A Systematic Literature Review of Non-Invasive Indoor Thermal Discomfort Detection

Abstract

Since 1997, scientists have been trying to utilize new non-invasive approaches for thermal discomfort detection, which promise to be more effective for comparing frameworks that need direct responses from users. Due to rapid technological development in the bio-metrical field, a systematic literature review to investigate the possibility of thermal discomfort detection at the work place by non-invasive means using bio-sensing technology was performed. Firstly, the problem intervention comparison outcome context (PICOC) framework was introduced in the study to identify the main points for meta-analysis and, in turn, to provide relevant keywords for the literature search. In total, 2776 studies were found and processed using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) methodology. After filtering by defined criterion, 35 articles were obtained for detailed investigation with respect to facility types used in the experiment, amount of people for data collection and algorithms used for prediction of the thermal discomfort event. The given study concludes that there is potential for the creation of non-invasive thermal discomfort detection models via utilization of bio-sensing technologies, which will provide a better user interaction with the built environment, potentially decrease energy use and enable better productivity. There is definitely room for improvement within the field of non-invasive thermal discomfort detection, especially with respect to data collection, algorithm implementation and sample size, in order to have opportunities for the deployment of developed solutions in real life. Based on the literature review, the potential of novel technology is seen to utilize a more intelligent approach for performing non-invasive thermal discomfort prediction. The architecture of deep neural networks should be studied more due to the specifics of its hidden layers and its ability of hierarchical data extraction. This machine learning algorithm can provide a better model for thermal discomfort detection based on a data set with different types of bio-metrical variables.

Application of Low-Cost Sensors for Building Monitoring: A Systematic Literature Review

“…Examples of these metering devices for measuring thermal transmittance of the building envelope can be find in refs. [18,80].…”

“…There are various review papers in the literature concerning: the approaches for smart monitoring of buildings [76], environmental monitoring sensors in buildings [77], heritage building information modeling [78], BIM-based end-of-lifecycle decision making and digital deconstruction [79], in-situ measurements of the building thermal parameters [80], indoor air quality monitoring system based on Internet of Things (IoT) [81], indoor particle matter monitoring [40], available techniques for monitoring of energy in buildings [19], monitoring the power usage of appliance in buildings [21], monitoring thermal comfort of the habitants based on the IoT paradigm [24], occupancy monitoring for energy saving in commercial buildings [38], and key sensors for monitoring of concrete structures [82]. Bakker et al focused on the approaches for monitoring of buildings occupancy based on lighting control.…”

The Study of Facial Muscle Movements for Non-Invasive Thermal Discomfort Detection via Bio-Sensing Technology. Part I: Development of the Experimental Design and Description of the Collected Data

“…The k-Nearest Neighbor, Support Vector Machine, Random Forest and many other supervised learning algorithms were implemented to build non-invasive TC prediction models, whose target functions are to predict the state of a person's comfort/discomfort. A reference of collected biometrical data among processed studies [26].…”

“…A combination of the following factors had a major part in the prevention of the model's deployment in real life. As it was elaborated in Marchenko and Temeljotov-Salaj [26], there is a great opportunity to utilize a novel equipment, in combination with artificial intelligence algorithms to develop non-invasive methods for thermal discomfort detection. Literature review suggested that it can be potentially helpful to use the connection between the thermoregulation of the body and its interaction with the subcortical level of the brain (or otherwise known as the lower brain) [26].…”

“…As it was elaborated in Marchenko and Temeljotov-Salaj [26], there is a great opportunity to utilize a novel equipment, in combination with artificial intelligence algorithms to develop non-invasive methods for thermal discomfort detection. Literature review suggested that it can be potentially helpful to use the connection between the thermoregulation of the body and its interaction with the subcortical level of the brain (or otherwise known as the lower brain) [26]. The overall research was divided into two stages: the thermal comfort study; the study of facial muscle movements for non-invasive thermal discomfort detection via bio-sensing technology (see Figure 3).…”