Wearable devices and Machine Learning algorithms to assess indoor thermal sensation: metrological analysis

Personal comfort modeling is considered the most promising solution for indoor thermal comfort management in buildings. The use of wearable sensors is investigated for the real-time measurement of physiological signals to train comfort models for buildings monitoring and control. To achieve the required reliability, different uncertainty sources should be considered and weighted in the measurement results evaluation. This study presents an example of personal comfort model (PCM) development based on wearable sensors (i.e., Empatica E4 smartband and MUSE headband) acquiring multimodal signals (i.e., photoplethysmographic – PPG, electrodermal activity – EDA, skin temperature – SKT, and electroencephalographic – EEG ones), together with a metrological characterization of the modeling procedure. Starting from the data collected within an experimental campaign on 76 subjects, different Machine Learning (ML) algorithms were exploited to create comfort models capable of predicting the human thermal sensation (TS). The most accurate model was considered to investigate the impact of sensors uncertainty through a Monte Carlo simulation. Results showed that the Random Forest model is the best performing one (accuracy: 0.86). Monte Carlo simulation method proved that the model is very robust towards measurement uncertainties of input features (expanded uncertainty of the model accuracy: ± 0.04, k = 2). This confirms the possibility to derive the subject’s TS exploiting only physiological signals; measurement uncertainty is influenced mostly by PPG and EDA signals. This kind of investigation could lead to the development of PCMs, exploitable within control systems to optimize subjects’ well-being and building energy efficiency.

[1]  S. Schiavon,et al.  Personal comfort models based on a 6‐month experiment using environmental parameters and data from wearables , 2022, Indoor air.

[2]  I. Pigliautile,et al.  A novel methodology for human thermal comfort decoding via physiological signals measurement and analysis , 2022, Building and Environment.

[3]  G. Cosoli,et al.  Combined use of wearable devices and Machine Learning for the measurement of thermal sensation in indoor environments , 2022, 2022 IEEE International Workshop on Metrology for Living Environment (MetroLivEn).

[4]  G. Cosoli,et al.  The importance of physiological data variability in wearable devices for digital health applications , 2022, ACTA IMEKO.

[5]  Bluyssen,et al.  Routledge Handbook of Resilient Thermal Comfort , 2022 .

[6]  I. Pigliautile,et al.  The NEXT.ROOM: Design principles and systems trials of a novel test room aimed at deepening our knowledge on human comfort , 2022, Building and Environment.

[7]  G. M. Revel,et al.  Impact of the measurement uncertainty on the monitoring of thermal comfort through AI predictive algorithms , 2021, ACTA IMEKO.

[8]  Xianguo Wu,et al.  Optimizing energy efficiency and thermal comfort in building green retrofit , 2021 .

[9]  Tibor Bosse,et al.  Detecting Emotions through Electrodermal Activity in Learning Contexts: A Systematic Review , 2021, Sensors.

[10]  Lorenzo Scalise,et al.  Measurement of multimodal physiological signals for stimulation detection by wearable devices , 2021 .

[11]  C. Chun,et al.  Differences between EEG during thermal discomfort and thermal displeasure , 2021 .

[12]  P. Wargocki,et al.  Investigating the relation between electroencephalogram, thermal comfort, and cognitive performance in neutral to hot indoor environment. , 2021, Indoor air.

[13]  Hansaem Park,et al.  Prediction of individual thermal comfort based on ensemble transfer learning method using wearable and environmental sensors , 2021, Building and Environment.

[14]  I. Pigliautile,et al.  Measuring human physiological indices for thermal comfort assessment through wearable devices: A review , 2021 .

[15]  Andres J. Rodriguez,et al.  Sources of Inaccuracy in Photoplethysmography for Continuous Cardiovascular Monitoring , 2021, Biosensors.

[16]  M. Krashes,et al.  Preoptic BRS3 neurons increase body temperature and heart rate via multiple pathways , 2021, bioRxiv.

[17]  I A Mayatskaya,et al.  Eco-sustainable architecture and comfortable living environment , 2021 .

[18]  S. M. Williams,et al.  Stages of Sleep , 2020, Sleep Insights.

[19]  C. Héberlé,et al.  Normal EEG during the neonatal period: maturational aspects from premature to full-term newborns , 2020, Neurophysiologie Clinique.

[20]  Nir Milstein,et al.  Validating Measures of Electrodermal Activity and Heart Rate Variability Derived From the Empatica E4 Utilized in Research Settings That Involve Interactive Dyadic States , 2020, Frontiers in Behavioral Neuroscience.

[21]  Ming Jin,et al.  Personal thermal comfort models with wearable sensors , 2019, Building and Environment.

[22]  P. Wargocki,et al.  Changes in EEG signals during the cognitive activity at varying air temperature and relative humidity , 2019, Journal of Exposure Science & Environmental Epidemiology.

[23]  Riccardo Bernardini,et al.  Driver’s stress detection using Skin Potential Response signals , 2018, Measurement.

[24]  Lihua Xie,et al.  Random forest based thermal comfort prediction from gender-specific physiological parameters using wearable sensing technology , 2018 .

[25]  S. Schiavon,et al.  Thermal comfort and self-reported productivity in an office with ceiling fans in the tropics , 2018 .

[26]  Leen Lauriks,et al.  A review of human thermal comfort experiments in controlled and semi-controlled environments , 2018 .

[27]  Joyce Kim,et al.  Personal comfort models: Predicting individuals' thermal preference using occupant heating and cooling behavior and machine learning , 2018 .

[28]  Young-Ho Cho,et al.  Wearable Sweat Rate Sensors for Human Thermal Comfort Monitoring , 2018, Scientific Reports.

[29]  Chad C. Williams,et al.  Choosing MUSE: Validation of a Low-Cost, Portable EEG System for ERP Research , 2017, Front. Neurosci..

[30]  Tongning Wu,et al.  Effects of stimulus mode and ambient temperature on cerebral responses to local thermal stimulation: An EEG study. , 2017, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[31]  Luca Citi,et al.  cvxEDA: A Convex Optimization Approach to Electrodermal Activity Processing , 2016, IEEE Transactions on Biomedical Engineering.

[32]  Diane J. Cook,et al.  Activity Learning: Discovering, Recognizing, and Predicting Human Behavior from Sensor Data , 2015 .

[33]  E. Ostertagová,et al.  Methodology and Application of the Kruskal-Wallis Test , 2014 .

[34]  Domen Novak,et al.  Metrological evaluation of skin conductance measurements , 2013 .

[35]  M. Brzeziński The Chen–Shapiro Test for Normality , 2012 .

[36]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[37]  ANSI/AAMI/IEC 60601-2-27:2011/(R)2016; Medical electrical equipment ─ Part 2-27: Particular requirements for the basic safety and essential performance of electrocardiographic monitoring equipment , 2010 .

[38]  Sylvia D. Kreibig,et al.  Autonomic nervous system activity in emotion: A review , 2010, Biological Psychology.

[39]  L. Breslow,et al.  A quantitative approach to the World Health Organization definition of health: physical, mental and social well-being. , 1972, International journal of epidemiology.

[40]  Yan Li,et al.  Rules-Based and SVM-Q Methods With Multitapers and Convolution for Sleep EEG Stages Classification , 2022, IEEE Access.

[41]  G. M. Revel,et al.  MEASURING METABOLIC RATE TO IMPROVE COMFORT MANAGEMENT IN BUILDINGS , 2018 .

[42]  Uwe Herwig,et al.  Using the International 10-20 EEG System for Positioning of Transcranial Magnetic Stimulation , 2004, Brain Topography.

[43]  L. Hejjel,et al.  Heart rate variability analysis. , 2001, Acta physiologica Hungarica.

[44]  Standard Ashrae Thermal Environmental Conditions for Human Occupancy , 1992 .