iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles
Abstract Scene risk identification is essential for the traffic safety of Internet of Vehicles. However, the performance of existing risk identification approaches is heavily limited by the imbalanced historical data and the poor model interpretability. Meanwhile, the large processing delay and the...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-12-01
|
| Series: | IET Communications |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cmu2.12704 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850113418787291136 |
|---|---|
| author | Wuchang Zhong Siming Wang Rong Yu |
| author_facet | Wuchang Zhong Siming Wang Rong Yu |
| author_sort | Wuchang Zhong |
| collection | DOAJ |
| description | Abstract Scene risk identification is essential for the traffic safety of Internet of Vehicles. However, the performance of existing risk identification approaches is heavily limited by the imbalanced historical data and the poor model interpretability. Meanwhile, the large processing delay and the potential privacy leakage threat also restrict their application. In this paper, a novel risk identification model is proposed that leverages the synthetic minority over‐sampling technique nearest neighbor (SMOTEENN) method to balance between high‐risk and low‐risk data. The risk identification model has fine interpretability by using recursive feature elimination cross validation (RFECV) with the Shapley additive explanation (SHAP) to analyze the importance of different features, and further elaborately design the Focal Loss function to tackle the disparity between the difficult and easy sample learning. The proposed interpretability scene risk identification framework, named iScene, is built on the infrastructure of 6G space‐air‐ground integrated networks (SAGINs) with blockchain assistance. The model updata efficiency and privacy preservation are effectively enhanced. An elastic computing offloading algorithm is applied to minimize the system overhead under the hierarchical edge service architecture. The experimental evaluation is carried out to verify the effectiveness of the proposed risk identification framework. The results indicate that the G‐Mean value is increased by 23.4%, while the task average response delay is reduced by 21.2%, compared to that in the traditional risk identification approaches with local computing services. |
| format | Article |
| id | doaj-art-9cb64d5d0cd44d8e8fdf9b7dda6f0d32 |
| institution | OA Journals |
| issn | 1751-8628 1751-8636 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Communications |
| spelling | doaj-art-9cb64d5d0cd44d8e8fdf9b7dda6f0d322025-08-20T02:37:09ZengWileyIET Communications1751-86281751-86362024-12-0118201900191410.1049/cmu2.12704iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehiclesWuchang Zhong0Siming Wang1Rong Yu2School of Automation Guangdong University of Technology Guangzhou ChinaSchool of Automation Guangdong University of Technology Guangzhou ChinaSchool of Automation Guangdong University of Technology Guangzhou ChinaAbstract Scene risk identification is essential for the traffic safety of Internet of Vehicles. However, the performance of existing risk identification approaches is heavily limited by the imbalanced historical data and the poor model interpretability. Meanwhile, the large processing delay and the potential privacy leakage threat also restrict their application. In this paper, a novel risk identification model is proposed that leverages the synthetic minority over‐sampling technique nearest neighbor (SMOTEENN) method to balance between high‐risk and low‐risk data. The risk identification model has fine interpretability by using recursive feature elimination cross validation (RFECV) with the Shapley additive explanation (SHAP) to analyze the importance of different features, and further elaborately design the Focal Loss function to tackle the disparity between the difficult and easy sample learning. The proposed interpretability scene risk identification framework, named iScene, is built on the infrastructure of 6G space‐air‐ground integrated networks (SAGINs) with blockchain assistance. The model updata efficiency and privacy preservation are effectively enhanced. An elastic computing offloading algorithm is applied to minimize the system overhead under the hierarchical edge service architecture. The experimental evaluation is carried out to verify the effectiveness of the proposed risk identification framework. The results indicate that the G‐Mean value is increased by 23.4%, while the task average response delay is reduced by 21.2%, compared to that in the traditional risk identification approaches with local computing services.https://doi.org/10.1049/cmu2.12704blockchaininterpretabilityspace‐air‐ground integrated networkrisk identification |
| spellingShingle | Wuchang Zhong Siming Wang Rong Yu iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles IET Communications blockchain interpretability space‐air‐ground integrated network risk identification |
| title | iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles |
| title_full | iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles |
| title_fullStr | iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles |
| title_full_unstemmed | iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles |
| title_short | iScene: An interpretable framework with hierarchical edge services for scene risk identification in 6G internet of vehicles |
| title_sort | iscene an interpretable framework with hierarchical edge services for scene risk identification in 6g internet of vehicles |
| topic | blockchain interpretability space‐air‐ground integrated network risk identification |
| url | https://doi.org/10.1049/cmu2.12704 |
| work_keys_str_mv | AT wuchangzhong isceneaninterpretableframeworkwithhierarchicaledgeservicesforsceneriskidentificationin6ginternetofvehicles AT simingwang isceneaninterpretableframeworkwithhierarchicaledgeservicesforsceneriskidentificationin6ginternetofvehicles AT rongyu isceneaninterpretableframeworkwithhierarchicaledgeservicesforsceneriskidentificationin6ginternetofvehicles |