COVID-19 SOP's Violations Detection in Terms of Face Mask Using Deep Learning

Facemask detection is a need of time as we are suffering in a pandemic situation of COVID-19, and facemask is considered the best preventive measure to stop the rapid spread. The vast majority of the world population is still unvaccinated, especially young and kids. Moreover, despite the vaccination, people are still getting Covid positive, and the majority are due to the Delta variant. So, we still need to have strict SOP implementation. The best way is to have some autonomous system to monitor SOP compliance and alert the authority to take countermeasures. Many people wear the mask, but the mask is usually on the chin and does not serve the purpose because the facemask must cover the mouth and nose to stop the spread. This study has proposed the improved version of the YOLOv4 model for the robust detection of face masks and checks whether the mask is worn in the recommended way. 2D convolutions of Yolov4 are replaced with the spatially separable convolutional in YOLOv4 to reduce the parameters so that the model can work in real-time. We have achieved an accuracy of 86.61% in terms of proper mask-wearing. Unlike other proposed approaches, our model is not only detecting the mask but also determines that whether the mask is worn in the recommended manner.

CNN Based COVID-19 Prediction from Chest X-ray Images

Coronavirus disease COVID-19 is an infectious disease caused by a newly discovered coronavirus. COVID-19 virus affects the respiratory system of healthy individuals. Chest X-ray is one of the important imaging methods to identify the coronavirus. In deep learning, a convolutional neural network (CNN), is a class of deep learning models, most commonly applied for better outcomes to analyzing visual imagery. Automated covid-19 using Deep Learning techniques could, therefore, serve as an effective diagnostic aid. In this study, we used a convolutional neural network (CNN) for detecting COVID-19 from chest X-ray images. The overall project comprises various convolutional layers. The Max-pooling layers diminish the size of the picture significantly and by joining convolutional and pooling layers, the net is able to combine its features to learn more global features of the Image. Eventually, we utilize the highlights in two completely associated (Dense) layers. Dropout is a regularization strategy, where the layer arbitrarily replaces an extent of its weights to zero for each training sample. This forces the net to learn features in an appropriate way, not depending a lot on specific weight, and thus improves speculation and 'relu' is the activation function. Applying convolutional neural network which is a Deep Learning algorithm that can take in an input image, relegate significance to different perspectives in the images and have the option to separate one from the other. © 2021 IEEE.