Ontology-based automated information extraction from building energy conservation codes

Peng, Zhou; El-Gohary, Nora

doi:10.1016/j.autcon.2016.09.004

Cited by 106 publications

(39 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ontology method is introduced into the computation field from the 1980s to provide a basis of building models of all things in which computer science is interested; thus, it is intelligible both to computers and humans. Ontology is a domain and application-oriented method to assist in extracting knowledge that is specific to a particular domain and/or application [26,27]. Besides, according to Moguillansky and Simari [28], an ontology model is not only formal and machine-understandable, but also available for knowledge sharing.…”

Section: Ontology Methodmentioning

confidence: 99%

Study on the Evaluation Method of Green Construction Based on Ontology and BIM

Wang

Zhou

et al. 2019

Advances in Civil Engineering

View full text Add to dashboard Cite

Many problems and issues affect the green construction process. Inaccurate assessment is one of the important factors for green construction. The objective of this study is to propose a BIM and ontology-based approach that enables the evaluation information of green construction to be inferred from a knowledge base in order to achieve scheme optimization. To automate the inference, this study established the BIM ontology that consists of BIM shared ontology and BIM construction ontology. First, IFC extension is adopted in green construction assessment system to generate attribute sets. IFC-based parameters stored in BIM models are mapped to OWL and will be used as the data source of the evaluation indicators. Then, BIM-shared ontology and BIM construction ontology are defined. Protégé is employed to simulate the evaluation indicator system. Last, utilizing BIM knowledge base, through the construction of SWRL rule language and the Drools inference, the scores of evaluation indicators could be obtained. The experimental results demonstrated that BIM knowledge base for the evaluation of green construction could realize the sharing, maintenance, and acquisition of knowledge among different participants of the project and improve the management of green construction. The proposed ontological inference of evaluation item enables an automated search of the aspects needing improvements in green construction and assist project managers in using BIM data more easily and effectively.

show abstract

Section: Ontology Methodmentioning

confidence: 99%

Study on the Evaluation Method of Green Construction Based on Ontology and BIM

Wang

Zhou

et al. 2019

Advances in Civil Engineering

View full text Add to dashboard Cite

show abstract

“…In construction literature, POS Tagging has been used as part of NLP pipelines for information extraction for compliance checking (Zhang & El-Gohary, 2014, 2015a, Zhou & El-Gohary, 2017, Li et al, 2016, contract requirements extraction (Zhou & El-Gohary, 2016), IFC schema extension , and information retrieval from Building Information Models (BIM) (Zhang & El-Gohary, 2015b, Lin et al, 2016, Oraee et al, 2017. However, to the best of the authors' knowledge, using approaches inspired by POS tagging to decipher construction activities was never attempted before.…”

Section: Literature Reviewmentioning

confidence: 99%

Automatic Understanding of Construction Schedules: Part-of-Activity Tagging

Amer¹,

Golparvar-Fard²

2019

Computing in Construction

View full text Add to dashboard Cite

Nowadays, construction planning practices, whether conducted by human planners or artificial intelligence (AI) systems, rely heavily on manually elaborated descriptions of construction means and methods. As part of envisioning a new planning system that automatically learns construction knowledge from previous projects' schedules, this paper introduces Part-of-Activity (POA) Tagging: a construction-specific word-category disambiguation method for decoding the constructional functionalities encoded in activity names. These functionalities represent the roles each token, i.e. word, in an activity name plays in understanding that activity from a construction point of view. The model is built using Bidirectional Long Short Term Memory Recurrent Neural Networks (BI-LSTM RNN). After training on a manually annotated dataset of more than 7000 activities, the model achieved a token accuracy of ~92%. The significance of this method lies in its ability to allow an AI System to decipher construction schedules. This schedule understanding opens the door for further applications such as the automated elaboration of weekly work plans and alignment of master schedules to weekly work plans.

show abstract

“…However, existing techniques and models for automatic GNER and classification are limited in their capabilities compared to other NER efforts involving geological reports for three reasons (Goyal et al, 2018;Liu & El-Gohary, 2017;Zhou & El-Gohary, 2017). Then, the extracted important information should be transformed into a structured form to enable further flexible analysis.…”

Section: Introductionmentioning

confidence: 99%

“…Then, the extracted important information should be transformed into a structured form to enable further flexible analysis. However, existing techniques and models for automatic GNER and classification are limited in their capabilities compared to other NER efforts involving geological reports for three reasons (Goyal et al, 2018;Liu & El-Gohary, 2017;Zhou & El-Gohary, 2017). First, compared to domain-general narrative text, geological reports are highly ambiguous and variable, in terms of both their textual characteristics and patterns because these reports are typically written by different inspectors/experts from a variety of scientific organizations and governmental agencies.…”

Section: Introductionmentioning

confidence: 99%

GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning

Qiu

Xie

Tao

2019

Earth and Space Science

View full text Add to dashboard Cite

A variety of detailed data about geological topics and geoscience knowledge are buried in the geoscience literature and rarely used. Named entity recognition (NER) provides both opportunities and challenges to leverage this wealth of data in the geoscience literature for data analysis and further information extraction. Existing NER models and techniques are mainly based on rule‐based and supervised approaches, and developing such systems requires a costly manual effort. In this paper, we first design a generic stepwise framework for domain‐specific NER. Following this framework, domain‐specific entities and domain‐general words are collected and selected as seed terms. Normalization and grouping processes are then applied to these seed terms for further analysis. A random extraction algorithm based on a unigram language model is used to generate a large‐scale training data set consisting of probabilistically labeled pseudosentences. Each generated sentence is then used as input to the self‐training and learning algorithm. Experimental results on two constructed data sets demonstrate that the proposed model effectively recognizes and identifies geological named entities.

show abstract

Ontology-based automated information extraction from building energy conservation codes

Cited by 106 publications

References 21 publications

Study on the Evaluation Method of Green Construction Based on Ontology and BIM

Study on the Evaluation Method of Green Construction Based on Ontology and BIM

Automatic Understanding of Construction Schedules: Part-of-Activity Tagging

GNER: A Generative Model for Geological Named Entity Recognition Without Labeled Data Using Deep Learning

Contact Info

Product

Resources

About