Dynamic Model-Based Monitoring of Human Thermal Comfort for Real-Time and Adaptive Control Applications

Thermal comfort and sensation are important aspects of the building design and indoor climate control as modern man spends most of the day indoors. Conventional indoor climate design and control approaches are based on static thermal comfort/sensation models that views the building occupants as passive recipients of their thermal environment. Assuming that people have relatively constant range of biological comfort requirements, and that the indoor environmental variables should be controlled to conform to that constant range. Recent advances in mobile technologies in healthcare, in particular wearable technologies (m-health) and smart clothing, have positively contributed to new possibilities in controlling and monitoring health conditions and human wellbeing in daily life applications. The wearable sensing technologies and their generated streaming data are providing a unique opportunity to understand the user’s behaviour and to predict future needs. Many advanced and accurate mechanistic thermoregulation models, such as the ‘Fiala thermal Physiology and Comfort’ model, are developed to assess the thermal strains and comfort status of humans.


Introduction
Thermal comfort (TC) is an ergonomic aspect determining the satisfaction about the surrounding environment and is defined as 'that condition of mind which expresses satisfaction with the thermal environment and is assessed by subjective evaluation' ASHRAE [1]. The effect of thermal environments on occupants might also be assessed in terms of thermal sensation (TS), which However, the most reliable mechanistic models are too complex to be implemented in realtime for monitoring and control applications. Additionally, such models are using not-easily or invasively measured variables (e.g., core temperatures and metabolic rate), which are often not practical and undesirable measurements for monitoring during varied activities over prolonged periods. The main goal of this paper is to develop dynamic model-based monitoring system of the occupant's thermal state and their thermoregulation responses under two different activity levels. In total, 25 test subjects were subjected to three different environmental temperatures, namely 5 o C (cold), 20 o C (moderate) and 37 o C (hot) at two different activity levels (at rest and cycling). Metabolic rate, heart rate, average skin temperature, skin heat flux and aural temperature are measured continuously during the course of the experiments. The results have shown that a reduced-ordered (second order)s MISO-DTF including three input variables (wearables), namely, aural temperature, heart rate, and average skin heat flux, is best to estimate the individual's metabolic rate (non-wearable) with mean-absolute-percentageerror of 8.7%.
can be defined as 'a conscious feeling commonly graded into the categories cold, cool, slightly cool, neutral, slightly warm, warm, and hot' ASHRAE [1]. Thermal sensation and thermal comfort are both subjective judgements, however, thermal sensation is related to the perception of one's thermal state, and thermal comfort to the evaluation of this perception ISO-10551 [2]. The assessment of thermal sensation has been regarded as more reliable and as such is often used to estimate thermal comfort Koelblen et al. [3].
Human thermal sensation is mainly depending on the human body temperature (core body temperature), which is a function of sets of comfort factors Enescu et al. [4,5].
These comfort factors are including indoor environmental factors, namely mean air temperature around the body, relative air velocity around the body, humidity, and mean radiant temperature to the body Parsons [5]. Additionally, some personal (individualrelated) factors, namely, metabolic rate or internal heat production in the body, which vary with the activity level and clothing thermos-physical properties (such as clothing insulation and vapour clothing resistance), are included. It should be mentioned that the individual thermal perception is deepening, as well, on psychological factors include naturalness (an environment where the people tolerate wide changes of the physical environment), expectations and short/long-term experience, which directly affect individuals' perceptions, time of exposure, perceived control, and environmental stimulation Nikolopoulou et al. [6].
The most considered way to have an accurate assessment of TS is to ask the individuals directly about their thermal sensation perception Enescu et al. [4,5]. Thermal sensation mathematical models have been developed in order to overcome the difficulties of direct enquiry of subjects. The development of such models is mostly depending on statistical approaches that by correlating experimental conditions (i.e., environmental and person-related variables) data to thermal sensation votes obtained from human subjects Koelblen et al. [3,5]. Most of these models (e.g., PMV) are static in the sense that they predict the average vote of a large group of people based on the seven-point thermal sensation scale, instead of individual thermal comfort, they only describes the overall thermal sensation of multiple occupants in a shared thermal environment. To overcome the disadvantages of static models, adaptive thermal comfort models aims to provide insights in increasing opportunities for personal and responsive control, thermal comfort enhancement, energy consumption reduction and climatically responsive and environmentally responsible building design De Dear et al. [7,8].
The idea behind adaptive model is that occupants and individuals are no longer regarded as passive recipients of the thermal environment but rather, play an active role in creating their own thermal preferences De Dear et al. [7]. Besides regression analysis, thermal sensation prediction can also be seen as a classification problem where various classification algorithms can be implemented Lu et al. [8]. Recently, number of research work (e.g., Chaudhuri et al. [9]; Dai et al. [10]; Farhan et al. [11]; Huang, Yang, and Newman [12]; Kim et al. [13] have demonstrated the possibility of using machine learning techniques, such as support vector machine (SVM), to assess and predict human thermal sensation. It can be concluded based on the published work (see The wearable sensing technologies and their generated streaming data are providing a unique opportunity to understand the user's behavior and to predict future needs Hussain, Kang, and Lee [14]. The generated streaming data is unique due to the personal nature of the wearable devices. However, the generated streaming data is forming a challenge related to the need of personalized adaptive models that can handle newly arrived personal data. Current HVAC control systems can be divided into two types: air temperature regulator (ATR) and thermal comfort regulator (TCR). Most TCR controllers use static models, mainly PMV, as a performance criterion. This paper is aiming to develop an adaptive model for real-time monitoring of human thermal states using personal non-intrusive sensing techniques. The developed model should be suitable for real-time adaptive controlling of indoor climate systems and smart wearable applications. however, each room is designed to provide different ranges of climate conditions as shown in (Table 1). Chart for cold exposure (National Weather Service of the US) and

Experiments and Experimental Setup
for hot temperatures exposure according to Dewhirst et al. [16].
The conducted experiments are consisted of two phases (Figure 1), upper graph), namely, low activity and high activity phases. During the first experimental phase, low activity phase, the test subjects (while being seated = low activity) are exposed, during 55 minutes, to three levels of temperatures in the following order: normal, low, high and normal again ( Figure 1). During the high activity phase, the test subjects is exposed to 15 minutes of light physical stress (80W of cycling on a fastened racing bicycle). During the course (75 minutes) of the active phase, each test subject is exposed to the predefined three temperature levels ( Figure 1), lower graph).
During each temperature level, starting from the normal level (

Modelling and Classification
For the sake of present study, the measured variables are divided into wearables, which are easily measured variables   Dynamic Modelling: Although the system under study (occupant's thermoregulation) is inherently a non-linear system, the essential perturbation behaviour can often be approximated well by simple linearized Transfer Function (TF) models Young [17,18]. For the purposes of the present paper, therefore, the following liner, Multi-input, single-output (MISO) discrete-timesystems are considered to estimate metabolic rate and core body temperature Young [19] ,

Dynamic Modelling and Estimation of Individual's Metabolic Rate
The average metabolic rate obtained from the 25 participants at the temperature levels (24, 5 and 37 o C) during low and high activity phases are presented in (    (Figure 4).

Figure 4:
A simulation example of the developed MISO-DTF model (2) to estimate the metabolic rate during the low activity experimental phase at normal temperature (24oC).
The estimation performance of the selected general MISO-DTF (2) is evaluated based on the mean-absolute-percentage-error The results have shown that the developed general model is shown, for all test subjects, a higher average MAPE value (10 ±2.2 %) during the low activity phases than the average MAPE value (7.6 ±2.6 %) resulted during the high activity phases. The METs (metabolic equivalent tasks) are a measure, which accounts for a normalized form of energy expenditure per kilogram of mass. There are consensus that the measurement of metabolic rate might vary amongindividuals (interpersonal) up to 75% Byrne et al. [24] and even within the same day from morning to afternoon for the same subject (intrapersonal) up to 6%, though measurements on different days might be comparable on fasted subjects Haugen et al. [25] . Hence, a general estimation model of individual metabolic rate will not be efficient in this case. However, the general estimation performance of the suggested general MISO model can be enhanced by using the online adaptive form of the SRIV algorithm Garnier, Young and Gilson [26]. The online adaptive (closed-loop) SRIV algorithm is providing the possibility to personalise the developed general model by retuning the model parameters and model delays based on the streaming data acquired from the wearable sensors (Table 3).

Thermal Sensation
In order to give an idea about the interaction relationship between considered variables, the correlation between all   (Table 4). Table 4: An overview of the selected feature space including the measured and estimated variables (six variables) and some operations on these variables (× = selected).   Table 5 The error performance results of the developed general classification for each class separately are shown in (Table 6). The results showed that the error performances of classes 1, 2, 6 and 7 are very low see (Table 6), which can be attributed to the low number (0, 2, 4, 2, respectively) of obtained votes for these classes or in other word due to the uneven class distribution. Therefore, the overall F1-score is more reliable and efficient measure of   In these studies, the results have shown that SVM is able to predict thermal comfort/ sensation with an accuracy and F1score of 76.7% and 84%, respectively. However, these results are only obtained by reducing the 7-classes classification problem to a 3-classes problem. Hence, we believe that reducing the number of classes will improve our suggested general model performance.
Moreover, based on streaming data obtained from wearable sensor technologies, a personalised adaptive classification model, based on the same extracted features, will enhance the model performance to predict the individual's thermal sensation.

Conclusion
In this present paper, 25  and 84%, respectively. It is suggested in this paper that the model overall performance of the model can be enhanced by using a personalised adaptive classification algorithm based on streaming data from wearable sensors.