All Issue

2021 Vol.12, Issue 2 Preview Page

General Article

Automated defect classification in the maintenance phase using a channel attention-based convolutional neural network model of natural language processing
Donguk Yang1
,
Byeol Kim2
,
Hayoung Kim1*
1Master Course, Graduate School of Information, Yonsei University, 50 Yonsei-ro, Seodaemun-gu, Seoul, South Korea
2Ph.D Candidate, Department of Architectural Engineering, Hanyang University-Erica, Ansan-si, South Korea
*Corresponding Author
30 June 2021. pp. 96-109
PDF XML Citation
Abstract

Defect management of buildings is considered an important field of research, not only for maintaining the performance of buildings and extending their lifespan, but also for preventing additional costs. However, because of the recent increase in the number of apartments resulting from urbanization, the scope of management over which that limited management personnel have to take charge has broadened, making it difficult to manage defects efficiently. The systematic classification of defect cases that must precede addressing this is an important concern among construction researchers and managers. Such a classification allows managers to analyze the trend of defects to respond quickly to them and formulate strategies to prevent the occurrence of the same defects. Therefore, we propose a model that automatically classifies defect text data by applying deep learning to overcome the limitations that manage defect cases through simple computerization. This model is designed based on Convolutional Neural Network (CNN) defines defect text data as input and generates classification each of four tasks as output. In terms of model development, we not only design a CNN-based model, but also improve the model’s performance by using a channel attention mechanism. The complete development of this model can contribute to establishing an efficient building defect management system in a Korean building environment and to facilitating defect management work by providing objectivity and consistency to managers.

Keywords
building defect management
defect text classification
deep learning
convolutional neural network
channel attention
natural language processing
References
1
J.S. Burati, J.J. Farrington, and W.B. Ledbetter, Causes of quality deviations in design and construction. Journal of Construction Engineering Management. 118(1) (1992), pp. 34-49. http://dx.doi.org/10.1061/(ASCE)0733- 9364(1992)118:1(34). 10.1061/(ASCE)0733-9364(1992)118:1(34)
2
T.H. Willis and W.D. Willis, A quality performance management system for industrial and construction engineering projects. International Journal of Quality & Reliability Management. 13(9) (1996), pp. 38-48. 10.1108/02656719610150605
3
P.E.D. Love, D.J. Edwards, Z. Irani, and D.H.T. Walker, Project pathogens: the anatomy of omission errors in construction and resource engineering projects. IEEE Transactions on Engineering Management. 56(3) (2009), pp. 425-435. 10.1109/TEM.2009.927774
4
D.W.M. Chan and M.M. Kumaraswamy, A comparative study of the causes of time and cost overruns in Hong Kong construction projects. International Journal of Project Management. 15(1) (1997), pp. 55-63. 10.1016/S0263-7863(96)00039-7
5
P.E.D. Love, S.O. Cheung, Z. Irani, and P.R. Davis, Causal discovery and inference of project disputes. IEEE Transactions on Engineering Management. 58(3) (2010), pp. 400-411. 10.1109/TEM.2010.2048907
6
CIDB. 1989. Managing Construction Quality, a CIDB manual on quality management systems for construction operations, Singapore.
7
P.E. Josephson and Y. Hammarlund, The causes of costs of defects in construction: a study of seven building projects. Automation in Construction. 8(6) (1999), pp. 681-687. 10.1016/S0926-5805(98)00114-9
8
A. Mills, P.E.D. Love, and P. Williams, Defect costs in residential construction. Journal of Construction Engineering and Management. 135(1) (2009), pp. 12-16. 10.1061/(ASCE)0733-9364(2009)135:1(12)
9
P.E.D. Love, Auditing the indirect consequences of rework in construction: a case based approach. Managerial Auditing Journal. 17(3) (2002), pp. 138-146. 10.1108/02686900210419921
10
B.D. Ilozor, M.I. Okoroh, C.E. Egbu, and Archicentre, Understanding residential house defects in Australia from the state of Victoria. Build. Environ. 39(3) (2004), pp. 327-337. 10.1016/j.buildenv.2003.07.002
11
N. Forcada, M. Macarulla, A. Fuertes, M. Casals, M. Gangolells, and X. Roca, Influence of building type on post-handover defects in housing. J. Perform. Constr. Facil. 26(4) (2012), pp. 433-440. 10.1061/(ASCE)CF.1943-5509.0000225
12
W.K. Chong and S.P. Low, Latent building defects: Causes and design strategies to prevent them. J. Perform. Constr. Facil. 20(3) (2006), pp. 213-221. 10.1061/(ASCE)0887-3828(2006)20:3(213)
13
H. Johnssona and J.H. Meilinga, Defects in offsite construction: Timber module prefabrication. Constr. Manage. Econ. 27(7) (2009), pp. 667-681. 10.1080/01446190903002797
14
S. Raslanas, J. Alchimoviene, and N. Banaitiene, Residential areas with apartment houses: analysis of the condition of buildings, planning issues, retrofit strategies and scenarios. Int. J. Strateg. Prop. Manage. 15(2) (2011), pp. 158-172 (ISSN1648-9180). 10.3846/1648715X.2011.586531
15
B. Yuen, A. Yeh, S.J. Appold, G. Earl, J. Ting, and L.K. Kwee, High-rise living in Singapore public housing. Urban Studies, 43(3) (2006), pp. 583-600. 10.1080/00420980500533133
16
B. Yuen and A. Yeh, High-Rise Living in Asian Cities. 2011, New York, Springer. 10.1007/978-90-481-9738-5
17
Y.S. Kim, S.W. Oh, Y.K. Cho, and J.W. Seo, A PDA and wireless web-integrated system for quality inspection and defect management of apartment housing projects. Automation in Construction. 17 (2008), pp. 163-179. 10.1016/j.autcon.2007.03.006
18
J. Georgiou, P.E.D. Love, and J. Smith, A comparison of defects in houses constructed by owners and registered builders in the Australian state of Victoria. Struc. Surv. 17(3) (1999), pp. 160-169. 10.1108/02630809910291343
19
J. Sommerville and J. McCosh, Defects in new homes: An analysis of data on 1.696 new U.K. houses. Struc. Surv. 24(1) (2006), pp. 6-21. 10.1108/02630800610654397
20
E. Valero, A. Forster, F. Bosche, E. Hyslop, L. Wilson, and A. Turmel, Automated defect detection and classification in ashlar masonry walls using machine learning. Automation in construction, 106 (2019). 10.1016/j.autcon.2019.102846
21
J. Georgiou, Verification of a building defect classification system for housing. Struc. Surv. 28(5) (2010), pp. 370-383. 10.1108/02630801011089164
22
P. Yung and B. Yip, Construction quality in China during transition: A review of literature and empirical examination. Int. J. Project Manage. 28(1) (2010), pp. 79-91. 10.1016/j.ijproman.2009.03.003
23
D. Lee, H. Chi, X. Wang, and C. Park, A linked data system framework for sharing construction defect information using ontologies and BIM environments. Automation in Construction. 68 (2016), pp. 102-113. 10.1016/j.autcon.2016.05.003
24
Y. Lin, J. Chang, and Y. Su, Developing construction defect management system using BIM technology in quality inspection. Journal of civil engineering and management. 22(7) (2016), pp. 903-914. 10.3846/13923730.2014.928362
25
C.U. Ubeynarayana and Y.M. Goh, An Ensemble Approach for Classification of Accident Narratives. In Computing in Civil Engineering. 2017 (2017), pp. 409-416. 10.1061/9780784480847.051
26
F. Zhang, H. Fleyeh, X. Wang, and M. Lu, Construction site accident analysis using text mining and natural language processing techniques. Automation in Construction. 99 (2019), pp. 238-248. 10.1016/j.autcon.2018.12.016
27
Y. Kim, Convolutional neural networks for sentence classification. (2014), arXiv preprint arXiv:1408.5882.
28
N. Kalchbrenner, E. Grefenstette, and P. Blunsom, A convolutional neural network for modelling sentences. (2014), arXiv preprint arXiv:1404.2188. 10.3115/v1/P14-1062
29
R. Johnson and T. Zhang, Deep pyramid convolutional neural networks for text categorization. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. (Volume 1: Long Papers) (2017, July), pp. 562-570. 10.18653/v1/P17-1052
30
D.S. Watt, Building pathology: Principles & practice. 1999, Wiley-Blackwell, Oxford, UK.
31
D.S. Seo, J.M. Park, Analysis of Consulting Reports on Defect Disputes in Apartment Building. Journal of the Korea Institute of Building Construction. 13(5) (2013). 10.5345/JKIBC.2013.13.5.498
32
M. Macarulla, N. Forcada, M. Casals, M. Gangolells, A. Fuertes, and X. Roca, Standardizing Housing Defects: Classification, Validation, and Benefits. J. Constr. Eng. Manage. 139(8) (2013), pp. 968-976. 10.1061/(ASCE)CO.1943-7862.0000669
33
N. Forcada, M. Macarulla, and P.E.D. Love, Assessment of residential defects at post-handover. J. Constr. Eng. Manage. 139(4) (2013), pp. 372-378. 10.1061/(ASCE)CO.1943-7862.0000603
34
N. Forcada, M. Macarulla, M. Gangolells, M. Casals, A. Fuertes, and X. Roca, Post-handover housing defects: Sources and origins. J. Perform. Constr. Facil. 27(6) (2013), pp. 756-762. 10.1061/(ASCE)CF.1943-5509.0000368
35
F.E. Rotimi, J. Tookey, and J.O. Rotimi, Evaluating Defect Reporting in New Residential Buildings in New Zealand. Buildings. 5 (2015), pp. 39-55. 10.3390/buildings5010039
36
W.K. Chong and S.P. Low, Assessment of defects at construction and occupancy stages. J. Perform. Constr. Facil. 19(4) (2005), pp. 283-289. 10.1061/(ASCE)0887-3828(2005)19:4(283)
37
W.K. Chong and S.P. Low, Latent Building Defects: Causes and Design Strategies to Prevent Them. J. Perform. Constr. Facil. 20(3) (2006), pp. 213-221. 10.1061/(ASCE)0887-3828(2006)20:3(213)
38
M.Y.L. Chew, Defect analysis in wet areas of buildings. Constr. Build. Mater. 19(3) (2005), pp. 165-173. 10.1016/j.conbuildmat.2004.07.005
39
E. Valero, A. Forster, F. Bosche, E. Hyslop, L. Wilson, and A. Turmel, Automated defect detection and classification in ashlar masonry walls using machine learning. Automation in construction. 106 (2019). 10.1016/j.autcon.2019.102846
40
K. Kimoto, K. Endo, S. Iwashita, and M. Fujiwar, The application of PDA as mobile computing system in construction management. Automation in Construction. 14(4) (2005), pp. 500-511. 10.1016/j.autcon.2004.09.003
41
L.C. Wang, Enhancing construction quality inspection and management using RFID technology. Automation in Construction. 17(4) (2008), pp. 467-479. 10.1016/j.autcon.2007.08.005
42
C. Park, D. Lee, O. Kwon, and X. Wang, A framework for proactive construction defect management using BIM, augmented reality and ontology-based data collection template. Automation in construction. 33 (2013), pp. 61-71. 10.1016/j.autcon.2012.09.010
43
O. Kwon, C. Park, and C. Lim, A defect management system for reinforced concrete work utilizing BIM, image-matching and augmented reality. Automation in construction. 46 (2014), pp. 74-81. 10.1016/j.autcon.2014.05.005
44
K. Lee, G. Hong, S. Lee, S. Lee, and H. Kim, MultiDefectNet: Multi-Class Defect Detection of Building Façade Based on Deep Convolutional Neural Network. Sustainability. 12 (2020), pp. 1-14. 10.3390/su12229785
45
K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition. (2014), arXiv preprint arXiv:1409.1556.
46
K. He, X. Zhang, S. Ren, and J. Sun, Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. (2016), pp. 770-778. 10.1109/CVPR.2016.90
47
J. Hu, L. Shen, and G. Sun, Squeeze-and-excitation networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. (2018), pp. 7132-7141. 10.1109/CVPR.2018.00745
48
T. Mikolov, K. Chen, G. Corrado, and J. Dean, Efficient estimation of word representations in vector space. (2013), arXiv preprint arXiv:1301.3781.
49
T. Mikolov, I. Sutskever, K. Chen, G.S. Corrado, and J. Dean, Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems, 26 (2013), pp. 3111-3119.
50
Ioffe, Sergey, and Christian Szegedy., Batch normalization: Accelerating deep network training by reducing internal covariate shift. (2015). arXiv preprint arXiv:1502.03167.
51
K. He, X. Zhang, S. Ren, and J. Sun, Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In Proceedings of the IEEE international conference on computer vision. (2015). pp. 1026-1034. 10.1109/ICCV.2015.123
52
V. Van Asch, Macro-and micro-averaged evaluation measures [[basic draft]]. (2013), Belgium: CLiPS, 49.
53
T. Kudo, Mecab: Yet another part-of-speech and morphological analyzer. (2006), http://mecab. sourceforge. jp.
54
D. Kingma and J. Ba, Adam: A method for stochastic optimization. (2014). arXiv preprint arXiv:1412.6980.
55
J. Devlin, M.W. Chang, K. Lee, and K. Toutanova, Bert: Pre-training of deep bidirectional transformers for language understanding. (2018), arXiv preprint arXiv:1810.04805.
56
A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, Language models are unsupervised multitask learners. OpenAI blog, 1(8) (2019), p. 9.
Information
  • Publisher :Sustainable Building Research Center (ERC) Innovative Durable Building and Infrastructure Research Center
  • Publisher(Ko) :건설구조물 내구성혁신 연구센터
  • Journal Title :International Journal of Sustainable Building Technology and Urban Development
  • Volume : 12
  • No :2
  • Pages :96-109
  • Received Date : 2021-02-03
  • Accepted Date : 2021-02-28
  • DOI :https://doi.org/10.22712/susb.20210009
Journal Informaiton International Journal of Sustainable Building Technology and Urban Development International Journal of Sustainable Building Technology and Urban Development
Online Submission
  • scopus
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close