An Edge Computing Approach to Explore Indoor Environmental Sensor Data for Occupancy Measurement in Office Spaces

Abstract

Human occupancy measurement has become a topic of increasing interest in the past few years, due to the important role it plays in controlling a number of demand-driven applications like smart lighting and smart heating, as well as improving the energy efficiency of these applications in a broader sense. Office occupancy monitoring in commercial buildings can yield huge savings and improvements in terms of thermal, visual, and air quality. However, this is often impeded due to the lack of fine-grained occupancy information. This paper explores the use of low-priced environmental (temperature and humidity) sensor data for measuring occupancy in an office space. The idea behind this work is to leverage the variation divergence between humidity and temperature caused by human presence. We used a Raspberry Pi with a daughterboard called Sense Hat, which is equipped with the environmental sensors used in this study. The results are compared with occupancy data obtained from camera feeds in order to assess the effectiveness and the accuracy of the combined occupancy measurements, and show up to 87% accuracy.

Estimating Occupancy Levels in Enclosed Spaces Using Environmental Variables: A Fitness Gym and Living Room as Evaluation Scenarios

“…Another alternative approach to detect occupancy is through statistical analysis. Zemouri et al [ 33 ] compared the performance of Machine Learning to detect occupancy against an algorithm developed using statistical analysis, obtaining accuracies of 0.82 and 0.87, respectively. Although they obtained a higher accuracy using statistical analysis, the authors highlighted two significant drawbacks of this approach: (1) the requirement of expert knowledge in the subject area and knowing the physical properties of the variables measured; (2) the slower and more costly performance of this approach, compared to Machine Learning, due to the manual extraction of features.…”

Indoor Air Quality Monitoring Systems Based on Internet of Things: A Systematic Review

“…Furthermore, 20 studies [ 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 , 42 , 43 , 44 , 45 , 46 , 47 ] were removed due to missing information about the design methodology and the type of sensors used for measuring IAQ parameters (IC4, EC3). In addition, five more studies [ 48 , 49 , 50 , 51 , 52 ] were excluded as they were focused on thermal comfort parameters only or had no relevant details about IAQ sensors (IC2, IC3, EC3). After applying inclusion and exclusion criteria, 40 studies were found eligible for conducting this systematic review.…”

Indoor Localization for Personalized Ambient Assisted Living of Multiple Users in Multi-Floor Smart Environments

“…This functionality allowed the system to work with a smaller number of RSSI datapoints while still being able to detect the indoor location of the user with a high accuracy that was deduced by the authors from the results of their experimental trials that included 15 participants. In addition to the above, recent works in this field have focused on building tailored magnetic maps for smartphones [70,71] and using edge computing approaches to analyze environmental sensor data [72,73] for indoor localization. While a few recent works [74][75][76][77][78][79][80] have investigated approaches for floor detection in the context of indoor localization but the performance characteristics of such systems are not that high to support widescale deployment and real-time implementation of the same.…”