IMPLEMENTASI ALGORITMA KLASIFIKASI GERAKAN TANGAN POPULER MENGGUNAKAN CUSTOM MODEL CONVOLUTIONAL NEURAL NETWORK (CNN)

Dilan Rizmawan Universitas Singaperbangsa Karawang
Ulinnuha Latifa Universitas Singaperbangsa Karawang

DOI: https://doi.org/10.36546/jte.v14i2.1445

Keywords: Convolutional Neural Network (CNN), Machine Learning, Tensorflow, Transfer Learning

Abstract

Pada penelitian ini, diimplementasikan Convolutional Neural Network (CNN) dengan model kustom untuk mengklasifikasikan Gerakan tangan populer. Dataset dibuat sendiri dengan contoh gerakan tangan yang diambil. Pengujian dilakukan dengan 361 epoch dan batch size 256. Hasil menunjukkan peningkatan konsisten dalam performa model, meskipun akurasi validasi tidak mencapai lebih dari 0.94. Evaluasi model mencapai akurasi 94% dengan nilai loss yang rendah. Laporan klasifikasi menunjukkan kekurangan pada beberapa kelas seperti tumbs down, peace, stop be strong shake sign, bang-bang, dan rock. Namun, kelas seperti tumbs up dan ok memiliki performa terbaik dengan nilai rata-rata 1.00. Dalam penelitian ini, juga menggunakan metode Transfer Learning untuk memperbaiki performa model CNN.

References

R. R. Karim, “IMPLEMENTASI KLASIFIKASI SENJATA TRADISIONAL JAWA BARAT MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) DENGAN METODE TRANSFER LEARNING,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 2, Apr. 2024, doi: 10.23960/jitet.v12i2.4166.

L. Chen, F. Wang, H. Deng, and K. Ji, “A Survey on Hand Gesture Recognition,” in 2013 International Conference on Computer Sciences and Applications, 2013, pp. 313–316. doi: 10.1109/CSA.2013.79.

A. Sani and S. Rahmadinni, “Deteksi Gestur Tangan Berbasis Pengolahan Citra,” Jurnal Rekayasa Elektrika, vol. 18, no. 2, Jul. 2022, doi: 10.17529/jre.v18i2.25147.

J. Jumadi, Y. Yupianti, and D. Sartika, “PENGOLAHAN CITRA DIGITAL UNTUK IDENTIFIKASI OBJEK MENGGUNAKAN METODE HIERARCHICAL AGGLOMERATIVE CLUSTERING,” JST (Jurnal Sains dan Teknologi), vol. 10, no. 2, pp. 148–156, Nov. 2021, doi: 10.23887/jst-undiksha.v10i2.33636.

K. Wisnudhanti and F. Candra, “Image Classification of Pandawa Figures Using Convolutional Neural Network on Raspberry Pi 4,” in Journal of Physics: Conference Series, IOP Publishing Ltd, Nov. 2020. doi: 10.1088/1742-6596/1655/1/012103.

E. Retnoningsih and R. Pramudita, “Mengenal Machine Learning Dengan Teknik Supervised dan Unsupervised Learning Menggunakan Python,” BINA INSANI ICT JOURNAL, vol. 7, no. 2, pp. 156–165, 2020, [Online]. Available: https://www.python.org/

Dufan J. P. Manajang, Sherwin R.U.A. Sompie, and Agustinus Jacobus, “Implementasi Framework Tensorflow Object Detection Dalam Mengklasifikasi Jenis Kendaraan Bermotor,” Jurnal Teknik Informatika, vol. 15, no. 3, pp. 171–178, Sep. 2020.

J. Christian and S. I. Al Idrus, “Introduction to Citrus Fruit Ripens Using the Deep Learning Convolutional Neural Network (CNN) Learning Method,” Asian Journal of Applied Education (AJAE), vol. 2, no. 3, pp. 459–470, Jul. 2023, doi: 10.55927/ajae.v2i3.5003.

D. R. R. Putra and R. A. Saputra, “IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK MENDETEKSI PENGGUNAAN MASKER PADA GAMBAR,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 11, no. 3, Aug. 2023, doi: 10.23960/jitet.v11i3.3286.

rafi Akram, S. Adinda Rachmadinasya, F. Hafidz Melvandino, and H. Ramza, “KLASIFIKASI AKTIVITAS OLAHRAGA BERDASARKAN CITRA FOTO DENGAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 11, no. 3, pp. 2830–7062, 2023, doi: 10.23960/jitet.v11i3%20s1.3496.

A. Lazaro, J. L. Buliali, and B. Amaliah, “Deteksi Jenis Kendaraan di Jalan Menggunakan OpenCV,” Jurnal Teknik ITS, vol. 6, no. 2, Sep. 2017, doi: 10.12962/j23373539.v6i2.23175.

Published

2024-11-15

Issue

Vol 14 No 2 (2024): Jurnal Teknik Elektro

Section

Articles

An author who publishes in the Jurnal Teknik Elektro (JTE) agrees to the following terms:

Author retains the copyright and grants the journal the right of first publication of the work simultaneously licensed under the Creative Commons Attribution-ShareAlike 4.0 License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Submission of a manuscript implies that the submitted work has not been published before (except as part of a thesis, report, or abstract); that it is not under consideration for publication elsewhere; that its publication has been approved by all co-authors. If and when the manuscript is accepted for publication, the author(s) still hold the copyright and retain publishing rights without restrictions. For the new invention, authors are suggested to manage its patent before publication. The license type is CC-BY-SA 4.0.