PERBANDINGAN KINERJA DEEP LEARNING LENET DAN ALEXNET DENGAN AUGMENTASI DATA PADA IDENTIFIKASI ANGGREK

  • ekanofi tarisa Universitas Teknokrat Indonesia
  • Fenty Ariany Universitas Teknokrat Indonesia
DOI: https://doi.org/10.31000/jika.v8i1.9923

Abstract

Anggrek adalah tanaman florikultura yang sangat digemari oleh masyarakat karena menarik perhatian dari segi bentuk dan warna bunga yang unik serta masa berbunganya yang relatif panjang. Meskipun banyak diminati keanekaragaman anggrek masih sangat sulit untuk diidentifikasi hanya berdasarkan bentuk dan warna. Deep learning berfokus pada penggunaan arsitektur jaringan syaraf tiruan yang mempunyai kemampuan dalam pengenalan citra. Sehingga deep learning dipilih sebagai metode utama untuk mengatasi permasalahan identifikasi citra anggrek. Penerapan metode deep learning pada penelitian ini untuk membandingkan hasil akurasi kinerja arsitektur LeNet dan AlexNet pada identifikasi citra anggrek dan menggunakan skenario pengujian K-Fold Cross Validation. Dataset anggrek memiliki 1000 gambar, lalu dataset di augmentasi menjadi 2000 gambar. Google Colab digunakan sebagai alat untuk melakukan proses pelatihan model deep learning. Hasil penelitian menunjukkan AlexNet menggunakan augmentasi rotate memiliki nilai akurasi 79.50% dan LeNet memiliki nilai akurasi 62,50%. Sehingga dapat disimpulkan bahwa identifikasi spesies anggrek dengan menggunakan arsitektur AlexNet lebih akurat dibandingkan dengan arsitektur LeNet.

References

Al Rivan, M. E., & Setiawan, A. (2022). Pengenalan Gestur Angka Pada Tangan Menggunakan Arsitektur AlexNet Dan LeNet Pada Metode Convolutional Neural Network. Komputika : Jurnal Sistem Komputer, 11(1), 19–28. https://doi.org/10.34010/komputika.v11i1.5176

Almryad, A., Technology, H. K.-S. and, Journal, an I., &(2020, undefined. (n.d.). Automatic identification for field butterflies by convolutional neural networks. Elsevier. Retrieved November 26, 2022, from https://www.sciencedirect.com/science/article/pii/S2215098619326011

Batubara, N., & Awangga, R. (2020). Tutorial Object Detection Plate Number With Convolution Neural Network (CNN). https://books.google.com/books?hl=id&lr=&id=JAgHEAAAQBAJ&oi=fnd&pg=PA1&dq=batubara+2020+object+detection+plate&ots=3VwkbkZuKz&sig=oXQQ_Jwd1ZtIsxket02dV-y7RQI

Falahkhi, B., Achmal, E. F., Rizaldi, M., Rizki, R., & Yudistira, N. (n.d.). Perbandingan Model AlexNet dan ResNet dalam Klasifikasi Citra Bunga Memanfaatkan Transfer Learning Comparison of AlexNet and ResNet Models in Flower Image Classification Utilizing Transfer Learning. http://journal.ipb.ac.id/index.php/jika

Goodfellow, I., Bengio, Y., & Courville, A. (n.d.). Deep Learning.

Hansel, L., #1, G., Bunyamin, H., & Si, S. (2021). Penggunaan Augmentasi Data pada Klasifikasi Jenis Kanker Payudara dengan Model Resnet-34 (Vol. 3). https://cs231n.github.io/convolutional-networks/

Irfansyah, D., Mustikasari, M., Suroso, A., Sistem Informasi Bisnis, J., Ilmu Komputer dan Teknologi Informasi, F., Gunadarma, U., Sistem Informasi, J., Bani Saleh, S., Margonda Raya No, J., Depok, B., & Hasibuan No, J. M. (2021). Arsitektur Convolutional Neural Network (CNN) Alexnet Untuk Klasifikasi Hama Pada Citra Daun Tanaman Kopi. 6(2).

Januar Rinaldi, M., & Roro Narwastu Dwi Rita, R. (2020). IDENTIFIKASI JENIS ANGGREK (Orcidaceae) DI KEBUN RAYA LEMOR DESA SUELA KECAMATAN SUELA KABUPATEN LOMBOK TIMUR. In 50 | Jurnal Silva Samalas (Vol. 3, Issue 1).

Lecun, Y., Eon Bottou, L., Bengio, Y., & Abstract|, P. H. (n.d.). Gradient-Based Learning Applied to Document Recognition.

Peryanto, A., Yudhana, A., & Umar, R. (2020). Klasifikasi Citra Menggunakan Convolutional Neural Network dan K Fold Cross Validation. Journal of Applied Informatics and Computing, 4(1), 45–51. https://doi.org/10.30871/jaic.v4i1.2017

Pramana, A. L., Setyati, E., & Kristian, Y. (2020). Model Cnn Lenet Dalam Pengenalan Jenis Golongan Kendaraan. Institut Sains Dan Teknologi Terpadu Surabaya, 13(2), 65–69.

Putra Pamungkas, D., KUNCI Anggrek, K., & Korespondensi, O. (2019). Ekstraksi Citra menggunakan Metode GLCM dan KNN untuk Indentifikasi Jenis Anggrek (Orchidaceae). 1(2), 51–56.

Rafly Alwanda, M., Putra, R., Ramadhan, K., & Alamsyah, D. (2020). Implementasi Metode Convolutional Neural Network Menggunakan Arsitektur LeNet-5 untuk Pengenalan Doodle. In Jurnal Algoritme (Vol. 1, Issue 1).

Rochmawati, N., … H. H.-J. I., & 2021, undefined. (n.d.). Analisa Learning Rate dan Batch Size pada Klasifikasi Covid Menggunakan Deep Learning dengan Optimizer Adam. Repository.Unair.Ac.Id. Retrieved November 26, 2022, from https://repository.unair.ac.id/117699/

Sanjaya, J., & Ayub, M. (2020). Augmentasi Data Pengenalan Citra Mobil Menggunakan Pendekatan Random Crop, Rotate, dan Mixup. Jurnal Teknik Informatika Dan Sistem Informasi, 6(2), 311–323. https://doi.org/10.28932/jutisi.v6i2.2688

Shorten, C., & Khoshgoftaar, T. M. (2019). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6(1). https://doi.org/10.1186/S40537-019-0197-0/

Published
2024-01-27
Issue
Vol. 8 No. 1 (2024): JIKA (Jurnal Informatika)
Section
Articles

Copyright (c) 2024 JIKA (Jurnal Informatika)

Creative Commons License

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

License and Copyright Agreement

In submitting the manuscript to the journal, the authors certify that:

  • They are authorized by their co-authors to enter into these arrangements.
  • That it is not under consideration for publication elsewhere,
  • That its publication has been approved by all the author(s) and by the responsible authorities – tacitly or explicitly – of the institutes where the work has been carried out.
  • They secure the right to reproduce any material that has already been published or copyrighted elsewhere.
  • They agree to the following license and copyright agreement.

Copyright

Authors who publish with International Journal of Advances in Intelligent Informatics agree to the following terms:

  1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal. 
  2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.

Licensing for Data Publication

International Journal of Advances in Intelligent Informatics use a variety of waivers and licenses, that are specifically designed for and appropriate for the treatment of data:

Other data publishing licenses may be allowed as exceptions (subject to approval by the editor on a case-by-case basis) and should be justified with a written statement from the author, which will be published with the article.

Open Data and Software Publishing and Sharing

The journal strives to maximize the replicability of the research published in it. Authors are thus required to share all data, code or protocols underlying the research reported in their articles. Exceptions are permitted but have to be justified in a written public statement accompanying the article.

Datasets and software should be deposited and permanently archived inappropriate, trusted, general, or domain-specific repositories (please consult http://service.re3data.org and/or software repositories such as GitHub, GitLab, Bioinformatics.org, or equivalent). The associated persistent identifiers (e.g. DOI, or others) of the dataset(s) must be included in the data or software resources section of the article. Reference(s) to datasets and software should also be included in the reference list of the article with DOIs (where available). Where no domain-specific data repository exists, authors should deposit their datasets in a general repository such as ZENODO, Dryad, Dataverse, or others.

Small data may also be published as data files or packages supplementary to a research article, however, the authors should prefer in all cases a deposition in data repositories.