Thermal Comfort Quality Monitoring and Controlling using Fuzzy Inference System Based on IoT Technology

Abstract

The environment indoor quality (EIQ) is linked to human health, comfort, performance, and well-being. Thermal comfort quality (TCQ) is one of the most critical issues in the quality of the EIQ. Thermal comfort pollutants (TCP), consisting of temperature and humidity, significantly impact the quality of human life because indoor pollutants are ten times worse than outdoor air pollutants. This research presents TCP monitoring and controlling using a fuzzy inference system (FIS) based on IoT technology to detect, control, identify, and classify the thermal comfort index (TCI) in four levels: most comfort, not comfort, and least comfort. This research used the IoT concept to monitor temperature and humidity toxicity levels. The results from the calibration tests for the temperature and humidity sensors show that the maximum error remains below 5% and that the sensors demonstrated high accuracy, with any deviations from the expected values being minimal and within the acceptable range. Prototype experiment results show that the system performs exceptionally well, with a maximum error between the prototype and the simulation of only 0.4%. The system can produce TCI ranges for most comfort (2.25-3), comfort (1.5-2.25), not comfort (0.75-1.5), and least comfort (0.75), with varying output responses for each cluster. Mechanical ventilation, alert, and notification output are presented to get efficient and accurate action to mitigate the TCP and notify the user about the TCP condition.