Pollutant Recognition Based on Supervised Machine Learning for Indoor Air Quality Monitoring Systems

2017-08-13T09:45:58Z (GMT) by Allan Melvin Andrew
<div>Indoor air may be polluted by various types of pollutants which may come from cleaning</div><div>products, construction activities, perfumes, cigarette smoke, water-damaged building materials and</div><div>outdoor pollutants. Although these gases are usually safe for humans, they could be hazardous</div><div>if their amount exceeded certain limits of exposure for human health. A sophisticated indoor air</div><div>quality (IAQ) monitoring system which could classify the specific type of pollutants is very helpful.</div><div>This study proposes an enhanced indoor air quality monitoring system (IAQMS) which could</div><div>recognize the pollutants by utilizing supervised machine learning algorithms: multilayer perceptron</div><div>(MLP), K-nearest neighbour (KNN) and linear discrimination analysis (LDA). Five sources of indoor</div><div>air pollutants have been tested: ambient air, combustion activity, presence of chemicals, presence</div><div>of fragrances and presence of food and beverages. The results showed that the three algorithms</div><div>successfully classify the five sources of indoor air pollution (IAP) with a classification rate of up to</div><div>100 percent. An MLP classifier with a model structure of 9-3-5 has been chosen to be embedded into</div><div>the IAQMS. The system has also been tested with all sources of IAP presented together. The result</div><div>shows that the system is able to classify when single and two mixed sources are presented together.</div><div>However, when more than two sources of IAP are presented at the same period, the system will</div><div>classify the sources as ‘unknown’, because the system cannot recognize the input of the new pattern.</div>