Impact of the measurement uncertainty on the monitoring of thermal comfort through AI predictive algorithms

Abstract

This paper presents an approach to assess the measurement uncertainty of human thermal comfort by using an innovative method that comprises a heterogeneous set of data, made by physiological and environmental quantities, and artificial intelligence algorithms, using Monte Carlo method (MCM). The dataset is made up of heart rate variability (HRV) features, air temperature, air velocity and relative humidity. Firstly, MCM is applied to compute the measurement uncertainty of the HRV features: results have shown that among 13 participants, there are uncertainty values in the measurement of HRV features that ranges from ±0.01% to ±0.7 %, suggesting that the uncertainty can be generalized among different subjects. Secondly, MCM is applied by perturbing the input parameters of random forest (RF) and convolutional neural network (CNN) algorithm, trained to measure human thermal comfort. Results show that environmental quantities produce different uncertainty on the thermal comfort: RF has the highest uncertainty due to the air temperature (14 %), while CNN has the highest uncertainty when relative humidity is perturbed (10.5 %). A sensitivity analysis also shows that air velocity is the parameter that causes a higher deviation of thermal comfort

A Multi-Sensor Fusion Approach Based on PIR and Ultrasonic Sensors Installed on a Robot to Localise People in Indoor Environments

“…To estimate the measurement uncertainty of the distance values after the application of the K-means, the statistical confidence with a coverage factor of k = 2 is used, expressing the level of confidence that can be attributable to the measured value [ 35 , 36 ].…”

IOT enviromental quality monitoring in smart buildings in presence of measurement uncertainty: a decision making approach

“…In situations like this, where there is a need to make decisions about exceeding a certain threshold, the algorithm has to analyse experimental data, considering not only the measured value, but also the uncertainty associated with the measurement process [38]- [41]. In this case we face to a particular class of problems that pertains to the field of decision-making.…”

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

“…The variance can be calculated as the square of the standard deviation in the case of normal distribution (i.e., the one selected in the presented work). Minimum number of samples for a leaf node [1,3,5,7,9] Criterion to measure the split quality ["gini", "entropy"]…”

“…A possible solution could be the restriction of the analysis to physiological parameters (preferably acquired through wearable sensors, not requiring specific installation in the built environment), monitored with appropriate accuracy. Several physiological parameters in literature have been demonstrated to be related to thermal comfort [8], such as ElectroCardioGram (ECG -Heart Rate, HR, and its variability, HRV, are expected to vary with thermal comfort [9]), ElectroEncephaloGram (EEG -whose frequency bands, related to diverse neural activities, vary along with thermal conditions [10], [11]), ElectroDermal Activity (EDAquantifying the arousal of the SNS and mirroring the activity of the sweat glands, hence carrying information dealing with the subject's perceived emotions [12] and experienced stress [13]), and SKin Temperature (SKT -reflecting the perception of the environmental temperature).…”