Learning desk fan usage preferences for personalised thermal comfort in shared offices using tree-based methods

A review of research on dynamic thermal comfort

“…Personal environment control can be combined with dynamic airflow, and local dynamic air supply can be achieved by using devices such as desktop fans. 86 It can be combined with local temperature adjustment equipment, such as heating insoles, heating/cooling seats, etc., to achieve local heating or cooling. 87 It can also couple multiple environmental adjustment devices to achieve higher thermal comfort of the human.…”

A Review of the Recent Developments in Integrating Machine Learning Models with Sensor Devices in the Smart Buildings Sector with a View to Attaining Enhanced Sensing, Energy Efficiency, and Optimal Building Management

“…It can be seen that 32% of the scientific papers selected and summarized in Table S6, presented in the Supplementary Materials file, analyze smart buildings in general, while 53% target exclusively smart homes, 11% take into consideration smart office buildings, and the remaining 4% analyze smart spaces. The authors of these papers make use of different types of sensors, including wireless sensor networks [17,21,53,79]; sensors for detecting carbon dioxide concentration [1,17,50,53,68,78]; sensors for detecting total volatile organic compounds [68]; air temperature and humidity sensors [1,50,53,68,80]; pressure sensors [5,80]; wind speed sensors [50,80]; motion sensors [30,78,81]; Passive Infrared (PIR) sensors [30,82]; electricity meters [1,78,81]; smartphone sensors and Bluetooth beacon data [19]; indoor environment sensors [1]; occupancy information sensors [1]; sensors measuring the visibility outside the building [80]; sensors embedded in the environment [81]; wearable and environmental sensors [53,74]; binary infrared sensors [83]; unobtrusive sensing modules, including a gateway and a set of passive sensors [14]; simple non-intrusive sensors, door sensors and occupancy sensors …”

“…In these papers, the reasons for using the Decision Tree integrated with sensor devices in smart buildings were mainly related to human activity recognition [1,5,14,17,19,21,30,50,53,68,69,74,[78][79][80][81][82][83][84]. In some of these papers, human activity recognition was just a first step, subsequently focusing on: analyzing and improving the energy prediction performance [1,80]; analyzing and ensuring the thermal comfort of the occupants [50,53]; forecasting energy consumption [21]; estimating the number of occupants [78]; identifying behavioral patterns [79]; detecting deviating human behavior [82]; monitoring the activities of elderly people living alone [14]; classifying the gender of occupants [5]; and improving home-based assisted living [30].…”

“…With respect to the devised research methods, in [ The performance metrics chosen by the authors of the scientific papers that used the Decision Tree method integrated with sensor devices in smart buildings included Accuracy [1,5,17,19,50,53,68,74,80]; Confusion Matrix [19]; Precision [19,30,69,74,80]; Recall [19,69,74,80]; F1 Score [19,74]; Standard Deviation [1]; Root Mean Square Error (RMSE) [17,21,68,80]; Mean Percentage Error (MPE) and Mean Absolute Percentage Error (MAPE) [21]; Average Error of Occupancy Estimation [78]; Normalized Root-Mean-Square Error and Coefficient of Variation of the RMSD (CV) [17]; True Positive Rate and True Negative Rate [68,80]; Mean Absolute Error (MAE) [68,80,84]; Runtime [79]; the Receiver Operating Characteristic (ROC) curve [80]; the F-Measure [30,69,80,81]; Recognition Success Rate [83,84]; Sensitivity (SN), Specificity (SP) and Area Under the Receive...…”

“…Ensuring the wellbeing of inhabitants in smart office buildings in terms of personal thermal comfort is a topic that has been approached in a recent paper [50], in which Shetty et al analyzed and compared the performance of several machine learning approaches, namely Decision Tree, Random Forest, and Boosted Trees with data recorded from sensors measuring the air temperature, relative humidity, air speed and CO 2 , with to the aim of classifying a desk fan's state and forecasting its speed in accordance with individual preferences regarding desk fan usage. In order to compare the results obtained for each of the machine learning approaches, the authors computed the Overall Prediction Accuracy, the On State Accuracy, the Present State Accuracy, the Confusion Matrix, the Mean Squared Error (MSE), the Root-Mean-Squared Error (RMSE), and the Average Test Accuracy performance metrics, concluding that the Random Forest approach registered the highest performance level.…”