An Intelligent Wireless Sensing and Control System to Improve Indoor Air Quality: Monitoring, Prediction, and Preaction

Abstract

The aim of this study is to construct an intelligent wireless sensing and control system to address health issues. We combine three technologies including (1) wireless sensing technology to develop an extendable system for monitoring environmental indicators such as temperature, humidity and CO2 concentration, (2) ARIMA (autoregressive integrated moving average) to predict air quality trends and take action before air quality worsens, and (3) fuzzy theory which is applied to build an energy-saving mechanism for feedback control. Experimental results show the following. (1) A longer historical data collected time interval will reduce the effects of abnormal surges on prediction results. We find the ARIMA prediction model accuracy improving from 3.19 ± 3.47% for a time interval of 10 minutes to 1.71 ± 1.45% for a time interval of 50 minutes. (2) The stability experiment shows that the error rate of prediction model is also less than 7.5%. (3) In the energy-saving experiment, fuzzy logic-based decision model can reduce the 55% energy while maintaining adequate air quality.