Recommendation of indoor luminous environment for occupants using big data analysis based on machine learning

Abstract To provide an optimal luminous environment for occupants, a personalized luminous environment can be recommended by analyzing personal lifelog data. A basic platform for collecting lifelog data was constructed based on a previous study, and the collected data were classified into three types: task, fatigue, and emotion. Twelve tasks were defined, and appropriate ranges of illuminance and correlated color temperature (CCT) were recommended for each task. In addition, fatigue was divided into four levels, and the most appropriate values of illuminance and CCT were specified within the ranges recommended for each task. In addition, the lighting colors that can alter or improve emotions were designated by selecting the first and second priorities among the five emotions. Totally, 31,680 luminous environment data were processed based on the collected lifelog data, which were divided into training and test datasets. A machine learning (ML)-based luminous environment recommendation system was constructed by applying four ML algorithms (K-nearest neighbor, decision tree, random forest, and support vector machine). The system was designed to recommend an occupant-customized luminous environment based on the task type, fatigue level, and emotion class, and showed an accuracy of approximately 92% or higher.

[1]  Y. Zhai,et al.  Using machine learning algorithms to predict occupants’ thermal comfort in naturally ventilated residential buildings , 2020, Energy and Buildings.

[2]  David A. Ferrucci,et al.  Introduction to "This is Watson" , 2012, IBM J. Res. Dev..

[3]  Kemal Yildirim,et al.  Effects of indoor color on mood and cognitive performance , 2007 .

[4]  L. Ou,et al.  A study of colour emotion and colour preference. Part I: Colour emotions for single colours , 2004 .

[5]  Ferdinando Salata,et al.  Influence of lighting colour temperature on indoor thermal perception: A strategy to save energy from the HVAC installations , 2019, Energy and Buildings.

[6]  Dae-Hyun Choi,et al.  Reinforcement Learning-Based Energy Management of Smart Home with Rooftop Solar Photovoltaic System, Energy Storage System, and Home Appliances , 2019, Sensors.

[7]  Shane Legg,et al.  Deep Reinforcement Learning from Human Preferences , 2017, NIPS.

[8]  Joshua Auld,et al.  Analysis of telecommuting behavior and impacts on travel demand and the environment , 2018, Transportation Research Part D: Transport and Environment.

[9]  G. Priya,et al.  EFFICIENT KNN CLASSIFICATION ALGORITHM FOR BIG DATA , 2017 .

[10]  Tuğçe Kazanasmaz,et al.  Artificial neural networks to predict daylight illuminance in office buildings , 2009 .

[11]  Chan-Su Lee,et al.  Analysis of the Effect on Attention and Relaxation Level by Correlated Color Temperature and Illuminance of LED Lighting using EEG Signal , 2013 .

[12]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[13]  Haisong Xu,et al.  Influence of color temperature on comfort and preference for LED indoor lighting , 2017 .

[14]  Songtao Hu,et al.  Research on work efficiency and light comfort based on EEG evaluation method , 2020 .

[15]  Ana Torres,et al.  Color preference cool versus warm in nursing homes depends on the expected activity for interior spaces , 2020, Frontiers of Architectural Research.

[16]  Miriam Seoane Santos,et al.  How distance metrics influence missing data imputation with k-nearest neighbours , 2020, Pattern Recognit. Lett..

[17]  Li Xiu,et al.  Application of data mining techniques in customer relationship management: A literature review and classification , 2009, Expert Syst. Appl..

[18]  P. Wargocki,et al.  Questionnaire survey on factors influencing comfort with indoor environmental quality in Danish housing , 2012 .

[19]  Rich Caruana,et al.  An empirical comparison of supervised learning algorithms , 2006, ICML.

[20]  J Grünberger,et al.  The effect of biologically-active light on the noo- and thymopsyche and on psychophysiological variables in healthy volunteers. , 1993, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[21]  Gesche M. Huebner,et al.  Saving energy with light? Experimental studies assessing the impact of colour temperature on thermal comfort , 2016 .

[22]  Laura Bellia,et al.  Lighting in indoor environments: Visual and non-visual effects of light sources with different spect , 2011 .

[23]  Songtao Hu,et al.  Experimental investigation about thermal effect of colour on thermal sensation and comfort , 2018, Energy and Buildings.

[24]  Jui-Sheng Chou,et al.  Forecasting energy consumption time series using machine learning techniques based on usage patterns of residential householders , 2018, Energy.

[25]  이희원,et al.  A Study on Influence of the Stress in a Color Temperature and Controllable Illuminance Environment on Human Body , 2015 .

[26]  W. Davis,et al.  How correlated colour temperature manipulates human thermal perception and comfort , 2020, Building and Environment.

[27]  F. Scheer,et al.  The human circadian system adapts to prior photic history , 2011, The Journal of physiology.

[28]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[29]  K. O’Hara,et al.  Lifelogging: Privacy and empowerment with memories for life , 2008 .

[30]  I. Heynderickx,et al.  Lighting up the office: The effect of wall luminance on room appraisal, office workers' performance, and subjective alertness , 2018, Building and Environment.

[31]  L. Schellen,et al.  The influence of light on thermal responses , 2016, Acta physiologica.

[32]  W. H. Engelmann,et al.  The National Human Activity Pattern Survey (NHAPS): a resource for assessing exposure to environmental pollutants , 2001, Journal of Exposure Analysis and Environmental Epidemiology.

[33]  Derk-Jan Dijk,et al.  Timing and Consolidation of Human Sleep, Wakefulness, and Performance by a Symphony of Oscillators , 2005, Journal of biological rhythms.

[34]  J. R. Quinlan.  Induction of decision trees , 2004, Machine Learning.

[35]  Hanui Yu,et al.  The effect of illuminance and correlated colour temperature on perceived comfort according to reading behaviour in a capsule hotel , 2019, Building and Environment.

[36]  F. Naef,et al.  Rhythms of the Genome: Circadian Dynamics from Chromatin Topology, Tissue-Specific Gene Expression, to Behavior. , 2018, Trends in genetics : TIG.

[37]  R. Burnett,et al.  It's about time: A comparison of Canadian and American time–activity patterns† , 2002, Journal of Exposure Analysis and Environmental Epidemiology.

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

[39]  P. Boyce,et al.  Effect of correlated colour temperature on the perception of interiors and colour discrimination performance , 1990 .

[40]  C. Brodley,et al.  Decision tree classification of land cover from remotely sensed data , 1997 .

[41]  Naz Kaya,et al.  Color associations with different building types: An experimental study on American college students , 2006 .

[42]  W. Schobersberger,et al.  Effects of variable lighting intensities and colour temperatures on sulphatoxymelatonin and subjective mood in an experimental office workplace. , 2008, Applied ergonomics.

[43]  Lei Zhao,et al.  A Practical GPU Based KNN Algorithm , 2009 .

[44]  Y. D. de Kort,et al.  Non-image forming effects of illuminance and correlated color temperature of office light on alertness, mood, and performance across cognitive domains , 2019, Building and Environment.

[45]  Naz Kaya,et al.  Relationship between color and emotion: A study of college students. , 2004 .

[46]  R. Baron,et al.  Effects of indoor lighting (illuminance and spectral distribution) on the performance of cognitive tasks and interpersonal behaviors: The potential mediating role of positive affect , 1992 .

[47]  Vladimir Vapnik,et al.  Support-vector networks , 2004, Machine Learning.

[48]  C. Chiang,et al.  Analysis of the Long-term Effect of Office Lighting Environment on Human Reponses , 2012 .

[49]  Minki Sung,et al.  Platform design for lifelog-based smart lighting control , 2020 .