GOBNILP algorithm in identifying optimal risk model structure for additional work in railway project realizations
Source abstract
Abstract
Abstract The article presents research results on applying Bayesian Network Structure Learning (BNSL) methodology to assess the risk of additional construction works occurring in railway infrastructure projects. The justification for conducting research using Bayesian networks is the fact that its effectiveness has been confirmed in many issues in civil engineering and related disciplines. On this background, implementations of this methodology in the issue of structural reliability are particularly distinguished. Bayesian network inference models can also serve as effective decision support systems in the context of complex design processes and construction project implementation. The research was based on a database of information about the determinants of the risk process associated with the necessity of additional construction work. Using this collected information, the Bayesian network methodology was implemented, particularly the GOBNILP network structure extraction algorithm. Due to the properties of Bayesian networks, the created model can be applied both in forecasting the risk of additional works becoming necessary, as well as in diagnosing the causes of such necessity. An additional advantage of this model is its interpretability, resulting directly from the connections (edges) between individual nodes forming the DAG (Directed Acyclic Graph) structure. The validated Bayesian network, understood as a generative AI tool, can also be used for data augmentation. This, in turn, can lead to a more detailed description of the process and make it possible to analyse the sensitivity of the model with respect to its variables encoded in the form of nodes of the DAG structure. It should be emphasized that in previous attempts to use Bayesian networks in engineering applications, their structure was typically specified by the user (expert) and had an arbitrary character. Therefore, the research presented in this work, concerning the autonomous extraction of Bayesian network structure from data, represents a significant achievement in the field of civil engineering.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Economic and Technological Systems Analysis · BIM and Construction Integration · Multi-Criteria Decision Making
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (49)
Show source-provided references
1. Sucar LE. Bayesian networks: learning. In: Sucar LE, editor. Probabilistic graphical models: principles and applications. Cham: Springer International Publishing; 2021. p. 153–79. https://doi.org/10.1007/978-3-030-61943-5_8.10.1007/978-3-030-61943-5_8 ↗
2. Conrady S, Jouffe L. Bayesian networks & BayesiaLab: A practical introduction for researchers. Bayesia USA, Vol. 1, 2015.
3. Scutari M, Denis J-B. Bayesian networks: with examples in R. Chapman and Hall/CRC, 2021.10.1201/9780429347436 ↗
4. Meshram K. Machine learning applications in civil engineering. Mach Learn Appl Civ Eng. 2023. https://doi.org/10.1016/C2022-0-01428-8.10.1016/C2022-0-01428-8 ↗
5. Korb K, Nicholson A. Bayesian Artificial Intelligence. New Jersey: CRC Press; 2010. https://doi.org/10.1198/tech.2005.s836.10.1198/tech.2005.s836 ↗
6. Hossain E. Machine learning crash course for engineers. Mach Learn Appl Civ Eng. 2023. https://doi.org/10.1007/978-3-031-46990-9.10.1007/978-3-031-46990-9 ↗
7. Pearl J. The Book of Why_ The New Science of Cause and Effect-Basic Books (2018). Notices of the American Mathematical Society, vol. 1, 2018.
8. Pearl J. Probabilistic reasoning in intelligent systems: networks of plausible inference. Elsevier; 2014.
9. Worden K, Tsialiamanis G, Cross EJ, Rogers TJ. Artificial neural networks. In Machine learning in modeling and simulation: Methods and applications. Springer; 2023. pp. 85–11910.1007/978-3-031-36644-4_2 ↗
10. Briganti G, Scutari M, McNally RJ. A tutorial on bayesian networks for psychopathology researchers. Psychol Methods. 2023;28(4):947.10.1037/met0000479 ↗
11. Koller D, Friedman N. Probabilistic graphical models: principles and techniques. MIT Press, 2009.
12. Ji Z, Xia Q, Meng G. A review of parameter learning methods in Bayesian network. In Advanced intelligent computing theories and applications: 11th international conference, ICIC 2015, Fuzhou, China, August 20–23, 2015. Proceedings, Part III 11. Springer; 2015. pp. 3–1210.1007/978-3-319-22053-6_1 ↗
13. Kitson NK, Constantinou AC, Guo Z, Liu Y, Chobtham K. A survey of Bayesian network structure learning. Artif Intell Rev. 2023;56(8):8721–814. https://doi.org/10.1007/s10462-022-10351-w.10.1007/s10462-022-10351-w ↗
14. Scutari M. Bayesian network constraint-based structure learning algorithms: Parallel and optimized implementations in the bnlearn R package. J Stat Softw. 2017. https://doi.org/10.18637/jss.v077.i02.10.18637/jss.v077.i02 ↗
15. Scutari M, Graafland CE, Gutiérrez JM. Who learns better Bayesian network structures: accuracy and speed of structure learning algorithms. Int J Approxim Reason. 2019;115:235–53.10.1016/j.ijar.2019.10.003 ↗
16. Scutari M, Silander T. bnlearn: Bayesian network structure learning, parameter learning and inference. R package version, vol. 3, 2022
17. Balov N, Salzman P. Catnet: categorical Bayesian network inference. R package version, 1(4), 201210.1109/BIBM.2012.6392692 ↗
18. Yuen K-V. Bayesian methods for structural dynamics and civil engineering. Wiley; 2010.10.1002/9780470824566 ↗
19. Cai B, Liu Y, Liu Z, Chang Y, Jiang L. Bayesian networks for reliability engineering. Springer; 2020.10.1007/978-981-13-6516-4 ↗
20. Rusek J, Alibrandi U, Leszek S, Chomacki L. BNSL GOBNILP algorithm in application to damage intensity prognostic system to RC multistorey residential buildings subjected to negative impacts of the industrial environment of mines. J Build Eng. 2023. https://doi.org/10.1016/j.jobe.2023.107885.10.1016/j.jobe.2023.107885 ↗
21. Jin Y, Zhang J, Sun L. Safety risk assessment of prefabricated building construction based on Bayesian network. In IOP conference series: earth and environmental science, 2019; vol. 371, p. 3205210.1088/1755-1315/371/3/032052 ↗
22. Leśniak A, Janowiec F. Risk assessment of additional works in railway construction investments using the bayes network. Sustainability. 2019. https://doi.org/10.3390/su11195388.10.3390/su11195388 ↗
23. Kovačević M, Ivanišević N, Stević D, Marković LM, Bulajić B, Marković L, Gvozdović N. Decision-support system for estimating resource consumption in bridge construction based on machine learning. Axioms. 2022;12(1):19.10.3390/axioms12010019 ↗
24. Leśniak A, Janowiec F. Analysis of additional works in completed railway construction projects. Sci Rev Eng Environ Sci. 2019;28(3):366–76. https://doi.org/10.22630/PNIKS.2019.28.3.34.10.22630/PNIKS.2019.28.3.34 ↗
25. Iqbal S, Choudhry RM, Holschemacher K, Ali A, Tamošaitienė J. Risk management in construction projects. Technol Econ Dev Econ. 2015. https://doi.org/10.3846/20294913.2014.994582.10.3846/20294913.2014.994582 ↗
26. Chenya L, Aminudin E, Mohd S, Yap LS. Intelligent risk management in construction projects: systematic literature review. IEEE Access. 2022. https://doi.org/10.1109/ACCESS.2022.3189157.10.1109/ACCESS.2022.3189157 ↗
27. Tamošaitienė J, Zavadskas EK, Turskis Z. Multi-criteria risk assessment of a construction project. In procedia computer science, vol. 17; 2013. https://doi.org/10.1016/j.procs.2013.05.01810.1016/j.procs.2013.05.018 ↗
28. Shibani A, Hasan D, Saaifan J, Sabboubeh H, Eltaip M, Saidani M, Gherbal N. Financial risk management in the construction projects. J King Saud Univ Eng Sci. 2022. https://doi.org/10.1016/j.jksues.2022.05.001.10.1016/j.jksues.2022.05.001 ↗
29. Cussens J. GOBNILP: Learning Bayesian network structure with integer programming. In International conference on probabilistic graphical models. PMLR; 2020, pp. 605–608.
30. Cussens J, Järvisalo M, Korhonen JH, Bartlett M. Bayesian network structure learning with integer programming: polytopes, facets and complexity. J Artific Intell Res. 2017;58:185–229.10.1613/jair.5203 ↗
31. Buntine W. Theory refinement on Bayesian networks. In Uncertainty in artificial intelligence. Elsevier; 1991. pp. 52–6010.1016/B978-1-55860-203-8.50010-3 ↗
32. Schwarz G. Estimating the dimension of a model. The annals of statistics, 1978. pp. 461–464.10.1214/aos/1176344136 ↗
33. Scanagatta M, Salmerón A, Stella F. A survey on Bayesian network structure learning from data. Progress Artific Intell. 2019;8(4):425–39.10.1007/s13748-019-00194-y ↗
34. Carvalho AM. Scoring functions for learning Bayesian networks. Inesc-id Tec Rep. 2009;12:1–48.
35. Tan X, Gao X, Wang Z, Han H, Liu X, Chen D. Learning the structure of Bayesian networks with ancestral and/or heuristic partition. Inf Sci. 2022;584:719–51.10.1016/j.ins.2021.10.052 ↗
36. Jaakkola T, Sontag D, Globerson A, Meila M. Learning Bayesian network structure using LP relaxations. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 2010, pp. 358–365.
37. Seoh R. Solving Bayesian network structure learning problem with integer linear programming. 2020. arXiv preprint arXiv:2007.02829.
38. Bartlett M, Cussens J. Integer linear programming for the Bayesian network structure learning problem. Artif Intell. 2017;244:258–71.10.1016/j.artint.2015.03.003 ↗
39. Bestuzheva K, Besançon M, Chen W-K, Chmiela A, Donkiewicz T, Van Doornmalen J. The SCIP optimization suite 8.0. 2021. arXiv preprint arXiv:2112.08872.
40. Cussens J. Pygobnilp manual (version 1.0). Retrieved December 10, 2024, from https://jcussens.github.io/#gradstudy
41. Gurobi Optimization L. Gurobi optimizer reference manual, 2023.
42. Sunday OA. Impact of variation orders on public construction projects. In 26th Annual ARCOM Conference, Leeds, UK. Citeseer, 2010.
43. Sutrisna M. Developing a knowledge based system for the valuation of variations on civil engineering works (Doctoral dissertation). University of Wolverhampton, 2004.
44. Bruzelius N, Flyvbjerg B, Rothengatter W. Big decisions, big risks. Improving accountability in mega projects. Transp Policy. 2002;9(2):143–54. https://doi.org/10.1016/S0967-070X(02)00014-8.10.1016/S0967-070X(02)00014-8 ↗
45. Sousa V, Marques N, Almeida D, Dias LA. Risk management framework for the construction industry according to the ISO 31000:2009 Standard.
46. Fallet-Fidry G, Weber P, Simon C, Iung B, Duval C. Evidential network-based extension of Leaky Noisy-OR structure for supporting risks analyses. In IFAC proceedings volumes (IFAC-PapersOnline), Vol. 45, pp. 672–677. 2012. IFAC Secretariat. https://doi.org/10.3182/20120829-3-MX-2028.0018310.3182/20120829-3-MX-2028.00183 ↗
47. Lorch L, Rothfuss J, Schölkopf B, Krause A. Dibs: Differentiable bayesian structure learning. Adv Neural Inf Process Syst. 2021;34:24111–23.
48. Deleu T, Góis A, Emezue C, Rankawat M, Lacoste-Julien S, Bauer S, Bengio Y. Bayesian structure learning with generative flow networks. In Uncertainty in Artificial Intelligence. PMLR; 2022, pp. 518–528.
49. Zheng Z, Wang C, Gao X, Chen G. RBNets: A reinforcement learning approach for learning Bayesian network structure. In Joint European conference on machine learning and knowledge discovery in databases. Springer, 2023. pp. 193–20810.1007/978-3-031-43418-1_12 ↗