scholarly journals Towards Online Personalized-Monitoring of Human Thermal Sensation Using Machine Learning Approach

2019 ◽  
Vol 9 (16) ◽  
pp. 3303 ◽  
Author(s):  
Ali Youssef ◽  
Ahmed Youssef Ali Amer ◽  
Nicolás Caballero ◽  
Jean-Marie Aerts
Keyword(s):  
Thermal Comfort ◽  
Thermal State ◽  
Thermal Sensation ◽  
Wearable Sensors ◽  
Building Design ◽  
Streaming Data ◽  
Classification Model ◽  
Support Vector ◽  
Indoor Climate ◽  
Climate Control

Thermal comfort and sensation are important aspects of 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 view the building occupants as passive recipients of their thermal environment. To overcome the disadvantages of static models, adaptive thermal comfort models aim to provide opportunity for personalized climate control and thermal comfort enhancement. Recent advances in wearable technologies contributed to new possibilities in controlling and monitoring health conditions and human wellbeing in daily life. The generated streaming data generated from wearable sensors are providing a unique opportunity to develop a real-time monitor of an individual’s thermal state. The main goal of this work is to introduce a personalized adaptive model to predict individual’s thermal sensation based on non-intrusive and easily measured variables, which could be obtained from already available wearable sensors. In this paper, a personalized classification model for individual thermal sensation with a reduced-dimension input-space, including 12 features extracted from easily measured variables, which are obtained from wearable sensors, was developed using least-squares support vector machine algorithm. The developed classification model predicted the individual’s thermal sensation with an overall average accuracy of 86%. Additionally, we introduced the main framework of streaming algorithm for personalized classification model to predict an individual’s thermal sensation based on streaming data obtained from wearable sensors.

scholarly journals Model-Based Monitoring of Occupant’s Thermal State for Adaptive HVAC Predictive Controlling

Processes ◽  
2019 ◽  
Vol 7 (10) ◽  
pp. 720 ◽  
Author(s):  
Youssef ◽  
Caballero ◽  
Aerts
Keyword(s):  
Metabolic Rate ◽  
Thermal Comfort ◽  
Thermal State ◽  
Thermal Sensation ◽  
Streaming Data ◽  
Classification Model ◽  
Percentage Error ◽  
Support Vector ◽  
Activity Levels ◽  
Model Based

Conventional indoor climate design and control approaches are based on static thermal comfort/sensation models that view the building occupants as passive recipients of their thermal environment. Recent advances in wearable sensing technologies and their generated streaming data are providing a unique opportunity to understand the user’s behaviour and to predict future needs. Estimation of thermal comfort is a challenging task given the subjectivity of human perception; this subjectivity is reflected in the statistical nature of comfort models, as well as the plethora of comfort models available. 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. The main goal of this paper was 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 participants were subjected to three different environmental temperatures at two different activity levels. The results have shown that a reduced-ordered (second-order) multi-inputs-single-output discrete-time transfer function (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 a mean absolute percentage error of 8.7%. A general classification model based on a least squares support vector machine (LS-SVM) technique is developed to predict the individual’s thermal sensation. For a seven-class classification problem, the results have shown that the overall model accuracy of the developed classifier is 76% with an F1-score value of 84%. The developed LS-SVM classification model for prediction of occupant’s thermal sensation can be integrated in the heating, ventilation and air conditioning (HVAC) system to provide an occupant thermal state-based climate controller. In this paper, we introduced an adaptive occupant-based HVAC predictive controller using the developed LS-SVM predictive classification model.

scholarly journals Using Thermostats for Indoor Climate Control in Office Buildings: The Effect on Thermal Comfort

Energies ◽  
2017 ◽  
Vol 10 (9) ◽  
pp. 1368 ◽  
Author(s):  
Georgios Kontes ◽  
Georgios Giannakis ◽  
Philip Horn ◽  
Simone Steiger ◽  
Dimitrios Rovas
Keyword(s):  
Thermal Comfort ◽  
Office Buildings ◽  
Indoor Climate ◽  
Climate Control

Thermal Performance of Nepalese Building- A Case Study of Dhulikhel and Biratnagar

2020 ◽  
Vol 15 (3) ◽  
pp. 73-77
Author(s):  
Nischal Chaulagain ◽  
Bivek Baral ◽  
Saurav Raj Bista
Keyword(s):  
Thermal Comfort ◽  
Thermal Performance ◽  
Research Work ◽  
Building Design ◽  
Comfort Level ◽  
Indoor Climate ◽  
Design Code ◽  
Electric Equipment ◽  
The Government ◽  
Real Scenario

Nepal has wide variation in altitude, so does its climate, lifestyle and housing. The building design code issued by the Government of Nepal does not address the issue of thermal comfort, which could be the reason the modern buildings built under the design code are performing poorly in terms of indoor thermal comfort. As a result, people have largely compromised in accommodation. The research includes selection of two representative buildings (at Biratnagar and Dhulikhel) followed by real time monitoring of indoor climate (temperature and Relative humidity). The logged data was used to calibrate the computer model. The model was approximated to real scenario including indoor heat loads from people, lighting, electric equipment and infiltration. Building energy modeling was done in EnergyPlus. The research work depicts the thermal performance of building by comparing the indoor climate of selected buildings of Biratnagar and Dhulikhel with the ASHARE suggested thermal comfort level for humans. The major problem found in the buildings of Biratnagar was overheating for more than 6 months period while for Dhulikhel was under heating for more than 4 months period. The author suggests further research to analyze passive techniques to improve thermal performance and reduce active energy consumption.

An integrated fuzzy support vector regression and the particle swarm optimization algorithm to predict indoor thermal comfort

2016 ◽  
Vol 25 (8) ◽  
pp. 1248-1258 ◽  
Author(s):  
Fayçal Megri ◽  
Ahmed Cherif Megri ◽  
Riadh Djabri
Keyword(s):  
Particle Swarm Optimization ◽  
Thermal Comfort ◽  
Support Vector Regression ◽  
Thermal Sensation ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Support Vector ◽  
Statistical Regression ◽  
Swarm Optimization ◽  
Comfort Indices

The thermal comfort indices are usually identified using empirical thermal models based on the human balanced equations and experimentations. In our paper, we propose a statistical regression method to predict these indices. To achieve this goal, first, the fuzzy support vector regression (FSVR) identification approach was integrated with the particle swarm optimization (PSO) algorithm. Then PSO was used as a global optimizer to optimize and select the hyper-parameters needed for the FSVR model. The radial basis function (RBF) kernel was used within the FSVR model. Afterward, these optimal hyper-parameters were used to forecast the thermal comfort indices: predicted mean vote (PMV), predicted percentage dissatisfied (PPD), new standard effective temperature (SET*), thermal discomfort (DISC), thermal sensation (TSENS) and predicted percent dissatisfied due to draft (PD). The application of the proposed approach on different data sets gave successful prediction and promising results. Moreover, the comparisons between the traditional Fanger model and the new model further demonstrate that the proposed model achieves even better identification performance than the original FSVR technique.

A Review of the Impact of Vegetation in Solar Control towards Enhanced Thermal Comfort and Energy Performance in Buildings

2019 ◽  
Vol 887 ◽  
pp. 428-434
Author(s):  
Dorcas A. Ayeni ◽  
Olaniyi O. Aluko ◽  
Morisade O. Adegbie
Keyword(s):  
Thermal Comfort ◽  
Adaptive Capacity ◽  
Thermal Environment ◽  
Thermal Conditions ◽  
Building Design ◽  
Energy Performance ◽  
Tropical Region ◽  
Indoor Climate ◽  
Solar Control ◽  
The Impact

Man requires a thermal environment that is within the range of his adaptive capacity and if this fluctuates outside the normal, a reaction is required beyond its adaptive capacity which results to health challenges. Therefore, the aim of building design in the tropical region is to minimize the heat gain indoors and enhance evaporative cooling of the occupants of the space so as to achieve thermal comfort. In most cases, the passive technologies are not adequate in moderating indoor climate for human comfort thereby relying on active energy technique to provide the needed comfort for the building users. The need for the use of vegetation as a panacea for achieving comfortable indoor thermal conditions in housing is recognised by architects globally. However, the practice by architects in Nigeria is still at the lower ebb. The thrust of this paper therefore is to examine the impact of vegetation in solar control reducing thermal discomfort in housing thereby enhancing the energy performance of the buildings. Using secondary data, the paper identifies the benefits of vegetation in and around buildings to include improvement of indoor air quality through the aesthetics quality of the environment and concludes that vegetation in and around building will in no small measure contributes to saving energy consumption.

scholarly journals Assessing the thermal comfort in non-air conditioned classrooms in Ho Chi Minh City

2017 ◽  
Vol 1 (T4) ◽  
pp. 232-240
Author(s):  
Nam Thi Que Nguyen ◽  
Nam Thi Que Nguyen ◽  
Thanh Cong Tran
Keyword(s):  
Thermal Comfort ◽  
Thermal Condition ◽  
Thermal Environment ◽  
Thermal Sensation ◽  
Cross Sectional Study ◽  
Ho Chi Minh City ◽  
University Campus ◽  
Indoor Climate ◽  
Cross Sectional ◽  
Class Time

Thermal comfort is a parameter to assess environmental indoor quality which affects especially performance of students. A cross-sectional study was conducted in classrooms at a university campus in Ho Chi Minh City to assess the thermal condition during the class time. Microclimate parameters were measured at the same time when students answered the survey on their thermal sensation and acceptability of the indoor climate. Objective data analysis from adaptive PMV model for non-air-conditioned buildings revealed that none of classes had the thermal condition were in the comfort zone of TCVN 7438:2004, coinciding with the subjective result from the surveys. The research showed that 72 percent of the 472 students did not accept the thermal environment and 91.3 percent of students preferred cooler. The suggested neutral temperature was 29.4 oC, the derived from the linear regression between adaptive Predicted Mean Vote (aPMV) and operative temperature (To).

Agent Based Modelling to Improve Comfort and Save Energy in the Built Environment

2008 ◽  
Author(s):  
Wim Zeiler ◽  
Gert Boxem ◽  
Rinus van Houten ◽  
Joep van der Velden ◽  
Willem Wortel ◽  
...  
Keyword(s):  
Energy Consumption ◽  
Built Environment ◽  
Control Strategy ◽  
Energy Demand ◽  
Building Design ◽  
Research Centre ◽  
Control Technology ◽  
Indoor Climate ◽  
Climate Control ◽  
Reduce Energy Consumption

In Europe comfort in buildings needs 40% of the total energy. With effects of Global warming becoming more and more apparent there is a need to reduce this energy demand by comfort within the built environment. In comfort control strategy there is an exciting development based on inclusive design: the user’s preferences and their behaviour have become central in the building services control strategy. Synergy between end-user and building is the ultimate in the intelligent comfort control concept. This new comfort control technology is based on the use of agent technology and can further reduce energy consumption of buildings while at the same time improve individual comfort. The TU/e (Technische Universiteit Eindhoven) together with Kropman and ECN (Energy research Centre Netherlands) work together in the research for user based preference indoor climate control technology. Central in this approach is the user focus of the whole building design process which makes it possible to reduce energy consumption by tuning demand and supply of the energy needed to fulfill the comfort demand of the occupants building.

scholarly journals Measuring Activities of Daily Living in Stroke Patients with Motion Machine Learning Algorithms: A Pilot Study

2021 ◽  
Vol 18 (4) ◽  
pp. 1634
Author(s):  
Pin-Wei Chen ◽  
Nathan A. Baune ◽  
Igor Zwir ◽  
Jiayu Wang ◽  
Victoria Swamidass ◽  
...  
Keyword(s):  
Machine Learning ◽  
Pilot Study ◽  
Activities Of Daily Living ◽  
Daily Living ◽  
Wearable Sensors ◽  
Classification Model ◽  
Support Vector ◽  
Stroke Patients ◽  
Extreme Gradient Boosting ◽  
Testing Data

Measuring activities of daily living (ADLs) using wearable technologies may offer higher precision and granularity than the current clinical assessments for patients after stroke. This study aimed to develop and determine the accuracy of detecting different ADLs using machine-learning (ML) algorithms and wearable sensors. Eleven post-stroke patients participated in this pilot study at an ADL Simulation Lab across two study visits. We collected blocks of repeated activity (“atomic” activity) performance data to train our ML algorithms during one visit. We evaluated our ML algorithms using independent semi-naturalistic activity data collected at a separate session. We tested Decision Tree, Random Forest, Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost) for model development. XGBoost was the best classification model. We achieved 82% accuracy based on ten ADL tasks. With a model including seven tasks, accuracy improved to 90%. ADL tasks included chopping food, vacuuming, sweeping, spreading jam or butter, folding laundry, eating, brushing teeth, taking off/putting on a shirt, wiping a cupboard, and buttoning a shirt. Results provide preliminary evidence that ADL functioning can be predicted with adequate accuracy using wearable sensors and ML. The use of external validation (independent training and testing data sets) and semi-naturalistic testing data is a major strength of the study and a step closer to the long-term goal of ADL monitoring in real-world settings. Further investigation is needed to improve the ADL prediction accuracy, increase the number of tasks monitored, and test the model outside of a laboratory setting.

scholarly journals Does a neutral thermal sensation determine thermal comfort?

2018 ◽  
Vol 39 (2) ◽  
pp. 183-195 ◽  
Author(s):  
Sally Shahzad ◽  
John Brennan ◽  
Dimitris Theodossopoulos ◽  
John K Calautit ◽  
Ben R Hughes
Keyword(s):  
Thermal Comfort ◽  
Thermal Environment ◽  
Thermal Sensation ◽  
Building Design ◽  
Thermal Preference ◽  
Practical Application ◽  
Comfort Zone ◽  
Indoor Thermal Environment ◽  
Human Thermal Comfort ◽  
Comfort Condition

The neutral thermal sensation (neither cold, nor hot) is widely used through the application of the ASHRAE seven-point thermal sensation scale to assess thermal comfort. This study investigated the application of the neutral thermal sensation and it questions the reliability of any study that solely relies on neutral thermal sensation. Although thermal-neutrality has already been questioned, still most thermal comfort studies only use this measure to assess thermal comfort of the occupants. In this study, the connection of the occupant’s thermal comfort with thermal-neutrality was investigated in two separate contexts of Norwegian and British offices. Overall, the thermal environment of four office buildings was evaluated and 313 responses (three times a day) to thermal sensation, thermal preference, comfort, and satisfaction were recorded. The results suggested that 36% of the occupants did not want to feel neutral and they considered thermal sensations other than neutral as their comfort condition. Also, in order to feel comfortable, respondents reported wanting to feel different thermal sensations at different times of the day suggesting that occupant desire for thermal comfort conditions may not be as steady as anticipated. This study recommends that other measures are required to assess human thermal comfort, such as thermal preference. Practical application: This study questions the application of neutral thermal sensation as the measure of thermal comfort. The findings indicate that occupant may consider other sensations than neutral as comfortable. This finding directly questions the standard comfort zone (e.g. ASHRAE Standard 55) as well as the optimum temperature, as many occupants required different thermal sensations at different times of the day to feel comfortable. These findings suggest that a steady indoor thermal environment does not guarantee thermal comfort and variations in the room temperature, which can be controlled by the occupant, need to be considered as part of the building design.

Sign in / Sign up

Export Citation Format

Share Document