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

Allan Andrew,Shaharil Mad Saad,Mohamed Hussein,Zair Ahmad,Mohd Mat Dzahir,Maziah Mohamad,Ali Md Shakaff

doi:10.3390/app7080823

Abstract

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

Highlights

The issue of outdoor air pollution (OAP), such as haze, is well known to the public due to the attention given to it by the media
There are various supervised machine learning used in classification techniques, which can be sorted into a few categories: logic-based, perceptron-based, instance-based, statistical learning-based and vector-based [54]
Three algorithms which have been used in many applications, especially involving odour or smell classification, have been chosen: multilayer perceptron (MLP), K-nearest neighbour (KNN), and linear discrimination analysis (LDA) [55,56,57]

Summary

Introduction

The issue of outdoor air pollution (OAP), such as haze, is well known to the public due to the attention given to it by the media. The issue of indoor air pollution (IAP) is less known to the public, IAP poses similar threats towards human health. More attention should be given to the issue of IAP, because people normally spend 90% of their time in indoor environments [1]. IAP can be defined as the disturbance of any gases, materials or human activities on the state of ambient air in indoor environment [2]. As long as the concentration in the normal ambient air is disturbed either by gases, other materials or combustion activity, it is already considered as pollution.

Objectives

Results

Conclusion