Data analytics and modelling for indoor occupant states

Abstract

This paper presents a study on data analysis and modeling of indoor occupant states in a built environment. The objective of this research is to investigate the impact of environmental parameters, such as CO2 concentration, temperature, humidity, air-conditioning fan speed, and air-conditioning power on the status of indoor personnel. The study employs data analytics techniques to obtain insights from IoT sensor data related to occupants. Pre-processing of data and correlation analysis are conducted to provide meaningful insights into the activities of occupants and their interactions with the indoor environment and appliances. The study further employs data-driven modeling methods to predict and forecast indoor occupant status and behaviors. Feature selection and feature importance study are carried out to identify relevant variables for the model. Python programming language is used to organize and visualize the data, and to train the models. The results of the study indicate that the identified environmental parameters have a significant impact on the state of indoor personnel. The significance of this research lies in its contribution to the field of indoor environment and occupant health. The study demonstrates the importance of big data analytics and modeling techniques in understanding the impact of environmental parameters on occupant states. The findings of this research can help in improving the design and operation of indoor environments, as well as in enabling people to adjust the parameters according to their desired state. This paper serves as a valuable reference for researchers and practitioners in the field of indoor environment and occupant health.