Building management insights driven by a multi-system semantic representation approach

Kaed, Charbel El; Leida, Brett; Gray, Tony

doi:10.1109/wf-iot.2016.7845433

Cited by 12 publications

(18 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Figure 3 indicates that among the building data types in building ontologies, the most common were building sensor and parameter data and physical building information. The use of BMS and integrated sensors have become more prevalent attributing the pervasive representation of building sensor and parameter data in the ontologies reviewed [26,5,27,28]. The prevalent use of BMS also speaks to the frequent inclusion of building actuator data.…”

Section: Socx Data Typesmentioning

confidence: 99%

“…On the basis of the reviewed ontologies an SOCx ontology should cover KPIs at various spatial and temporal scales for building performance assessment, contextual information for reasoning situations, and control and optimization rules for building performance improvement. Only 32% of papers included KPI semantic data in their ontologies [2,31,23,32,33,5,4,34,28,35].…”

Section: Socx Data Typesmentioning

confidence: 99%

“…A further complication of proposing a fully new ontology based on a set of proprietary building systems lies in the proprietary nature of that semantic structure defined (e.g. [5]).…”

Section: Characteristics Of Socx Ontologiesmentioning

confidence: 99%

“…For instance, maintenance, simulation, and performance-based data are required to support SOCx applications while these data types were found in relatively few ontologies (19%, 26%, and 35%, respectively). Before all necessary data types can be included in an ontology, further research in capturing data is also required [5]. For instance, where BIM models do not exist, strategies such as 3D scanning or automated processes to convert 2D floor plans to BIM models [52] can be employed to avoid manually inputting spatial building data.…”

Section: Characteristics Of Socx Ontologiesmentioning

confidence: 99%

“…The challenge in integrating and accessing building data sources lies in their heterogeneous nature. The most common integration technique for building data sources is referred to as Linked Data [3,4,5]. This approach typically stores building data sources separately and relies on a standardized serialization of semantic data in order to cross reference data sources and access timeseries data (sensor, actuator, meter, etc.).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Data Ontology Assessment To Support Smart And Ongoing Commissioning Of Buildings

Quinn¹

2021

Preprint

View full text Add to dashboard Cite

To achieve Canada’s GHG reduction targets, building performance must be improved. Enabling buildings with Smart and Ongoing Commissioning (SOCx) applications will help to achieve peak performance in energy use and improved occupant health and comfort, at minimum cost. A comprehensive literature review highlighted the viability of Brick and Project Haystack ontologies, prompting a quantitative comparison of completeness and expressiveness using a case study with an industry ontology as the baseline for comparison. Additionally, a qualitative comparison was completed using key ontology qualities outlined in literature. A recommendation of Brick is made based on results. Brick achieved higher assessment values in completeness and expressiveness achieving 59% and 100% respectively, as compared to Haystacks 43% and 96%. Additionally, Brick exhibited five of six desirable qualities, where Haystack exhibited only three. If used by SOCx applications, the appropriate ontology permits the optimization of building performance. The recommendation of the appropriate ontology forms the basis for longer- term SOCx prototype development, which will support innovative approaches to sustainability in building operations across scale, as well as next- generation building controls and automation strategies.

show abstract

Section: Socx Data Typesmentioning

confidence: 99%

Section: Socx Data Typesmentioning

confidence: 99%

“…A further complication of proposing a fully new ontology based on a set of proprietary building systems lies in the proprietary nature of that semantic structure defined (e.g. [5]).…”

Section: Characteristics Of Socx Ontologiesmentioning

confidence: 99%

Section: Characteristics Of Socx Ontologiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Data Ontology Assessment To Support Smart And Ongoing Commissioning Of Buildings

Quinn¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

A Pre-screening Approach for Faster Bayesian Network Structure Learning

Rahier¹,

Marié²,

Forbes³

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Learning the structure of Bayesian networks from data is a NP-Hard problem that involves optimization over a super-exponential sized space. Still, in many real-life datasets a number of the arcs contained in the final structure correspond to strongly related pairs of variables and can be identified efficiently with information-theoretic metrics. In this work, we propose a meta-algorithm to accelerate any existing Bayesian network structure learning method. It contains an additional arc pre-screening step allowing to narrow the structure learning task down to a subset of the original variables, thus reducing the overall problem size. We conduct extensive experiments on both public benchmarks and private industrial datasets, showing that this approach enables a significant decrease in computational time and graph complexity for little to no decrease in performance score.

show abstract

RETRACTED ARTICLE: Deep learning model for home automation and energy reduction in a smart home environment platform

Popa

Pop

Şerbănescu

et al. 2018

Neural Comput & Applic

View full text Add to dashboard Cite

Building management insights driven by a multi-system semantic representation approach

Cited by 12 publications

References 11 publications

Data Ontology Assessment To Support Smart And Ongoing Commissioning Of Buildings

Data Ontology Assessment To Support Smart And Ongoing Commissioning Of Buildings

A Pre-screening Approach for Faster Bayesian Network Structure Learning

RETRACTED ARTICLE: Deep learning model for home automation and energy reduction in a smart home environment platform

Contact Info

Product

Resources

About