English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The COVID-19 pandemic has disrupted various levels of society. The use ofmasks is essential in preventing the spread of COVID-19 by identifying an imageof a person using a mask. Although only 23.1% of people use masks correctly,Artificial Neural Networks (ANN) can help classify the use of good masks tohelp slow the spread of the Covid-19 virus. However, it requires a largedataset to train an ANN that can classify the use of masks correctly.MaskedFace-Net is a suitable dataset consisting of 137016 digital images with 4class labels, namely Mask, Mask Chin, Mask Mouth Chin, and Mask Nose Mouth.Mask classification training utilizes Vision Transformers (ViT) architecturewith transfer learning method using pre-trained weights on ImageNet-21k, withrandom augmentation. In addition, the hyper-parameters of training of 20epochs, an Stochastic Gradient Descent (SGD) optimizer with a learning rate of0.03, a batch size of 64, a Gaussian Cumulative Distribution (GeLU) activationfunction, and a Cross-Entropy loss function are used to be applied on thetraining of three architectures of ViT, namely Base-16, Large-16, and Huge-14.Furthermore, comparisons of with and without augmentation and transfer learningare conducted. This study found that the best classification is transferlearning and augmentation using ViT Huge-14. Using this method onMaskedFace-Net dataset, the research reaches an accuracy of 0.9601 on trainingdata, 0.9412 on validation data, and 0.9534 on test data. This research showsthat training the ViT model with data augmentation and transfer learningimproves classification of the mask usage, even better than convolutional-basedResidual Network (ResNet).

Mask Usage Recognition using Vision Transformer with Transfer Learning and Data Augmentation