Information match between continuous occupant data streams and one-time manual surveys on indoor climate

Abstract Occupant-centric data streams, and more specifically continuous subjective occupant feedback (CSOF) systems, offer the possibility for autonomous collection of occupant feedback in buildings. They are made possible by recent developments in pervasive ICT technology and can enable a continuous flow of information that may enhance human-centric building design and operation. Due to the relative novelty of these systems, no research has been developed so far to systematically evaluate whether information collected by CSOF systems is truly representative of the entire population's opinions and evaluations. In this study, we analyze how information on occupant's opinions on indoor climate collected though a multi-level CSOF system compare to the information obtained though simultaneously performed manual surveys. We used data collected from five field tests in modern office buildings with uninformed occupants, and compare a total of 317 Satisfaction evaluations, 124 Complaints, and 44 Control actions with 546 surveys. Using logistic regression techniques, we investigated the relations between the feedback information and the information from surveys. We found that cumulative link models were suitable for modeling the relationship between feedback and survey data. The Building ID tag was the most important variable for modeling Occupant satisfaction and Occupant complaint feedback. Occupant control actions was best modeled using the Workplace ID. When comparing CSOF with surveys, we found a Mean Absolute Error (MAE) of 16% and of 12%, for Occupant satisfaction and for Occupant complaint feedback, respectively. We demonstrated that the adopted methods are suitable for understanding the meaning of the collected CSOF data. Further studies based on this methodology and using a larger dataset should be carried out to deepen the understanding of CSOF feedback significance and to increase the soundness of the results obtained in this study.

[1]  Yevgeniy B. Sirotin,et al.  Measuring Satisfaction With Standard Survey Instruments and Single-Button Responses on Kiosks , 2018 .

[2]  Koushik Kar,et al.  BEES: Real-time occupant feedback and environmental learning framework for collaborative thermal management in multi-zone, multi-occupant buildings , 2016 .

[3]  William O'Brien,et al.  A method to conduct longitudinal studies on indoor environmental quality and perceived occupant comfort , 2019, Building and Environment.

[4]  Alberto Cerpa,et al.  Thermovote: participatory sensing for efficient building HVAC conditioning , 2012, BuildSys@SenSys.

[5]  Therese Peffer,et al.  How people use thermostats in homes: A review , 2011, Building and Environment.

[6]  Sarvapali D. Ramchurn,et al.  It is too Hot: An In-Situ Study of Three Designs for Heating , 2016, CHI.

[7]  N Lassen,et al.  Experimental setup and testing of an in-field system for real- time occupant feedback , 2019 .

[8]  Yi Jiang,et al.  Preliminary study of learning individual thermal complaint behavior using one-class classifier for indoor environment control , 2014 .

[9]  Francesco Goia,et al.  Design and in-field testing of a multi-level system for continuous subjective occupant feedback on indoor climate , 2020 .

[10]  Jared Donovan,et al.  Evaluating the use of ambient and tangible interaction approaches for personal indoor climate preferences , 2014, UbiComp Adjunct.

[11]  Branislav Kusy,et al.  Model-free HVAC control using occupant feedback , 2013, 38th Annual IEEE Conference on Local Computer Networks - Workshops.

[12]  Francesco Goia,et al.  A theoretical framework for classifying occupant-centric data streams on indoor climate using a physiological and cognitive process hierarchy , 2021 .

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

[14]  Kyle Konis.  Leveraging ubiquitous computing as a platform for collecting real-time occupant feedback in buildings , 2013 .

[15]  Francesco Goia,et al.  Field investigations of a smiley-face polling station for recording occupant satisfaction with indoor climate , 2020 .

[16]  Zoltán Nagy,et al.  Temperature-preference learning with neural networks for occupant-centric building indoor climate controls , 2019, Building and Environment.

[17]  Paul P. Maglio,et al.  FORCES: feedback and control for occupants to refine comfort and energy savings , 2016, UbiComp.

[18]  Gail Brager,et al.  Post-occupancy evaluation: State-of-the-art analysis and state-of-the-practice review , 2018 .

[19]  Burcin Becerik-Gerber,et al.  Human-Building Interaction Framework for Personalized Thermal Comfort-Driven Systems in Office Buildings , 2014, J. Comput. Civ. Eng..

[20]  Karim Hadjri,et al.  Post‐occupancy evaluation: purpose, benefits and barriers , 2009 .

[21]  Angela Sanguinetti,et al.  Occupant thermal feedback for improved efficiency in university buildings , 2017 .

[22]  Henrik Madsen,et al.  Introduction to General and Generalized Linear Models , 2010 .

[23]  Gail Brager,et al.  Commercial Office Plug Load Energy Consumption Trends and the Role of Occupant Behavior , 2016 .

[24]  Phil Roberts,et al.  Who is post-occupancy evaluation for? , 2001 .

[25]  Burcin Becerik-Gerber,et al.  User-led decentralized thermal comfort driven HVAC operations for improved efficiency in office buildings , 2014 .

[26]  Burcin Becerik-Gerber,et al.  Toward adaptive comfort management in office buildings using participatory sensing for end user driven control , 2012, BuildSys '12.

[27]  Bharathan Balaji,et al.  ZonePAC: Zonal Power Estimation and Control via HVAC Metering and Occupant Feedback , 2013, BuildSys@SenSys.

[28]  Sami Karjalainen,et al.  User problems with individual temperature control in offices , 2007 .

[29]  Dan Wang,et al.  Carrying My Environment with Me: A Participatory-sensing Approach to Enhance Thermal Comfort , 2013, BuildSys@SenSys.

[30]  Mateja Dovjak,et al.  Challenging the assumptions for thermal sensation scales , 2017 .

[31]  Burcin Becerik-Gerber,et al.  Personalized Thermal Comfort Driven Control in HVAC Operated Office Buildings , 2013 .