@article{fan_unsupervised_2018,
	title = {Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: {A} review},
	volume = {159},
	issn = {0378-7788},
	shorttitle = {Unsupervised data analytics in mining big building operational data for energy efficiency enhancement},
	url = {http://www.sciencedirect.com/science/article/pii/S0378778817326671},
	doi = {10.1016/j.enbuild.2017.11.008},
	abstract = {Building operations account for the largest proportion of energy use throughout the building life cycle. The energy saving potential is considerable taking into account the existence of a wide variety of building operation deficiencies. The advancement in information technologies has made modern buildings to be not only energy-intensive, but also information-intensive. Massive amounts of building operational data, which are in essence the reflection of actual building operating conditions, are available for knowledge discovery. It is very promising to extract potentially useful insights from big building operational data, based on which actionable measures for energy efficiency enhancement are devised. Data mining is an advanced technology for analyzing big data. It consists of two main types of data analytics, i.e., supervised and unsupervised analytics. Despite of the power of supervised analytics in predictive modeling, unsupervised analytics are more practical and promising in discovering novel knowledge given limited prior knowledge. This paper provides a comprehensive review on the current utilization of unsupervised data analytics in mining massive building operational data. The commonly used unsupervised analytics are summarized according to their knowledge representations and applications. The challenges and opportunities are elaborated as guidance for future research in this multi-disciplinary field.},
	language = {en},
	urldate = {2020-10-01},
	journal = {Energy and Buildings},
	author = {Fan, Cheng and Xiao, Fu and Li, Zhengdao and Wang, Jiayuan},
	month = jan,
	year = {2018},
	keywords = {Big data, Building energy efficiency, Building energy management, Building operational performance, Unsupervised data mining},
	pages = {296--308},
}

{"_id":"XT35pMH3wcm8xbJ3p","bibbaseid":"fan-xiao-li-wang-unsuperviseddataanalyticsinminingbigbuildingoperationaldataforenergyefficiencyenhancementareview-2018","author_short":["Fan, C.","Xiao, F.","Li, Z.","Wang, J."],"bibdata":{"bibtype":"article","type":"article","title":"Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: A review","volume":"159","issn":"0378-7788","shorttitle":"Unsupervised data analytics in mining big building operational data for energy efficiency enhancement","url":"http://www.sciencedirect.com/science/article/pii/S0378778817326671","doi":"10.1016/j.enbuild.2017.11.008","abstract":"Building operations account for the largest proportion of energy use throughout the building life cycle. The energy saving potential is considerable taking into account the existence of a wide variety of building operation deficiencies. The advancement in information technologies has made modern buildings to be not only energy-intensive, but also information-intensive. Massive amounts of building operational data, which are in essence the reflection of actual building operating conditions, are available for knowledge discovery. It is very promising to extract potentially useful insights from big building operational data, based on which actionable measures for energy efficiency enhancement are devised. Data mining is an advanced technology for analyzing big data. It consists of two main types of data analytics, i.e., supervised and unsupervised analytics. Despite of the power of supervised analytics in predictive modeling, unsupervised analytics are more practical and promising in discovering novel knowledge given limited prior knowledge. This paper provides a comprehensive review on the current utilization of unsupervised data analytics in mining massive building operational data. The commonly used unsupervised analytics are summarized according to their knowledge representations and applications. The challenges and opportunities are elaborated as guidance for future research in this multi-disciplinary field.","language":"en","urldate":"2020-10-01","journal":"Energy and Buildings","author":[{"propositions":[],"lastnames":["Fan"],"firstnames":["Cheng"],"suffixes":[]},{"propositions":[],"lastnames":["Xiao"],"firstnames":["Fu"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Zhengdao"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Jiayuan"],"suffixes":[]}],"month":"January","year":"2018","keywords":"Big data, Building energy efficiency, Building energy management, Building operational performance, Unsupervised data mining","pages":"296–308","bibtex":"@article{fan_unsupervised_2018,\n\ttitle = {Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: {A} review},\n\tvolume = {159},\n\tissn = {0378-7788},\n\tshorttitle = {Unsupervised data analytics in mining big building operational data for energy efficiency enhancement},\n\turl = {http://www.sciencedirect.com/science/article/pii/S0378778817326671},\n\tdoi = {10.1016/j.enbuild.2017.11.008},\n\tabstract = {Building operations account for the largest proportion of energy use throughout the building life cycle. The energy saving potential is considerable taking into account the existence of a wide variety of building operation deficiencies. The advancement in information technologies has made modern buildings to be not only energy-intensive, but also information-intensive. Massive amounts of building operational data, which are in essence the reflection of actual building operating conditions, are available for knowledge discovery. It is very promising to extract potentially useful insights from big building operational data, based on which actionable measures for energy efficiency enhancement are devised. Data mining is an advanced technology for analyzing big data. It consists of two main types of data analytics, i.e., supervised and unsupervised analytics. Despite of the power of supervised analytics in predictive modeling, unsupervised analytics are more practical and promising in discovering novel knowledge given limited prior knowledge. This paper provides a comprehensive review on the current utilization of unsupervised data analytics in mining massive building operational data. The commonly used unsupervised analytics are summarized according to their knowledge representations and applications. The challenges and opportunities are elaborated as guidance for future research in this multi-disciplinary field.},\n\tlanguage = {en},\n\turldate = {2020-10-01},\n\tjournal = {Energy and Buildings},\n\tauthor = {Fan, Cheng and Xiao, Fu and Li, Zhengdao and Wang, Jiayuan},\n\tmonth = jan,\n\tyear = {2018},\n\tkeywords = {Big data, Building energy efficiency, Building energy management, Building operational performance, Unsupervised data mining},\n\tpages = {296--308},\n}\n\n","author_short":["Fan, C.","Xiao, F.","Li, Z.","Wang, J."],"key":"fan_unsupervised_2018","id":"fan_unsupervised_2018","bibbaseid":"fan-xiao-li-wang-unsuperviseddataanalyticsinminingbigbuildingoperationaldataforenergyefficiencyenhancementareview-2018","role":"author","urls":{"Paper":"http://www.sciencedirect.com/science/article/pii/S0378778817326671"},"keyword":["Big data","Building energy efficiency","Building energy management","Building operational performance","Unsupervised data mining"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["iwKepCrWBps7ojhDx"],"keywords":["big data","building energy efficiency","building energy management","building operational performance","unsupervised data mining"],"search_terms":["unsupervised","data","analytics","mining","big","building","operational","data","energy","efficiency","enhancement","review","fan","xiao","li","wang"],"title":"Unsupervised data analytics in mining big building operational data for energy efficiency enhancement: A review","year":2018}