A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion
To address poor real-time performance and low accuracy in car-following risk identification, a model based on autoencoders is proposed. Using the SHRP2 natural driving dataset, this paper constructs a car-following risk identification model in two stages. In Stage 1, a deep feedforward neural networ...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Systems |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-8954/13/1/41 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587451739144192 |
|---|---|
| author | Shuwei Guo Yunyu Bo Jie Chen Yanan Liu Jiajia Chen Huimin Ge |
| author_facet | Shuwei Guo Yunyu Bo Jie Chen Yanan Liu Jiajia Chen Huimin Ge |
| author_sort | Shuwei Guo |
| collection | DOAJ |
| description | To address poor real-time performance and low accuracy in car-following risk identification, a model based on autoencoders is proposed. Using the SHRP2 natural driving dataset, this paper constructs a car-following risk identification model in two stages. In Stage 1, a deep feedforward neural network autoencoder reconstructs preprocessed multi-source heterogeneous indicators of human-vehicle-road-environment. The high-dimensional latent space feature representation is used as input for Stage 2, enhancing the basic model’s performance. Eight basic models and sixteen models with autoencoders are compared using multiple evaluation indicators. A simulated driving test verifies the model’s generalization and robustness. Results show improved accuracy in car-following risk identification, with the optimized AutoEncoder_LR performing best at 91.33% for risk presence and 70.14% for risk levels. These findings can aid in safe driving and rear-end accident prevention. |
| format | Article |
| id | doaj-art-b86bd9b2c0af4dfe863ecb2b8985a981 |
| institution | Kabale University |
| issn | 2079-8954 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Systems |
| spelling | doaj-art-b86bd9b2c0af4dfe863ecb2b8985a9812025-01-24T13:50:35ZengMDPI AGSystems2079-89542025-01-011314110.3390/systems13010041A Follow-Up Risk Identification Model Based on Multi-Source Information FusionShuwei Guo0Yunyu Bo1Jie Chen2Yanan Liu3Jiajia Chen4Huimin Ge5School of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212013, ChinaSchool of Automotive and Transportation Engineering, Jiangsu University, Zhenjiang 212013, ChinaTo address poor real-time performance and low accuracy in car-following risk identification, a model based on autoencoders is proposed. Using the SHRP2 natural driving dataset, this paper constructs a car-following risk identification model in two stages. In Stage 1, a deep feedforward neural network autoencoder reconstructs preprocessed multi-source heterogeneous indicators of human-vehicle-road-environment. The high-dimensional latent space feature representation is used as input for Stage 2, enhancing the basic model’s performance. Eight basic models and sixteen models with autoencoders are compared using multiple evaluation indicators. A simulated driving test verifies the model’s generalization and robustness. Results show improved accuracy in car-following risk identification, with the optimized AutoEncoder_LR performing best at 91.33% for risk presence and 70.14% for risk levels. These findings can aid in safe driving and rear-end accident prevention.https://www.mdpi.com/2079-8954/13/1/41traffic engineeringrisk identificationautoencodercar-following scenariosnatural driving |
| spellingShingle | Shuwei Guo Yunyu Bo Jie Chen Yanan Liu Jiajia Chen Huimin Ge A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion Systems traffic engineering risk identification autoencoder car-following scenarios natural driving |
| title | A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion |
| title_full | A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion |
| title_fullStr | A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion |
| title_full_unstemmed | A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion |
| title_short | A Follow-Up Risk Identification Model Based on Multi-Source Information Fusion |
| title_sort | follow up risk identification model based on multi source information fusion |
| topic | traffic engineering risk identification autoencoder car-following scenarios natural driving |
| url | https://www.mdpi.com/2079-8954/13/1/41 |
| work_keys_str_mv | AT shuweiguo afollowupriskidentificationmodelbasedonmultisourceinformationfusion AT yunyubo afollowupriskidentificationmodelbasedonmultisourceinformationfusion AT jiechen afollowupriskidentificationmodelbasedonmultisourceinformationfusion AT yananliu afollowupriskidentificationmodelbasedonmultisourceinformationfusion AT jiajiachen afollowupriskidentificationmodelbasedonmultisourceinformationfusion AT huiminge afollowupriskidentificationmodelbasedonmultisourceinformationfusion AT shuweiguo followupriskidentificationmodelbasedonmultisourceinformationfusion AT yunyubo followupriskidentificationmodelbasedonmultisourceinformationfusion AT jiechen followupriskidentificationmodelbasedonmultisourceinformationfusion AT yananliu followupriskidentificationmodelbasedonmultisourceinformationfusion AT jiajiachen followupriskidentificationmodelbasedonmultisourceinformationfusion AT huiminge followupriskidentificationmodelbasedonmultisourceinformationfusion |