Machine Learning Model for Reduction of Airborne Infections and Cognitive Load in a Car Cabin

Abstract

The importance of medical care has grown massively, making it one of life's most essential components. People often use their vehicles in recirculation mode to provide optimum cooling in many cities with high air humidity and temperatures. On the other side, the recirculation mode of the cabin's air prevents O₂ from entering and causes a rise in CO₂. Increased health concerns, a decline in focus, and poor performance are all related to the increased CO₂ concentration brought on by human exhale and metabolism. The paper describes an experimental investigation on how carbon dioxide builds up in a car's interior as a  result of metabolism and breathing by passengers; specific levels of this gas may be dangerous for everyone inside, especially drivers. It is critical to maintain cabin concentration levels within the authorized limits since inhaling this gas may impair a driver's ability to make intelligent decisions. Opening the cabin windows may be a practical, easy, and affordable way to do this. Opening the cabin windows, though might always make it less comfortable inside. As a response, given model passengers can temporarily open the windows may significantly affect how much CO₂ is present within the cabin. Using Our MVPR machine learning model and we demonstrate a GUI Framework, that can predict the forecast of CO₂ concentrations in a cabin at a particular time, temperature, and relative humidity to avoid negative health impacts caused by CO₂ gas.