Feasibility study to detect occupant thermal sensation using a low-cost thermal camera for indoor environments in Indonesia

Abstract

This paper concerns the feasibility study of 7 classes of thermal sensation detection in Indonesia's indoor environment using a low-cost thermal camera through face skin temperature. This study is required as an initial step to build a thermal comfort sensor system of HVAC control systems to produce a comfortable indoor environment with minimum and efficient energy use. The feasibility study was started by studying the thermoregulation system of respondents in Indonesia through measuring their body and facial skin temperatures under heating and cooling conditions, including their relationship with thermal sensations. The facial skin temperature variable, which is covered by four measurement points, namely forehead, nose, cheeks, and chin, represents the MST variable by the coefficient of determination of 0.54. The thermal sensation detection algorithm based on Artificial Neural Network (ANN) is 35.7% of accuracy. The thermal sensation questionnaire with 7 class categories is unsuitable for Indonesian respondents, and the number of the category classes predicted too much compared to the number of inputs. The detection algorithm has better accuracy with a smaller number of classes, namely 52.2% and 68.70% for the 5 and 3 classes of thermal sensation. Practical application: The air conditioning buildings system is possible to influence a thermal environmental control system to meet the occupants' thermal comfort level requirement in an indoor environment if the system is equipped with a sensor that can detect the occupants' thermal sensations. The thermal camera can be used as a non-contact sensor, detecting the occupant’s thermal sensation by reading the occupant's face skin temperature in an indoor environment.

Variables That Affect Thermal Comfort and Its Measuring Instruments: A Systematic Review

“…As for skin temperature, this variable was covered in more specific studies. For example, Faridah F. et al [49] detected thermal sensations from facial skin temperature using a thermal camera.…”

Smart detection of indoor occupant thermal state via infrared thermography, computer vision, and machine learning

“…Wang et al [21] used a TIR camera to measure the upper body temperatures of a subject and directly control the indoor set-point temperature. Faridah et al [22] used skin temperatures of the forehead, nose, cheek, and chin of 17 male subjects in an artificial neural network to predict their thermal states, reaching a highest accuracy (on a seven-point scale) of 69%. Li et al [23] used TIR cameras to measure skin temperature at six local body parts (the forehead, nose, cheeks, ears, mouth, and neck), predicting the thermal sensations of 12 subjects with an average accuracy of 85%.…”

“…(3) Past studies have typically used skin temperatures at selected local measurement points as inputs for predicting thermal state [22]. Large individual differences in body shapes (e.g., face shapes) can make the location of specific pg 4 https://doi.org/10.1016/j.buildenv.2022.109811 points challenging.…”