Deteksi Masker Pencegahan Covid19 Menggunakan Convolutional Neural Network Berbasis Android

Abstract

Masks are an important part of preventing Covid19 disease.The World Health Organization (WHO) have also recommended the community use masks when doing activities in public areas. There are many types of masks that are used to cover the nose and mouth. In general, there are about 3 types of masks that are commonly used by the public today, namely medical masks, N95 and cloth masks. This study aims to detect the type of mask used by the community. So that it can make easier for the government to apply discipline in COVID-19 health protocol. The detection method used in this study is a convolutional neural network (CNN). The first step is acquisition of knowledge, which first collects the types of masks on the market, followed by the representation of that knowledge before being modeled into a mathematical calculation formula, which will then be processed using the Convolutional Neural Network method. The system will be carried out by analyzing the recall value, its precision and accuracy.Testing process is carried out on an Android-based device and the mobilenetV2 framework. In this study, the accuracy value is 90% using ADAM Optimization and 80 % using Gradient descent optimization.

Mask Detection Using Convolutional Neural Network Algorithm

“…The mask detection model using the CNN method was created using Python with the help of Tensorflow and Keras, a framework used to create machine learning and deep learning models. While Keras is a Neural Network API that has the ability to run on Tensorflow [4].…”

“…There are about three types of masks that are now commonly used by some people, such as cloth or scuba masks, surgical or medical masks, and N-95 masks. With the various types of masks, sometimes they are not used according to the standards set by WHO, the standard is to ensure that the mask covers the nose and mouth, which is adjusted to the bridge of the nose to minimize the gap between the face and the mask [4].…”

“…The development of technology such as Artificial Intelligence (AI) is one of the technologies that is increasingly being applied by several researchers in recent years [4]- [8] to detect or recognize objects in an image [9]. One of the methods of artificial intelligence technology is the Deep Learning (DL) method, which is part of the science of Machine Learning (ML) based on artificial neural networks (ANN).…”

“…Research conducted by Nyoman Purnama, et al [4] performed mask detection using CNN with two optimizations, namely Adam and Gradient Descent. Based on the test results using the MobileNetV2 pretraining model, it produces an accuracy value of 90% using CNN optimization, namely Adam, and 80% from Gradient Descent optimization.…”

Deteksi Ketepatan Pengunaan Masker Wajah dengan Algoritma CNN dan Haar Cascade

“…Dalam sistem pendeteksian penggunaan masker wajah telah mengalami kemajuan yang signifikan dalam domain pemrosesan gambar dan visi komputer, sejak maraknya pandemi Covid-19 [6], karena visi komputer telah terbukti sebagai aspek revolusioner dari teknologi modern [7]. Saat ini ada beberapa metode yang digunakan dalam mendeteksi penggunaan masker wajah diantaranya yaitu Convolutional Neural Network (CNN) [8] [14], You Look Only Once(YOLO) [15][16] [17], dan menggunakan teknik Hybrid Deep Transfer Learning [1] [6]. Dari berbagai macam metode yang digunakan dalam deteksi wajah dan pengenalan citra untuk mendeteksi penggunaan masker wajah [10], kemampuan Convolutional Neural Network (CNN) diklaim sebagai metode terbaik dalam hal deteksi objek dan pengenalan objek [8] [18].…”