ABSTRACT
People have been encouraged to wear masks and avoid touching their faces in public as part of the new measures to prevent the spread of coronavirus 2019 (COVID-19). During the COVID-19 epidemic, few research have examined the effect of everyday living on the frequency of facial touch activity. To develop a face touching avoidance system, deep learning algorithms have been proposed and have demonstrated their amazing performance. However, an important drawback of deep learning is its extensive dependence on hyperparameters. The results of deep learning algorithms may vary depending on hyperparameters, such as the size of the filters, the number of filters, the batch size, the number of epochs, and the training optimization technique used. In this paper, we present an effective approach for hyperparameter tuning of convolutional neural networks (CNNs) for efficiently recognized face touching activities based on accelerometer data. Two hyperparameter tuning methods (Grid search and Bayesian optimization) were evaluated in order to construct the CNN with high performance. The experiment results show that Bayesian optimization can provide suitable hyperparameters for CNNs for face touching recognition with the highest accuracy of 96.61%. © 2022 IEEE.
ABSTRACT
Globally, the COVID-19 pandemic has caused dev-Astation and continues to do so even a year after its first outbreak. Behavioral modifications could help to mitigate a mechanism for acquiring and spreading illnesses. Using wearable devices such as smartwatches to recognize face contact has the opportunity to decrease face touching and, therefore, the spread of respiratory disease through fomite transmission. The purpose of this paper is to demonstrate how we can utilize accelerometer data from wristwatch sensors to identify face touching actions using deep learning techniques. We proposed the BiGRU deep learning model for the high-performance recognition of hand-To-face actions. The Face Touching dataset is used as a benchmark for evaluating the recognition accuracy of deep learning networks, including our network model. The experimental findings indicate that the BiGRU surpasses other baseline deep learning models regarding accuracy (98.56%) and F1-score (98.56%). © 2021 IEEE.