|
Machine Learning Enabled-System for Screening Covid-19 Kind of Disease for Dense Population Sectors |
|---|---|
| รหัสดีโอไอ | |
| Creator | Mohammed Mahaboob Basha |
| Title | Machine Learning Enabled-System for Screening Covid-19 Kind of Disease for Dense Population Sectors |
| Contributor | Bhuvaneswari P, V Madhurima, Lachi Reddy Poreddy, Srinivasulu Gundala |
| Publisher | Faculty of Engineering Mahasasakham University |
| Publication Year | 2568 |
| Journal Title | Engineering Access |
| Journal Vol. | 11 |
| Journal No. | 1 |
| Page no. | 128-133 |
| Keyword | Covid-19, Detection, Machine learning, Rehabilitation, Power consumption |
| URL Website | https://ph02.tci-thaijo.org/index.php/mijet/index |
| Website title | THAIJO Engineering Access |
| ISSN | 2730-4175 |
| Abstract | The Covid-19 and kind of pandemics flare-up has caused the world to suffer from health crisis and the situation in the developing countries is deplorable. The ever-growing cases are pushing the nation's well-being framework. The most effective way to protect yourself is to wear the face mask of your face in all areas of dense population. According to studies, wearing a mask reduces the chance of transmission. Cleanliness is a reference to practices that improve health and anticipation, specifically through orderliness, like hand washing. Hand washing is a great way of preventing transmission of virus which is transmitted through contact. A method of utilizing the human mind to build an environment that is solid and stable in a symbiotic environment that is strong and smart. A crossover model combining traditional and profound Deep Learning is going to be developed for mask recognition. In this paper we employ a training set to identify faces with a greater accuracy from live stream of camera. Infrared thermal sensors have been used for temperature estimation and safe following. Entryway regulators based on Raspberry Pi help security personnel avoid getting stuck in different locations, such as banks, entrances to schools, bank doors and medical clinic entrances. The validation factor of accuracy 0.97 and loss 0.02 were achieved. |
