not be held liable for anything that may arise due to internal author disputes.

Lisensi :
Jurnal Saintekom : Sains, Teknologi, Komputer dan Manajemen  is published under the terms of the Creative Commons Attribution 4.0 International License (CC BY-SA). This license permits anyone to:.

  1. Share - copy and redistribute this material in any form or format;
  2. Adaptation - modify, alter, and create derivatives of this material for any purpose.
  3. Attribution - you must give appropriate credit, include a link to the license, and state that changes have been made. You may do this in any appropriate manner, but it does not imply that the licensor endorses you or your use.
  4. Similar Sharing - If you modify, alter, or create a derivative of this material, you must distribute your contribution under the same license as the original material.