Occupancy Detection in Room Using Sensor Data

Abstract

Purpose-With the advent of Internet of Thing (IoT), and ubiquitous data collected every moment by either portable (smart phone) or fixed (sensor) devices, it is important to gain insights and meaningful information from the sensor data in context-aware computing environments. Many researches have been implemented by scientists in different fields, to analyze such data for the purpose of security, energy efficiency, building reliability and smart environments. One study, that many researchers are interested in, is to utilize Machine Learning techniques for occupancy detection where the aforementioned sensors gather information about the environment. This paper provides a solution to detect occupancy using sensor data by using and testing several variables. Additionally we show the analysis performed over the gathered data using Machine Learning and pattern recognition mechanisms is possible to determine the occupancy of indoor environments. Seven famous algorithms in Machine Learning, namely as Decision Tree, Random Forest, Gradient Boosting Machine, Logistic Regression, Naive Bayes, Kernelized SVM and K-Nearest Neighbors are tested and compared in this study.

Fundamentals, Algorithms, and Technologies of Occupancy Detection for Smart Buildings Using IoT Sensors

“…These algorithms often create a model of the room and its occupancy patterns using data from various sensors, including temperature sensors, CO 2 sensors, light sensors, and sound sensors [64]. In order to increase their accuracy and performance over time, machine learning algorithms can be employed for both supervised and unsupervised learning.…”

“…A supervised machine learning approach called Support Vector Machine (SVM) is utilized for classification and regression tasks [52,64,70]. SVMs can be used in occupancy detection to ascertain if a space (for example, a room) is occupied based on specific traits or qualities.…”

“…Feature Selection: In this step, we choose which input variables or features to include in the SVM model. The objective is to choose the most pertinent features to classify occupancy status using SVM accurately [52,64,70]. We explain some related terminologies as follows.…”

“…Finding the hyperplane that best divides the data into various classes is the main goal of SVM. Spaces that are occupied and vacant [52,64,70].…”

“…SVM uses a kernel trick to translate the data into a higher-dimensional space where it might become linearly separable in order to handle this. Typical kernel operations include [52,64,70] • Linear Kernel: This is used for linearly separable data. These metrics provide insight into the SVM model's performance and determine whether it satisfies the requirements for occupancy detection.…”