Ensemble Deep Learning Approach with Attention Mechanism for COVID-19 Detection and Prediction

New coronavirus (COVID-19), which first appeared in Wuhan City and is now rapidly disseminating worldwide, may be predicted, diagnosed, and treated with the help of cutting-edge medical technology, such as artificial intelligence and machine learning algorithms. To detect COVID-19, we suggested an Ensemble deep learning method with an attention mechanism. The suggested approach uses an ensemble of RNN and CNN to extract features from data from diverse sources, such as CT scan pictures and blood test results. For image and video processing, CNNs are the most effective. RNNs, on the other hand, use text and speech data to extract features. Further, an attention mechanism is used to determine which features are most relevant for classification. Finally, the deep learning network utilizes the selected features for detection and prediction. As a result, data can be used to forecast future medical needs. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Prototype for Integration of Face Mask Detection and Person Identification Model - COVID-19

As people across the globe are combating the widespread COVID-19 pandemic and it becomes very essential to develop new technologies to analyse and fight against the disease spread. The most essential protection against corona virus is Face Mask and as the day surpasses scientist and Doctors have recommended everyone to wear the mask. Therefore, to distinguish the individuals wearing Face Mask, various identification procedures are available. Veils are prescribed as a straightforward obstruction to protect the respiratory beads from going into the air and onto others, when the individual is found to be wearing the cover hacks, wheezes, talks, or raises their voice. Moreover, this is called source control. This proposal depends on the present idea about the job respiratory beads that play a main role in the spread of the COVID-19 infection, matched with developing proof from clinical and research center examinations that show covers and decrease the splash of drops, when worn over the nose and mouth. Coronavirus spreads essentially among individuals who are in close contact with each other (inside around 6 feet), so the utilization of veils is especially significant in settings where individuals are near one another or where social removing is hard to keep up. CDC's suggestions for masks will be updated as new logical proof. Our project is more of a real-world application, the proposed face mask detection platform utilizes artificial network to identify the person with and without mask. If a person is not wearing a mask, then the proposed platform will send a notification to the person if he or she is in the database of the platform. MobileNet_V2 neural networks are used as our classification algorithm and the face recognition module is also used for the person identification model © 2020 IEEE.