Modifikasi Arsitektur Single Shoot Mulibox Detector Untuk Deteksi Penggunaan Masker
DOI:
https://doi.org/10.26877/jeti.v2i2.156Abstract
Abstrak— berakhirnya pandemi covid-19 berimbas pada monitoring penggunan masker yang semakin diabaikan, meskipun memakai masker dapat mengurangi resiko penularan. Memanfaatkan Artificial Intelegence untuk melakukan object detection menjadi salah satu solusi agar monitoring tetap dapat dilaksanakan, salah satunya dengan metode Single Shoot Multibox Detector (SSD) [1]. Arsitektur SSD memiliki 3 layer utama yaitu, base network, extra convolutional feature layers, dan convolutional predictor layer. Convolutional predictor layer menghasilkan 8732 deteksi untuk tiap kelas, dari hasil kombinasi base network dan extra convolutional feature layer dengan default boxes. Pada penilitian ini, arsitektur SSD dilakukan modifikasi (SSD v2) pada convolutional predictor layer yang hanya mendapat input dari extra convolutional feature layers, sehingga deteksi yang dihasilkan berkurang menjadi 790 deteksi. Dari hasil training dan testing dalam melakukan deteksi masker, SSD v2 mempunyai mAP sebesar 87,23%, sedangkan SSD mempunyai mAP sebesar 92,79%. Akan tetapi, SSD v2 memiliki nilai loss yang lebih kecil yaitu sebesar 1,03, sedangkan SSD v2 memiliki nilai loss 1,39.
Kata kunci: Masker; Artificial Intelegence; Object detection; SSD
References
W. Liu dkk., “SSD: Single shot multibox detector,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9905 LNCS, hal. 21–37, 2016.
F. O. R. L. Arge dan C. I. Mage, “VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION,” hal. 1–14, 2015.
I. Vasilev, D. Slater, G. Spacagna, P. Roelants, dan V. Zocca, Python Deep Learning. 2019.
A. H. Reynolds, “Convolutional Neural Network (CNNs),” https://anhreynolds.com, 2019. [Daring]. Tersedia pada: https://anhreynolds.com/blogs/cnn.html. [Diakses: 08-Jun-2023].
J. W. G. Putra, “Artificial Neural Network,” 2020.
Hecht-Nielsen, “Theory of the backpropagation neural network,” in International 1989 Joint Conference on Neural Networks, 1989, hal. 593–605 vol.1.
S. Ruder, “An overview of gradient descent optimization,” hal. 1–14, 2016.
J. Hui, “mAP (mean Average Precision) for Object Detection,” https://jonathan-hui.medium.com/, 2018 [Daring].Tersedia pada: https://jonathan-hui.medium.com/map-mean-average-precision-for-object-detection-45c121a31173.[Diakses: 13-Jun-2023].
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Bayu Krisna Mukti
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
JETI : Jurnal Elektro dan Teknologi Informasi is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
You are free to:
Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Under the following terms:
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
