Abstract
Abstract. The knowledge about the occupancy of an indoor space can serve to various domains ranging from emergency response to energy efficiency in buildings. The literature in the field presents various methods for occupancy detection. Data gathered for occupancy detection, can also be used to predict the number of occupants at a certain indoor space and time. The aim of this research was to determine the number of occupants in an indoor space, through the utilisation of information acquired from a set of sensors and machine learning techniques. The sensor types used in this research was a sound level sensor, temperature/humidity level sensor and an air quality level sensor. Based on data acquired from these sensors six automatic classification techniques are employed and tested with the aim of automatically detecting the number of occupants in an indoor space by making use of multi-sensor information. The results of the tests demonstrated that machine learning techniques can be used as a tool for prediction of number of occupants in an indoor space.
Highlights
Occupancy detection and occupant number prediction have a critical importance in order to increase the automation capability of buildings and to strengthen the decision-making capabilities of emergency responders and facility managers
The Machine Learning (ML) model generated using Deep Learning (DL) algorithm has been successful in predicting the number of occupants with 88.99% +/- 2.39% success rate, which showed a better performance compared to Naïve Bayes (NB) and Generalized Linear Model (GLM)
The ML model generated using DT algorithm in our study has been successful in predicting the number of occupants with 92.47% +/- 1.17% success rate, which showed a better performance compared to NB, GLM, DL, but the performance was worse than DT
Summary
Occupancy detection and occupant number prediction have a critical importance in order to increase the automation capability of buildings and to strengthen the decision-making capabilities of emergency responders and facility managers. Automatic prediction of the number of occupants of an indoor space is an active research problem, and today Machine Learning emerges as a key tool to deal with it. In the Supervised Learning approach, a human provides a machine with the training data containing the independent/predictor variables and the correct values of the dependent variable which needs to be predicted later by the machine. The aim of this research was to determine the occupancy status and several occupants in an indoor space, through the utilisation of a set of sensors and machine learning techniques. Based on data acquired from these sensors automatic classification techniques are employed to detect the number of occupants in an indoor space. Following the background on the subject, data acquisition and machine learning processes in the study are elaborated in the paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
