Feature-based evidential reasoning for probabilistic risk analysis and prediction
Risk analysis plays an important role in quality control in engineering projects for the consideration of time, cost, safety, and the environment. This study proposes a feature-based evidential reasoning approach for probabilistic risk analysis and prediction, incorporating the learning process of b...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/160686 |
| _version_ | 1811684248216666112 |
|---|---|
| author | Wang, Ying Zhang, Limao |
| author2 | School of Civil and Environmental Engineering |
| author_facet | School of Civil and Environmental Engineering Wang, Ying Zhang, Limao |
| author_sort | Wang, Ying |
| collection | NTU |
| description | Risk analysis plays an important role in quality control in engineering projects for the consideration of time, cost, safety, and the environment. This study proposes a feature-based evidential reasoning approach for probabilistic risk analysis and prediction, incorporating the learning process of belief degrees and estimation of the judgment quality. Firstly, classifiers are trained to estimate the probabilistic risk from sub-groups of factors. Secondly, the judgment from each classifier is evaluated according to the classifier's performance which is characterized by the importance weight and reliability. Finally, the judgments from classifiers are fused via evidential reasoning to give the overall probabilistic risk classification result. The proposed approach displays superior performance on the dataset from Wuhan Metro with a 16% increase in precision, a 6% increase in recall, and an 8% increase in F1-score, compared to the direct model without information fusion. The fused model achieves a classification accuracy of 0.86 on the testing samples, which is better than the direct model. Besides, the model shows good error tolerance for wrongly classified results from classifiers without information fusion. The model has an acceptable performance even when the dataset is challenging to conduct classification tasks due to high overlapping areas in the attribute space. |
| first_indexed | 2024-10-01T04:25:36Z |
| format | Journal Article |
| id | ntu-10356/160686 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:25:36Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1606862022-08-01T02:24:41Z Feature-based evidential reasoning for probabilistic risk analysis and prediction Wang, Ying Zhang, Limao School of Civil and Environmental Engineering Engineering::Civil engineering Probabilistic Risk Analysis Information Fusion Risk analysis plays an important role in quality control in engineering projects for the consideration of time, cost, safety, and the environment. This study proposes a feature-based evidential reasoning approach for probabilistic risk analysis and prediction, incorporating the learning process of belief degrees and estimation of the judgment quality. Firstly, classifiers are trained to estimate the probabilistic risk from sub-groups of factors. Secondly, the judgment from each classifier is evaluated according to the classifier's performance which is characterized by the importance weight and reliability. Finally, the judgments from classifiers are fused via evidential reasoning to give the overall probabilistic risk classification result. The proposed approach displays superior performance on the dataset from Wuhan Metro with a 16% increase in precision, a 6% increase in recall, and an 8% increase in F1-score, compared to the direct model without information fusion. The fused model achieves a classification accuracy of 0.86 on the testing samples, which is better than the direct model. Besides, the model shows good error tolerance for wrongly classified results from classifiers without information fusion. The model has an acceptable performance even when the dataset is challenging to conduct classification tasks due to high overlapping areas in the attribute space. Ministry of Education (MOE) Nanyang Technological University The Ministry of Education Tier 1 Grant, Singapore (No. 04MNP000279C120 and No. 04MNP002126C120) and the StartUp Grant at Nanyang Technological University, Singapore (No. 04INS000423C120) are acknowledged for their financial support of this research. 2022-08-01T02:24:41Z 2022-08-01T02:24:41Z 2021 Journal Article Wang, Y. & Zhang, L. (2021). Feature-based evidential reasoning for probabilistic risk analysis and prediction. Engineering Applications of Artificial Intelligence, 102, 104237-. https://dx.doi.org/10.1016/j.engappai.2021.104237 0952-1976 https://hdl.handle.net/10356/160686 10.1016/j.engappai.2021.104237 2-s2.0-85104315738 102 104237 en 04MNP000279C120 04MNP002126C120 04INS000423C120 Engineering Applications of Artificial Intelligence © 2021 Elsevier Ltd. All rights reserved. |
| spellingShingle | Engineering::Civil engineering Probabilistic Risk Analysis Information Fusion Wang, Ying Zhang, Limao Feature-based evidential reasoning for probabilistic risk analysis and prediction |
| title | Feature-based evidential reasoning for probabilistic risk analysis and prediction |
| title_full | Feature-based evidential reasoning for probabilistic risk analysis and prediction |
| title_fullStr | Feature-based evidential reasoning for probabilistic risk analysis and prediction |
| title_full_unstemmed | Feature-based evidential reasoning for probabilistic risk analysis and prediction |
| title_short | Feature-based evidential reasoning for probabilistic risk analysis and prediction |
| title_sort | feature based evidential reasoning for probabilistic risk analysis and prediction |
| topic | Engineering::Civil engineering Probabilistic Risk Analysis Information Fusion |
| url | https://hdl.handle.net/10356/160686 |
| work_keys_str_mv | AT wangying featurebasedevidentialreasoningforprobabilisticriskanalysisandprediction AT zhanglimao featurebasedevidentialreasoningforprobabilisticriskanalysisandprediction |