Pengenalan Masker Wajah Menggunakan VGG-16 dan Multilayer Perceptron

Khairul Fadhli Margolang, Sugeng Riyadi, Rika Rosnelly, Wanayumini -

Abstract


The use of face masks during the Covid-19 pandemic can be identified based on images taken of a person's face and then classified based on the results of their feature extraction. VGG 16 is a pre-trained CNN model that can extract 4,096 features from an image and transfer learning to the multilayer perceptron algorithm in classifying someone using a face mask. The results of this study indicate that the combination of ReLu activation with adaptive moment optimization (Adam) and stochastic gradient descent (SGD), the combination of ReLu and Adam, produces the best classification performance with accuracy, precision, and recall values of 98.1%.  Penggunaan masker wajah pada masa pandemi Covid-19 dapat diidentifikasi berdasarkan citra yang diambil dari wajah seseorang kemudian diklasifikasi berdasarkan hasil ekstraksi fiturnya. VGG 16 merupakan sebuah pre-trained CNN model yang dapat mengekstrak 4.096 fitur dari sebuah citra dan melakukan transfer learning kepada algoritme multilayer perceptron dalam mengklasifikasikan seseorang menggunakan masker wajah atau tidak. Hasil dari penelitian ini menunjukkan bahwa kombinasi aktivasi ReLu dengan optimasi adaptive moment (Adam) dan stochastic gradient descent (SGD), kombinasi ReLu dan Adam, menghasilkan performa klasifikasi terbaik dengan nilai accuracy, precision, dan recall sebesar 98,1%.

Keywords


ReLu, Adam, VGG 16, multilayer perceptron, transfer learning

References


C. K. Poetra, S. F. Pane, dan R. N. S. Fatonah, “Meningkatkan akurasi long-short term memory (LSTM) pada analisis sentimen vaksin Covid-19 di Twitter dengan Glove,” J. Telemat., vol. 16, no. 2, hlm. 85–90, 2021.

L. Martinelli, dkk., “Face masks during the Covid-19 pandemic: a simple protection tool with many meanings,” Front. Public Heal., vol. 8, Januari, hlm. 1-12, 2021.

F. Amer, M. Ali, dan M. S. H. Al-Tamimi, “Face mask detection methods and techniques: a review,” Int. J. Nonlinear Anal. Appl, vol. 13, Februari, hlm. 2008–6822, 2022.

G. NaliniPriya, M. Shobana, C. Siva, B. Kanisha, J. K. Monica, dan V. Siva Vadivu Ragavi, “Dynamic face mask detection using machine learning,” dalam 2022 International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN), Juni, 2022, hlm. 1-5.

M. F. Naufal dan S. F. Kusuma, “Pendeteksi citra masker wajah menggunakan CNN dan transfer learning,” J. Teknol. Inf. dan Ilmu Komput., vol. 8, no. 6, hlm. 1293, 2021.

P. R. Togatorop dan A. Fauzi, “Classification of face mask usage using Squeezenet,” Jatisi (Jurnal Tek. Inform. dan Sist. Informasi), vol. 9, no. 1, hlm. 397–406, 2022.

R. Rismiyati dan A. Luthfiarta, “VGG-16 transfer learning architecture for salak fruit quality classification,” Telematika, vol. 18, no. 1, hlm. 37, 2021.

S. Tammina, “Transfer learning using VGG-16 with deep convolutional neural network for classifying images,” Int. J. Sci. Res. Publ., vol. 9, no. 10, hlm. 143-150, 2019.

M. Kurniawan, M. Hakimah, dan S. Agustini, “Perbandingan SVM dan perceptron dengan optimasi heuristik,” J. Telemat., vol. 15, no. 2, hlm. 85–92, 2020.

M. Handayani, M. Riandini, dan Z. Zakarias, “Comparison of neural network optimization functions in candidate husband eligibility classification,” J. Inform., vol. 9, no. 1, hlm. 78–84, 2022.

D. Pardede, B. H. Hayadi, dan Iskandar, “Multilayer perceptron literature review how well this algorithm performs,” J. ICT Apl. Syst., vol. 1, no. 1, hlm. 23–35, 2022.

E. Pirdia Wanti, “Pengidentifikasian citra ikan berformalin dengan menggunakan metode multilayer perceptron,” J. Sains Komput. Inform., vol. 5, no. 1, hlm. 491–502, 2021.

S. Shadkani, A. Abbaspour, S. Samadianfard, S. Hashemi, A. Mosavi, dan S. S. Band, “Comparative study of multilayer perceptron-stochastic gradient descent and gradient boosted trees for predicting daily suspended sediment load: the case study of the Mississippi River, U.S.,” Int. J. Sediment Res., vol. 36, no. 4, hlm. 512–523, 2021.

M. A. Firmansyah, K. N. Ramadhani, dan A. Arifianto, “Pengenalan angka tulisan tangan menggunakan diagonal feature extraction dan klasifikasi artificial neural network multilayer perceptron,” Indones. J. Comput., vol. 3, no. 1, hlm. 65–74, 2018.

J. Pardede, B. Sitohang, S. Akbar, dan M. L. Khodra, “Implementation of transfer learning using VGG-16 on fruit ripeness detection,” Int. J. Intell. Syst. Appl., vol. 13, no. 2, hlm. 52–61, 2021.

J. N. Mogan, C. P. Lee, K. M. Lim, dan K. S. Muthu, “VGG-16 - MLP: Gait recognition with fine-tuned VGG-16 and multilayer perceptron,” Appl. Sci., vol. 12, no. 15, hlm. 1–12, 2022.

Y. Gultom, A. M. Arymurthy, dan R. J. Masikome, “Batik classification using deep convolutional network transfer learning,” J. Ilmu Komput. dan Inf., vol. 11, no. 2, hlm. 189-194, 2018.

O. Gurav, “Face mask detection dataset,” 2020. [Daring]. Tersedia: https://www.kaggle.com/datasets/omkargurav/face-mask-dataset.

K. L. Kohsasih, M. Dipo, A. Rizky, T. Fahriyani, V. Wijaya, dan R. Rosnelly, “Analisis perbandingan algoritme convolutional neural network dan algoritme multilayer perceptron neural dalam klasifikasi citra sampah,” J. Times, vol. 10, no. 2, hlm. 22–28, 2022.

D. Irfan, R. Rosnelly, M. Wahyuni, J. T. Samudra, dan A. Rangga, “Comparison of SGD, Adadelta, and Adam optimization in hydrangea classification using CNN,” J. Sci. Soc. Res., vol. 5, no. 2, hlm. 244-253, 2022.

J. Kusuma, B. H. Hayadi, dan R. Rosnelly, “Comparison of multilayer perceptron (MLP) and support vector machine (SVM) methods for breast cancer classification,” MIND (Multimedia Artif. Intell. Netw. Database) J., vol. 7, no. 1, hlm. 51–60, 2022.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Jurnal Telematika

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

____________________________________________

Institut Teknologi Harapan Bangsa

Jl. Dipatiukur no. 80-84 Lt. 2

Bandung 40132


Creative Commons License

Jurnal Telematika is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.