Air Condition Management for Smart Living Area Networks
Abstract
With the development of affordable sensors, real-time geospatial assessment of the quality of indoor air is now possible. It might be difficult to choose among the many low-cost sensors (LCSs) that are available. Our goal is to combine the knowledge from several study domains to convert every sensor into a whole sensing network, therefore establishing IAQ as a crucial element of smart homes. Modern the field of home automation for networked indoor air quality LCSs-based IAQ control and monitoring is the main topic of this study. To transform conventional homes into smart homes, critical procedures such developing models for forecasting, processing information, sensor selection, and distribution methods are essential. We have delineated the advantages and constraints of air pollution LCSs for spatial mapping of IAQ by means of an extensive synthesis of data. Prior to deployment, it is advised to assess the effectiveness of LCSs in a controlled laboratory environment for quality assurance and control. On the other hand, a sensor network requires constant calibration or the use of statistical methods while it is in operation, particularly for long-term monitoring. The position and penetration height of occupants inside their dwellings should be taken into consideration while adjusting the deployment height of cameras for spatiotemporal mapping. Appropriate processing information technologies are required to manage vast volumes of multivariate data in order to automate both pre- and post-processing operations and provide more scalable, dependable, and adaptable solutions. The paper also emphasizes how machine learning methods may be used to forecast spatiotemporal IAQ in LCS systems with networks.