Explainable AI for Gas Sensors

Releasing harmful pollutants like ozone and nitrogen dioxide gas into the atmosphere has been a serious concern in recent times. Such gases endanger the health of humans as well as other species and cause damage to the environment. As a result, it has become vital to monitor the air quality around us. With technological advancement, low-cost chemical gas sensors equipped with machine learning or deep learning algorithms can be employed to detect these gases and their concentrations. However, with the use of such algorithms, there comes a challenge to understanding why they made certain predictions in human terms. This paper aims to address this difficulty by adopting different methodologies of explainable artificial intelligence (XAI) for gas sensors. These methods in turn help understand the reasoning behind the predictions made by the models and at the same time facilitate the characterization of the sensor behavior.