[논문]Neural Structured Learning 기반 그래프 합성을 활용한 BIM 부재 자동분류 모델 성능 향상 방안에 관한 연구

유영수; 이고은; 구본상; 이관훈

doi:10.12652/ksce.2021.41.3.0277

[국내논문] Neural Structured Learning 기반 그래프 합성을 활용한 BIM 부재 자동분류 모델 성능 향상 방안에 관한 연구
Modeling Element Relations as Structured Graphs Via Neural Structured Learning to Improve BIM Element Classification 원문보기

KSCE Journal of Civil and Environmental Engineering Research = 대한토목학회논문집, v.41 no.3, 2021년, pp.277 - 288

유영수 (서울과학기술대학교 건설시스템공학과) , 이고은 (서울과학기술대학교 건설시스템공학과) , 구본상 (서울과학기술대학교 건설시스템공학과) , 이관훈 (고려대학교 컴퓨터학과)

초록
AI-Helper

IFC 정보의 시멘틱 무결성 확보를 위해 BIM 부재와 IFC 엔티티 간 매핑 검증이 필요하다. 이와 관련된 기존 연구들은 기하정보 기반으로 학습시킨 기계학습 알고리즘을 활용하여 BIM 부재 인식 및 분류를 통해 매핑 검증을 실시하였으나, 유사한 기하특성을 가진 부재를 구분하지 못한다는 한계점이 존재하였다. 이에 본 연구는 BIM 모델의 주요 부재를 인공신경망 기반으로 자동 분류하되, 부재 간 관계정보를 삽입하여 분류성능을 향상시키는 것을 목적으로 하였다. 이를 위해 기존 특성 외에 구조화된 신호를 함께 학습하는 NSL 프레임워크를 활용하여 8개의 BIM 부재를 분류하는 모델을 구축하였으며, 그 결과 기하정보 기반 인공신경망 모델과 대비하여 부재 간 관계정보를 삽입한 NSL 모델의 분류정확도가 현저히 상승한 것을 확인하였다.

Abstract ▼ AI-Helper

Building information modeling (BIM) element to industry foundation classes (IFC) entity mappings need to be checked to ensure the semantic integrity of BIM models. Existing studies have demonstrated that machine learning algorithms trained on geometric features are able to classify BIM elements, thereby enabling the checking of these mappings. However, reliance on geometry is limited, especially for elements with similar geometric features. This study investigated the employment of relational data between elements, with the assumption that such additions provide higher classification performance. Neural structured learning, a novel approach for combining structured graph data as features to machine learning input, was used to realize the experiment. Results demonstrated that a significant improvement was attained when trained and tested on eight BIM element types with their relational semantics explicitly represented.

주제어

표/그림 (18)

그림 Fig. 1. Inference Rule-Based IFC Entity Verification Case (Brilakis et al., 2014)
그림 Fig. 2. Learning Process of Perceptron
그림 Fig. 3. Multi-Layer Perceptron Structure
그림 Fig. 4. A Neural Structured Learning Framework (TensorFlow, 2020)
그림 Fig. 5. The Research Process
그림 Fig. 6. Office Building Utilized in the Research
표 Table 1. Element Breakdown of the BIM Model with Respect to IFC Classes
그림 Fig. 7. Process of Extracting Relational Information
표 Table 2. Definition and Average Value of Geometric Features by IFC Classes
그림 Fig. 8. Neural Structured Learning Model Training Process (TensorFlow, 2020)
표 Table 3. Training and Test Set for Each IFC Class
표 Table 4. Accuracy, Precision, Recall and F₁ -score per IFC Class for Multi-Layer Perceptron
그림 Fig. 9. Precision-Recall Curve for Multi-Layer Perceptron (Baseline)
그림 Fig. 10. Precision-Recall Curve for Neural Structured Learning
표 Table 5. Accuracy, Precision, Recall and F₁ -score per IFC Class for Neural Structured Learning
그림 Fig. 11. Multi-Layer Perceptron Classification Results (Confusion Matrix)
그림 Fig. 12. Neural Structured Learning Classification Results (Confusion Matrix)
표 Table 6. Delta Values between Multi-Layer Perceptron and Neural Structured Learning

참고문헌 (23)

Bassier, M., Vergauwen, M. and Van Genechten, B. (2017). "Automated classification of heritage buildings for as-built BIM using machine learning techniques." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 4-2, No. W2, pp. 25-30.
Bazjanac, V. and Kiviniemi, A. (2007). "Reduction, simplification, translation and interpretation in the exchange of model data." International Council for Research and Innovation in Building and Construction w78 Conference, Cape Town, South Africa, Vol. 78, pp. 163-168.
Belsky, M., Sacks, R. and Brilakis, I. (2016). "Semantic enrichment for building information modeling." Computer-Aided Civil and Infrastructure Engineering, Vol. 31, No. 4, pp. 261-274.

상세보기
Bloch, T. and Sacks, R. (2018). "Comparing machine learning and rule-based inferencing for semantic enrichment of BIM models." Automation in Construction, Vol. 91, No. 21, pp. 256-272.
Brilakis, I., Belsky, M. and Sacks, R. (2014). "A semantic enrichment engine for building information modelling." Computer-Aided Civil and Infrastructure Engineering, Vol. 31, pp. 261-274.
Bui, T. D., Ravi, S. and Ramavajjala, V. (2018). "Neural graph learning: Training neural networks using graphs." Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, Marina del Rey, California, pp. 64-71.
Cursi, S., Simeone, D. and Coraglia, U. M. (2017). "An ontology-based platform for BIM semantic enrichment." Proceedings of the 35th eCAADe Conference, Vol. 2, Rome, Italy, pp. 649-656.
Eastman, C., Lee, J. M., Jeong, Y. S. and Lee, J. K. (2009). "Automatic rule-based checking of building designs." Automation in Construction, Vol. 18, No. 8, pp. 1011-1033.

상세보기
Jung, R. K., Koo, B. S. and Yu, Y. S. (2019). "Using deep learning for automated classification of wall subtypes for semantic integrity checking of building information models." KIBIM Magazine, Vol. 9, No. 4, pp. 31-40 (in Korean).
Kim, J. S., Song, J. Y. and Lee, J. K. (2019). "Recognizing and classifying unknown object in BIM using 2D CNN." International Conference on Computer-Aided Architectural Design Futures, pp. 47-57 (in Korean).
Kipf, T. N. and Welling, M. (2016). "Semi-supervised classification with graph convolutional networks." Published as a Conference Paper at ICLR 2017, Toulon, France, arXiv:1609.02907.
Koo, B. S. and Shin, B. J. (2018). "Applying novelty detection to identify model element to IFC class misclassifications on architectural and infrastructure building information models." Journal of Computational Design and Engineering, Vol. 5, No. 4, pp. 391-400.

상세보기
Koo, B. S., La, S. M., Cho, N. W. and Yu, Y. S. (2019). "Using support vector machines to classify building elements for checking the semantic integrity of building information models." Automation in Construction, Vol. 98, No. 15, pp. 183-194.
Koo, B. S., Yu, Y. S. and Jung, R. K. (2018). "Machine learning based approach to building element classification for semantic integrity checking of building information models." Korean Journal of Computational Design and Engineering, Vol. 23, No. 4, pp. 373-383 (in Korean).

상세보기
Lomio, F., Farinha, R., Laasonen, M. and Huttunen, H. (2018). "Classification of building information model (BIM) structures with deep learning." 2018 7th European Workshop on Visual Information Processing (EUVIP), IEEE, Tampere, Finland, pp. 1-6.
Ma, L., Sacks, R. and Kattell, U. (2017). "Building model object classification for semantic enrichment using geometric features and pairwise spatial relations." 2017 Lean and Computing in Construction Congress (LC3), Heraklion, Crete, Greece, Vol. 1, pp. 373-380.
Pauwels, P. and Terkaj, W. (2016). "EXPRESS to OWL for construction industry: Towards a recommendable and usable ifcOWL ontology." Automation in Construction, Vol. 63, pp. 100-133.

상세보기
Sacks, R., Ma, L., Yosef, R., Borrmann, A., Daum, S. and Kattel, U. (2017). "Semantic enrichment for building information modeling: Procedure for compiling inference rules and operators for complex geometry." Journal of Computing in Civil Engineering, Vol. 31, No. 6, 04017062.

상세보기
Shin, J. H., Kwon, S. W., Lee, K. H., Choi, S. D. and Kim, J. M. (2015). "A study of the establishment of framework for information exchange based on IFC model in domestic collaborative design environment." Korean Journal of Construction Engineering and Management, Vol. 16, No. 1, pp. 24-34. (in Korean).
Su, W., Yuan, Y. and Zhu, M. (2015, September). "A relationship between the average precision and the area under the roc curve." In Proceedings of the 2015 International Conference on The Theory of Information Retrieval, Northampton, Massachusetts, pp. 349-352.
TensorFlow (2020). The neural structured learning framework, Available at: https://www.tensorflow.org/neural_structured_learning/framework?hlko (Accessed: July 4, 2020).
Venugopal, M., Eastman, C. M., Sacks, R. and Teizer, J. (2012). "Semantics of model views for information exchanges using the industry foundation class schema." Advanced Engineering Informatics, Vol. 26, No. 2, pp. 411-428.

상세보기
Wu, J. and Zhang, J. (2019). "New automated BIM object classification method to support BIM interoperability." Journal of Computing in Civil Engineering, Vol. 33, No. 5, 04019033.

상세보기

저자의 다른 논문 :

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증