ABSTRACT
Artificial intelligence is now penetrating into all the domains. Any domain can incorporate artificial intelligence to automate their process. In the outbreak of COVID pandemic, artificial intelligence has been very useful in many ways. artificial intelligence helps in automating process where it's not always possible for people to do and to reduce the wastage of human resource. Here we proposed a frame work to automate the detection of covid protocol violation in public places. Our work detecting people with & without masks and detects social distancing with a single model. The best performing model from the standard convolution neural network architectures namely VGG16 and MobileNetV2 are used in the present work, from the experiments it's found that MobileNetV2 outperformed VGG16. The developed system can easily be integrated/implemented on various embedded devices with limited computational capacity by using the MobileNetV2 architecture. Compared to other previous works, our work outstands by having good accuracy and compatible to use in real life application because of its requirement of less computational complexity. © 2022 IEEE.
ABSTRACT
SARS-COV-2, also known as COVID-19 pandemic, has escalated calamity in the entire world. Due to its contagious properties, the disease spreads swiftly from person to person via direct contact. More than 210 million people got infected worldwide with more than 18 million active patients as of August 29, 2021. In numerous places, the test process for COVID-19 detection takes longer than 2 days. Once the patient is affected by COVID-19, the obstruction in lungs causes difficulty in analyzing the presence of other lung diseases, such as variants of pneumonia. In this paper, we propose an enhancement technique via the acclaimed signal processing method called variational mode decomposition (VMD) aiding any X-ray image classification method for the detection of pneumonia using convolutional neural networks (CNN). The experiments were conducted on VGG-16 model loaded with ImageNet weights followed by numerous configurations of dense layers. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.