Figure 1 - uploaded by Marco Arnesano
Content may be subject to copyright.
a) MUSE 2 headband sensors overview. b) Top-down view of the EEG electrode positions on the subject's head.
Source publication
Multidomain comfort theories have been demonstrated to interpret human thermal comfort in buildings by employing human-centered physiological measurements coupled with environmental sensing techniques. Thermal comfort has been correlated with brain activity through electroencephalographic (EEG) measurements. However, the application of low-cost wea...
Context in source publication
Context 1
... this study, the EEG signal acquisition was done using a commercial wearable device: the Interaxon MUSE headband [18]. The reference electrode FPz (CMS/DRL) is located on the forehead, the input electrodes are two front (left and right of the reference: AF7, AF8, silver made) and two posteriors, above each ear (TP9 and TP10, conductive silicone -rubber) (Figure 1). The device acquires signals at 256 Hz sampling frequency. ...
Similar publications
Deep neural networks are parametrized by several thousands or millions of parameters, and have shown tremendous success in many classification problems. However, the large number of parameters makes it difficult to integrate these models into edge devices such as smartphones and wearable devices. To address this problem, knowledge distillation (KD)...
Citations
... In addition, our study utilized a new innovative approach, using an entropy measure, that offers unique advantages in studying brain activity and complexity. In the context of human environmental conditions and comfort, traditional EEG analysis methods often focus on analyzing PSD, which may not fully capture the complexity of brain signals and which so far have not led to unique results [40,43]. Entropy analysis, on the other hand, provides a holistic view of brain signal complexity, identifying irregularity and randomness in brain activity. ...
Understanding the neural responses to indoor characteristics like temperature and light is crucial for comprehending how the physical environment influences the human brain. Our study introduces an innovative approach using entropy analysis, specifically, approximate entropy (ApEn), applied to electroencephalographic (EEG) signals to investigate neural responses to temperature and light variations in indoor environments. By strategically placing electrodes over specific brain regions linked to temperature and light processing, we show how ApEn can be influenced by indoor factors. We also integrate heart indices from a multi-sensor bracelet to create a machine learning classifier for temperature conditions. Results showed that in anterior frontal and temporoparietal areas, neutral temperature conditions yield higher ApEn values. The anterior frontal area showed a trend of gradually decreasing ApEn values from neutral to warm conditions, with cold being in an intermediate position. There was a significant interaction between light and site factors, only evident in the temporoparietal region. Here, the neutral light condition had higher ApEn values compared to blue and red light conditions. Positive correlations between anterior frontal ApEn and thermal comfort scores suggest a link between entropy and perceived thermal comfort. Our quadratic SVM classifier, incorporating entropy and heart features, demonstrates strong performance (until 90% in terms of AUC, accuracy, sensitivity, and specificity) in classifying temperature sensations. This study offers insights into neural responses to indoor factors and presents a novel approach for temperature classification using EEG entropy and heart features.
... Majority of rest-state studies found higher theta band activities in neutral thermal environment [36][37][38], however there are also studies which found lower theta band activities in this state [39,40]. Task-based studies reported increase in neutral environment. ...
... Sensitivity of alpha band to temperature has been found in rest-state studies [34,35], and specially in heated environments [39,45]. Lower alpha band activities in neutral environments in comparison with the cooled and heated environments was observed in both steady-state [40] and dynamic studies [37]. ...
... The beta band activities were found to be increased by moving from the neutral environments in rest-state studies [34][35][36][37]39,40,45,46]. On the other hand, in task-based investigations, there are disagreements regarding the trends of the beta band. ...
... Muse headband channel[30] ...
Human activities that require cognitive performance is doing cognitive computer-based tasks. One of the important cognitive performances in people when doing some active thinking tasks is attention. This study focuses on measuring cognitive performance through cognitive tasks in the form of a Stroop Color Word Test with a neurophysiological approach, namely EEG, related to the effects of physical environment factors: room temperature. The temperature variations that will be studied refer to the concepts of slightly warm, neutral, and slightly cool with 18 °C representing slightly cool, 24 °C representing neutral, and 30 °C representing slightly warm. This study used an experimental design method and was conducted on 12 subjects. This study showed that room temperature treatment had a significant effect on TRT (sig. 0.00), but not on accuracy which it refers to cognitive performance to do the task correctly. To explain of the beta EEG signal, it was found that the highest power spectrum value occurred when the respondent was subjected to room temperature treatment of 24 °C. While in the ERP P3 measurement, it was found that the amplitude (µV) of P3 was best at 24 °C.
... However, the data collected was not commented, being used only for method's demonstration purposes. Other analysis from the mentioned experiment can be accessed at (Mansi et al., 2021). Considering the four different sources of information, namely, (1) the objects attributes from the BIM model (transcribed in an IFC file), (2) monitoring data from environmental sensors, (3) monitoring data from wearable sensors, and (4) answers from subjective questions to the participants, python routines supported the creation of Cypher language files and nodes/relationships establishment. ...
The technological innovation is touching different areas of knowlegde, including the building industry. The representation of the built environment through digital models and the inclusion of real-time information in the represented objects, assisting its operation and management, is possible using digital twins. This study aims to to adress the interoperability issues tackled by the digital models, using neural networks to integrate and generate data in an open, accessible and common language format. From a standardized test room facility model (IFC), all the different information of a real experimental procedure was embedded into python environment. Relationships were stablished according subjects' caracteristics and identifiers, generating a new graph neural network, that associates all the relevant information to visualization and management. Deep learning algorithms supports the interpretation of larger and more complex databases, also to relationships' prediction and classification. The proposed method assists the creation of a more integrated digital environment in the building industry.
... The MUSE2 shown in Fig.1, is a portable EEG measurement headband that is compact and userfriendly. It is widely applicable, simple to use, and reasonably priced (nearby USD 250), enabling the recording of EEG and head movement activities outside of a restricted laboratory environment [18]. This product is offered for commercial use, such as for sleep monitoring, meditation, or other relaxation-related activities. ...
... ) Overview of MUSE2 headband sensors. b) The EEG electrode positions on the subject's head, a top-down view[18]. ...
Cheating in e-exams is a real problem that threatens academic integrity and underminesconfidence in the feasibility of remote assessments. Many previous research papers and studies discussedthe issue of cheating in e-exams to prevent or reduce it through the use of the available technologies suchas the use of a web camera to monitor the examinee, some researchers proposed using specific software torestrict the examinee from accessing resources that are not permitted during the exam. This work aims todesign a Semi-automatic, AI-based e-proctoring system that mitigates cheating in e-exams. This researchproposed an innovative method to detect the possibility of cheating in the e-exams. This method relies onthe use of IoT and the Muse2 devices to detect the examinee's physiological state and determine whether itis “Normal” or “Abnormal” through the examinee`s EEG signal, where the abnormal state indicates apossibility of cheating. Convolutional Neural Network (CNN) was used to distinguish the examinee's state.The collected data from 15 students at the fourth stage of the Computer Engineering Department/ Universityof Mosul ranging between 23 and 26 years old showed that there is an obvious difference between the“calm” or “Normal” state and “stress” or “Abnormal” state in the EEG signal of the volunteer. The accuracyof the system was obtained for many testing datasets. The dataset was divided into two main datasets; the30 and 60 seconds duration time. The best accuracy obtained for the 30sec duration time was 97.37%, and97.14% for the 60sec duration time. The researchers concluded that the EEG signal contains a lot ofimportant information that can be utilized to detect the physiological state of the examinee and that theMuse2 device can be reliable to record the EEG signal.
... A first study involving a Muse 2 headband for thermal comfort evaluation was performed by Mansi et al. (2021) [34]. This study is preliminary to the others presented in Table 3 because sets the data processing -noise removal and power spectrum analysis-and feature extraction procedures. ...
... Similar analyses were performed by Mansi et al. (2022a) [8] who used Muse 2 headband with Empatica E4 wristband. The performed analyses confirmed the results obtained in [34], especially regarding the correlation between the increase/decrease of power of brain waves as a function of the user thermal sensation. ...
Human thermal comfort depends on objective variables -related to the environment- and to subjective variables, related to physiological conditions. While the former are relatively easy to be measured, the latter are difficult to be investigated since differ from person to person and they are characterized by sudden variations over time. The recent spread of off-the-shelf wearable devices for monitoring bio-signals has considerably facilitate this challenging task. The aim of this work is to provide a detailed framework about the use of off-the-shelf wearable devices for thermal comfort investigations. A systematic review of 35 scientific papers -selected over 302 results from the initial database query- was performed. The results highlight that wristbands (mainly, Empatica E4 and Fitbit), headbands (i.e., Muse 2), chest bands (mainly, BioHarness 3.0 and Polar H7), miniature data loggers (i.e., iButton), and activity sensors (i.e., Move 3) were the off-the-shelf devices whose use is predominant in thermal comfort investigations. Those devices were adopted for different purposes, namely finding correlations between physiological signals and thermal sensations, training and/or validating thermal comfort models, improving data acquisition, and controlling HVAC systems. The proposed framework could represent a solid background for future investigations which should focus on two main research streams. The first one should aim at strengthening the knowledge about statistical correlations between thermal sensations and physiological signals, as well as defining standardized procedures for the model development and validation. The second research stream should aim at integrating off-the-shelf wearable devices and personalized thermal comfort models into HVAC control systems.
... In Ref. [21], the EEG of observers with different clothes was studied, and the MUSE Fig. 2. IEQ Lab -a model of a controlled office room with workplace and virtual window (left, middle), IT devices for controlling IEQ Lab indoor environment, controlling the course of experiments and measurement and data analysis of the psychological and the physiological response of observers (right). S mEEG device was also used in a thermal comfort study [22], for research into the influence of the size of the office space and the position of the windows on the cognitive characteristics of the observers [23] as well as in recent research [24,25] on the physiological response of observers in the outdoor parks. For post hoc processing, data from MUSE S are stored in the cloud via a smart mobile device using Bluetooth communication for each electrode separately at a time step of 0.5 s. ...
The window view quality related to the window view motif was recently introduced in buildings' certification methods such as LEED, BREAM, WELL and in technical standard EN 17037 as well. The experimental study of psychological and physiological response of observers to window view was performed in thermostatic chamber at class I of indoor environment quality conditions. The aim of the study was to: i) review models for numerical characterization of window view motifs; ii) collect observers' votes of window view quality, using 5-point Likert scale, with experiment simulating different window view motifs; iii) propose a new model for predicting window view quality vote, based on characterization of a window view motif, with additional consideration of sunny or cloudy conditions; iv) measure the brain waves power during window view observation in resting state, using wearable electroencephalography device, to find out to what extend observers' votes correlates with their physiological response. The results show that window view votes increase in case of dominance of natural elements, however the window view votes of built environment significantly increase in case of sunny conditions as well. No significant difference in window view votes was found regarding to the gender or age of observers. It was found that ranking, used in reviewed methods, significantly differ in correlation to our experimental results, with Spearman's correlation index from -0.35 (EN 17037) to 0.85 (View-out Quality Index method). The best fit model was upgraded with additional parameter, indicating sunny or cloudy conditions, defined as Window View Index. The power of alpha waves, the frontal alpha asymmetry and the alpha to beta ratio were used as physiological response indicators, because they are related to the observes' resting state. It was found out that physiological response is significantly less pronounced as observers' votes. Among analyzed biomarkers frontal alpha asymmetry shows the highest positive response, regardless of gender, to window views with dominated natural elements and also to sunny conditions. Based on these results we recommend frontal alpha asymmetry as most suitable biomarker in research of window view impact on well-being of occupants.
... The tool proved to be satisfactory to predict body core temperature and the overall sensation of participants. Mansi et al. [25] investigated the encephalographic (EEG) signals using wearable devices, during an experimental campaign in a test room. The subjects were exposed to different thermal conditions and answered different surveys relating to their comfort perception. ...
The improvement of comfort monitoring resources is pivotal for a better understanding of personal perception in indoor and outdoor environments and thus developing personalized comfort models maximizing occupants’ well-being while minimizing energy consumption. Different daily routines and their relation to the thermal sensation remain a challenge in long-term monitoring campaigns. This paper presents a new methodology to investigate the correlation between individuals’ daily Thermal Sensation Vote (TSV) and environmental exposure. Participants engaged in the long-term campaign were instructed to answer a daily survey about thermal comfort perception and wore a device continuously monitoring temperature and relative humidity in their surroundings. Normalized daily profiles of monitored variables and calculated heat index were clustered to identify common exposure profiles for each participant. The correlation between each cluster and expressed TSV was evaluated through the Kendall tau-b test. Most of the significant correlations were related to the heat index profiles, i.e., 49% of cases, suggesting that a more detailed description of physical boundaries better approximates expressed comfort. This research represents the first step towards personalized comfort models accounting for individual long-term environmental exposure. A longer campaign involving more participants should be organized in future studies, involving also physiological variables for energy-saving purposes.
... In addition, heart rate variability is impacted by several thermoregulatory processes, such as vasodilation and sweating, and could be used as a measure of the thermoregulation system performance [21]. Since the main controlling mechanism of thermoregulation is located in the hypothalamus, thermal comfort has been correlated with brain activities; these activities can be measured via electroencephalogram (EEG) [22]. In addition, the changes in body postures and gestures can also indicate thermal comfort [23]. ...
Thermal comfort is one of the primary factors influencing occupant health, well-being, and productivity in buildings. Existing thermal comfort systems require occupants to frequently communicate their comfort vote via a survey which is impractical as a long-term solution. Here, we present a novel thermal infrared-fused computer vision sensing method to capture thermoregulation performance in a non-intrusive and non-invasive manner. In this method, we align thermal and visible images, detect facial segments (i.e., nose, eyes, face boundary), and accordingly read the temperatures from the appropriate coordinates in the thermal image. We focus on the human face since it is often clearly visible to cameras and is not merged into a hot background (unlike hands). We use a regularized Gaussian Mixture model to track the thermoregulation changes over time and apply a heuristic algorithm to extract hot and cold indices. We present a personalized and a generalized comfort modeling method, selected based on the availability of the occupant historical indices measurements in a neutral environment, and use the time-series of the hot and cold indices to define corrections to HVAC system operations in the form of setpoint constraints. To evaluate the efficacy of our proposed approach in responding to thermal stimuli, we designed a series of controlled experiments to simulate exposure to cold and hot environments. While applying personalized modeling showed an acceptable average accuracy of 91.3%, the generalized model’s average accuracy was only 65.2%. This shows the importance of having access to physiological records in modeling and assessing comfort. We also found that individual differences should be considered in selecting the cooling and heating rates when some knowledge of the occupant’s overall thermal preference is available.
... Experimental studies on brainwaves and human thermal perception predominately investigated the Power Spectrum Densities (PSDs) variation related to the different ambient temperature exposure of participants. In general, results revealed that different environmental temperatures correspond to an increase or decrease of power in particular brain frequency bands [24][25][26]. Son and colleagues [27] showed a significant increase in the relative theta when the subject felt pleasure thermal sensation. Other studies revealed that participants showed higher values of alpha power in pleasant thermal environments, while beta power has lower values [28,29]. ...
... Several studies validated the usage of this low-cost portable device for continuous recording of EEG data [55,56]. In particular, a preliminary study was conducted [26] to validate the presented experimental protocol and the MUSE's capability of performing thermal comfort assessment. The study demonstrated the accuracy of the device in collecting the EEG and its low invasiveness. ...
... Additionally, the internal CO2 concentration (also continuously monitored) was always kept below 500 ppm thanks to the mechanical ventilation operation. Statistical results of physiological responses are summarized in Table 6 and Table 7, and shown in Figure 6A and Figure 7. Regarding the EEG physiological domain , the results partially confirmed what was found in the previous study [26]. In general, EEG measurements showed a correlation with the thermal sensation in terms of increase or decrease of power of brain waves. ...
Personal comfort models (PCM) represent the most promising paradigm for human-centric thermal comfort in buildings. Several data sources can be used to generate a PCM: environmental data, physiological data, occupants' response. Advances in wearable sensing suggest that the use of physiological data for real time comfort measurement can be the base of the next generation of buildings design and operation with PCMs. However, proof of evidence about the adoption of non-invasive but accurate measurement methods and about correlations between physiological features and thermal sensation are still required. This study presents the results from a large experimental campaign aiming at human thermal comfort decoding via physiological signal. Two non-invasive wearables were used to simultaneously measure four key physiological signals (electroencephalography (EEG), Heart Rate Variability (HRV), electrodermal activity (EDA) and skin temperature (ST) on 52 subjects exposed to three different thermal conditions (namely cold, warm, and neutral) in a controlled environment. Data acquired from 219 tests were therefore analysed to determine the statistical importance of physiological features. Results showed that cold and warm thermal sensations can be uniquely identified by each physiological signal; while neutral sensation is the less distinguishable. More specifically, statistical differences (p-value <0.01) between cold and warm were detected among EEGs features (Beta TP10, Gamma TP10 relative alpha TP9), time- and frequency-domain features of HRV, EDA tonic component and mean ST. Experimental results demonstrated that physiological measurements can detect specific thermal sensation, of crucial importance for the most advanced PCMs, accounting for people's diversities.
