Inferring personalized visual satisfaction profiles in daylit offices from comparative preferences using a Bayesian approach

Abstract This paper presents a new method for developing personalized visual satisfaction profiles in private daylit offices using Bayesian inference. Unlike previous studies based on action data, a set of experiments with human subjects and changing visual conditions were conducted to collect comparative preference data. The likelihood function was defined by linking comparative visual preference data with the visual satisfaction utility function using a probit model structure. A parametrized Gaussian bell function was adopted for the latent satisfaction utility model, based on our belief that each person has a specific set of neighboring visual conditions that are most preferred. Distinct visual preference profiles were inferred with a Bayesian approach using the experimental data. The inferred visual satisfaction utility functions and the model performance results reflect the ability of the models to discover different personalized visual satisfaction profiles. The method presented in this paper will serve as a paradigm for developing personalized preference models, for potential use in personalized controls, balancing human satisfaction with indoor environmental conditions and energy use considerations.

[1]  Iason Konstantzos,et al.  Occupant interactions with shading and lighting systems using different control interfaces: A pilot field study , 2016 .

[2]  Athanasios Tzempelikos,et al.  Daylight-linked synchronized shading operation using simplified model-based control , 2017 .

[3]  Antoine Guillemin,et al.  An energy-efficient controller for shading devices self-adapting to the user wishes , 2002 .

[4]  J. Neumann,et al.  Theory of games and economic behavior , 1945, 100 Years of Math Milestones.

[5]  Lisa Heschong,et al.  Approved Method: IES Spatial Daylight Autonomy (sDA) and Annual Sunlight Exposure (ASE) , 2012 .

[6]  Simon Breslav,et al.  Coupling stochastic occupant models to building performance simulation using the discrete event system specification formalism , 2014 .

[7]  Ilias Bilionis,et al.  A Bayesian modeling approach of human interactions with shading and electric lighting systems in private offices , 2017 .

[8]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[9]  Peter Boyce,et al.  Occupant use of switching and dimming controls in offices , 2006 .

[10]  L.F.M. Kuijt-Evers,et al.  Personal environmental control: Effects of pre-set conditions for heating and lighting on personal settings, task performance and comfort experience , 2015 .

[11]  P. Tregenza,et al.  Temporal effects on glare response from daylight , 2017 .

[12]  Nando de Freitas,et al.  Active Preference Learning with Discrete Choice Data , 2007, NIPS.

[13]  Gillian Isoardi,et al.  Discomfort glare in open plan green buildings , 2014 .

[14]  Tadj Oreszczyn,et al.  Occupant control of passive systems: the use of Venetian blinds , 2001 .

[15]  Dj Carter,et al.  A field study of occupant controlled lighting in offices , 2002 .

[16]  Christoph F. Reinhart,et al.  The ‘adaptive zone’ – A concept for assessing discomfort glare throughout daylit spaces , 2012 .

[17]  Darren Robinson,et al.  Adaptive actions on shading devices in response to local visual stimuli , 2010 .

[18]  Sanae Chraibi,et al.  Satisfying light conditions: a field study on perception of consensus light in Dutch open office environments , 2016 .

[19]  Robert E. Kass,et al.  A default conjugate prior for variance components in generalized linear mixed models (comment on article by Browne and Draper) , 2006 .

[20]  Kwang Ho Lee,et al.  Automated control strategies of inside slat-type blind considering visual comfort and building energy performance , 2012 .

[21]  Daphne Koller,et al.  Making Rational Decisions Using Adaptive Utility Elicitation , 2000, AAAI/IAAI.

[22]  Ian Beausoleil-Morrison,et al.  On adaptive occupant-learning window blind and lighting controls , 2014 .

[23]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[24]  Christoph F. Reinhart,et al.  Lightswitch-2002: a model for manual and automated control of electric lighting and blinds , 2004 .

[25]  T. Inoue,et al.  The development of an optimal control system for window shading devices based on investigations in office buildings , 1988 .

[26]  Jennifer A. Veitch,et al.  End Users‘ Knowledge, Beliefs, and Preferences for Lighting , 1993 .

[27]  Jan Wienold,et al.  Evaluation methods and development of a new glare prediction model for daylight environments with the use of CCD cameras , 2006 .

[28]  E. Jaynes.  Probability theory : the logic of science , 2003 .

[29]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[30]  Nicolas Morel,et al.  Bayesian estimation of visual discomfort , 2008 .

[31]  Murali Annavaram,et al.  The Occupant Mobile Gateway: A participatory sensing and machine-learning approach for occupant-aware energy management , 2017 .

[32]  Jean-Louis Scartezzini,et al.  Visual discomfort and glare rating assessment of integrated daylighting and electric lighting systems using HDR imaging techniques , 2010 .

[33]  Jan Wienold,et al.  DYNAMIC SIMULATION OF BLIND CONTROL STRATEGIES FOR VISUAL COMFORT AND ENERGY BALANCE ANALYSIS , 2007 .

[34]  Eric J. Johnson,et al.  The adaptive decision maker , 1993 .

[35]  Athanasios Tzempelikos,et al.  Bayesian classification and inference of occupant visual preferences in daylit perimeter private offices , 2018 .

[36]  Athanasios Tzempelikos,et al.  Model-based shading and lighting controls considering visual comfort and energy use , 2016 .

[37]  Shengbo Guo,et al.  Bayesian recommender systems : models and algorithms , 2011 .

[38]  P. R. Tregenza,et al.  Discomfort glare from interesting images , 2005 .

[39]  Athanasios Tzempelikos,et al.  Comparative control strategies for roller shades with respect to daylighting and energy performance , 2013 .

[40]  Gregory R. Lockhead,et al.  Absolute Judgments Are Relative: A Reinterpretation of Some Psychophysical Ideas , 2004 .

[41]  Hicham Johra,et al.  Verification of simple illuminance based measures for indication of discomfort glare from windows , 2015 .

[42]  Jennifer A. Veitch,et al.  Preferred luminous conditions in open-plan offices: research and practice recommendations , 2000 .

[43]  Filip Radlinski,et al.  Query chains: learning to rank from implicit feedback , 2005, KDD '05.

[44]  Anca D. Galasiu,et al.  Occupant preferences and satisfaction with the luminous environment and control systems in daylit offices: a literature review , 2006 .

[45]  Vítor Leal,et al.  Occupants interaction with electric lighting and shading systems in real single-occupied offices: Results from a monitoring campaign , 2013 .

[46]  Mehlika Inanici,et al.  A Critical Investigation of Common Lighting Design Metrics for Predicting Human Visual Comfort in Offices with Daylight , 2014 .

[47]  Tianzhen Hong,et al.  Occupant behavior modeling for building performance simulation: Current state and future challenges , 2015 .

[48]  Chuang Wang,et al.  A generalized probabilistic formula relating occupant behavior to environmental conditions , 2016 .

[49]  Athanasios Tzempelikos,et al.  A Bayesian approach for probabilistic classification and inference of occupant thermal preferences in office buildings , 2017 .

[50]  G. Newsham,et al.  Windows, view, and office characteristics predict physical and psychological discomfort , 2010 .

[51]  Christoph F. Reinhart,et al.  A Concept for Predicting Occupants’ Long-Term Visual Comfort within Daylit Spaces , 2016 .

[52]  Athanasios Tzempelikos,et al.  Efficient venetian blind control strategies considering daylight utilization and glare protection , 2013 .

[53]  Jian Yao,et al.  An investigation into the impact of movable solar shades on energy, indoor thermal and visual comfort improvements , 2014 .

[54]  Dirk Müller,et al.  Modelling diversity in building occupant behaviour: a novel statistical approach , 2017 .

[55]  Ian Beausoleil-Morrison,et al.  Development and implementation of an adaptive lighting and blinds control algorithm , 2017 .

[56]  Mpj Mariëlle Aarts,et al.  Building automation and perceived control : a field study on motorized exterior blinds in Dutch offices , 2014 .

[57]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.

[58]  Eric Shen,et al.  Energy and visual comfort analysis of lighting and daylight control strategies , 2014 .

[59]  F. Nicol,et al.  Using field measurements of desktop illuminance in european offices to investigate its dependence on outdoor conditions and its effect on occupant satisfaction, and the use of lights and blinds , 2006 .

[60]  Kevin Van Den Wymelenberg,et al.  Visual Comfort, Discomfort Glare, and Occupant Fenestration Control: Developing a Research Agenda , 2014 .

[61]  Vorapat Inkarojrit,et al.  Monitoring and modelling of manually-controlled Venetian blinds in private offices: a pilot study , 2008 .

[62]  Nicolas Morel,et al.  A novel occupant-adapted and fuzzy logic-ready visual comfort modelling approach using machine learning algorithms , 2015 .

[63]  Kang Soo Kim,et al.  The influence of shading control strategies on the visual comfort and energy demand of office buildings , 2014 .

[64]  Scott Sanner,et al.  Gaussian Process Preference Elicitation , 2010, NIPS.

[65]  L. G. Bakker,et al.  User satisfaction and interaction with automated dynamic facades: A pilot study , 2014 .

[66]  P. R. Tregenza,et al.  View and discomfort glare from windows , 2007 .

[67]  S. Siegel,et al.  Nonparametric Statistics for the Behavioral Sciences , 2022, The SAGE Encyclopedia of Research Design.

[68]  Dj Carter,et al.  Long-term patterns of use of occupant controlled office lighting , 2003 .

[69]  Sanae Chraibi,et al.  Lighting preference profiles of users in an open office environment , 2017 .

[70]  An-Seop Choi,et al.  Performance of Integrated Systems of Automated Roller Shade Systems and Daylight Responsive Dimming Systems , 2011 .

[71]  Iason Konstantzos,et al.  Daylight glare evaluation with the sun in the field of view through window shades , 2017 .

[72]  Peter Boyce,et al.  Lighting quality and office work: two field simulation experiments , 2006 .

[73]  Antoine Guillemin,et al.  An innovative lighting controller integrated in a self-adaptive building control system , 2001 .

[74]  Wei Chu,et al.  Preference learning with Gaussian processes , 2005, ICML.

[75]  Stefano Paolo Corgnati,et al.  Verification of stochastic behavioural models of occupants' interactions with windows in residential buildings , 2015 .

[76]  Darius Braziunas,et al.  Computational Approaches to Preference Elicitation , 2006 .

[77]  Ardeshir Mahdavi,et al.  A preliminary study of representing the inter-occupant diversity in occupant modelling , 2017 .

[78]  Iason Konstantzos,et al.  Experimental and simulation analysis of daylight glare probability in offices with dynamic window shades , 2015 .

[79]  Ralph L. Keeney,et al.  Multiplicative Utility Functions , 1974, Oper. Res..

[80]  Ardeshir Mahdavi,et al.  Occupants' operation of lighting and shading systems in office buildings , 2008 .

[81]  Kyle Konis,et al.  Predicting visual comfort in side-lit open-plan core zones: Results of a field study pairing high dynamic range images with subjective responses , 2014 .