Edge Computing-Based Internet of Things Framework for Indoor Occupancy Estimation

Edge Computing-Based Internet of Things Framework for Indoor Occupancy Estimation

Krati Rastogi (Shiv Nadar University, India) and Divya Lohani (Shiv Nadar University, India)
Copyright: © 2020 |Pages: 22
DOI: 10.4018/IJACI.2020100102
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Indoor occupancy estimation has become an important area of research in the recent past. Information about the number of people entering or leaving a building is useful in estimation of hourly sales, dynamic seat allocation, building climate control, etc. This work proposes a decentralized edge computing-based IoT framework in which the majority of the data analytics is performed on the edge, thus saving a lot of time and network bandwidth. For occupancy estimation, relative humidity and carbon dioxide concentration are used as inputs, and estimation models are developed using multiple linear regression, quantile regression, support vector regression, kernel ridge regression, and artificial neural networks. These estimations are compared using execution speed, power consumption, accuracy, root mean square error, and mean absolute percentage error.
Article Preview
Top

1. Introduction

Air quality has a direct impact on human health and to the productivity and comfort of the people. As air is all around us and constantly needed for survival, it is important that the air we breathe is clean and free from hazardous pollutants. Indoor air quality (IAQ) is an important factor for human health because the present generation spends most of the time indoors- in their homes, offices, factories, schools, malls and theatres. Poor levels of indoor quality may cause allergy or asthma symptoms, sinus trouble, coughing, fatigue, eye irritation, nausea, skin rashes and other health problems. Continued poor air quality conditions may cause sick building syndrome.

Maintaining good levels of air quality in non-residential buildings such as factories, malls, offices and educational institutions is important to enhance the well-being, comfort and productivity of the occupants. Main factors that affect IAQ are ventilation, occupancy, and the surrounding air. Ventilation helps in maintaining proper air quality by circulating the air in and out, thus diffusing harmful pollutants and bringing in fresh air. The presence and activates of people leads to deterioration of IAQ. The number of occupants present in a building or enclosed area considerably affects the air quality as CO2 is released with the air exhaled by individuals. The change in the number of occupants changes the ventilation and cooling/heating requirement of the enclosed space.

Occupancy of non-residential buildings is constantly fluctuating as people enter and leave shops, malls, theatres, offices, factories and schools for work purposes, communicating with others, attending lectures, delivering goods, relishing food or watching shows. Keeping a count on the number of occupants is useful in improving building security, estimating building energy demand, tracking human movement, finding if some space is occupied or not and rescuing survivors in emergencies such as fires. Occupancy estimation can thus be classified into (Akkaya et al 2015):

  • 1.

    Occupancy Detection: This problem addresses the presence or absence of occupants. The result is zero if the space is unoccupied and one if one if occupants are present. The count of occupants is not taken care of in this problem;

  • 2.

    Occupancy Counting: Contrary to the first problem, this problem takes into record, the number of persons a place is occupied with;

  • 3.

    Occupancy Tracking: It is the super-set of the above problems in the sense that it not only detects occupancy of a space, but also takes into account, the occupancy count of the place;

  • 4.

    Occupancy Event/ Behaviour Recognition: If occupants are detected at a space under study, the activity or behaviour of the occupant is analysed using this problem. Figure 1 shows the relationship between different occupancy monitoring problems discussed in the above paragraph.

Figure 1.

Classification of occupancy monitoring problems

IJACI.2020100102.f01

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 13: 6 Issues (2022): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing