Cargando…

A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning

Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Hanqing, Wang, Xiaoyuan, Han, Junyan, Xiang, Hui, Li, Hao, Zhang, Yang, Li, Shangqing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8781618/
https://www.ncbi.nlm.nih.gov/pubmed/35062603
http://dx.doi.org/10.3390/s22020644
_version_ 1784638122340909056
author Wang, Hanqing
Wang, Xiaoyuan
Han, Junyan
Xiang, Hui
Li, Hao
Zhang, Yang
Li, Shangqing
author_facet Wang, Hanqing
Wang, Xiaoyuan
Han, Junyan
Xiang, Hui
Li, Hao
Zhang, Yang
Li, Shangqing
author_sort Wang, Hanqing
collection PubMed
description Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven recognition methods of ADB, which are caused by the problems such as the improper processing of the dataset with imbalanced class distribution and one single classifier utilized. Aiming to deal with these disadvantages, an ensemble learning-based recognition method of ADB is proposed in this paper. First, the majority class in the dataset is grouped employing the self-organizing map (SOM) and then are combined with the minority class to construct multiple class balance datasets. Second, three deep learning methods, including convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU), are employed to build the base classifiers for the class balance datasets. Finally, the ensemble classifiers are combined by the base classifiers according to 10 different rules, and then trained and verified using a multi-source naturalistic driving dataset acquired by the integrated experiment vehicle. The results suggest that in terms of the recognition of ADB, the ensemble learning method proposed in this research achieves better performance in accuracy, recall, and F(1)-score than the aforementioned typical deep learning methods. Among the ensemble classifiers, the one based on the LSTM and the Product Rule has the optimal performance, and the other one based on the LSTM and the Sum Rule has the suboptimal performance.
format Online
Article
Text
id pubmed-8781618
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-87816182022-01-22 A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning Wang, Hanqing Wang, Xiaoyuan Han, Junyan Xiang, Hui Li, Hao Zhang, Yang Li, Shangqing Sensors (Basel) Article Aggressive driving behavior (ADB) is one of the main causes of traffic accidents. The accurate recognition of ADB is the premise to timely and effectively conduct warning or intervention to the driver. There are some disadvantages, such as high miss rate and low accuracy, in the previous data-driven recognition methods of ADB, which are caused by the problems such as the improper processing of the dataset with imbalanced class distribution and one single classifier utilized. Aiming to deal with these disadvantages, an ensemble learning-based recognition method of ADB is proposed in this paper. First, the majority class in the dataset is grouped employing the self-organizing map (SOM) and then are combined with the minority class to construct multiple class balance datasets. Second, three deep learning methods, including convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent unit (GRU), are employed to build the base classifiers for the class balance datasets. Finally, the ensemble classifiers are combined by the base classifiers according to 10 different rules, and then trained and verified using a multi-source naturalistic driving dataset acquired by the integrated experiment vehicle. The results suggest that in terms of the recognition of ADB, the ensemble learning method proposed in this research achieves better performance in accuracy, recall, and F(1)-score than the aforementioned typical deep learning methods. Among the ensemble classifiers, the one based on the LSTM and the Product Rule has the optimal performance, and the other one based on the LSTM and the Sum Rule has the suboptimal performance. MDPI 2022-01-14 /pmc/articles/PMC8781618/ /pubmed/35062603 http://dx.doi.org/10.3390/s22020644 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Wang, Hanqing
Wang, Xiaoyuan
Han, Junyan
Xiang, Hui
Li, Hao
Zhang, Yang
Li, Shangqing
A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning
title A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning
title_full A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning
title_fullStr A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning
title_full_unstemmed A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning
title_short A Recognition Method of Aggressive Driving Behavior Based on Ensemble Learning
title_sort recognition method of aggressive driving behavior based on ensemble learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8781618/
https://www.ncbi.nlm.nih.gov/pubmed/35062603
http://dx.doi.org/10.3390/s22020644
work_keys_str_mv AT wanghanqing arecognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT wangxiaoyuan arecognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT hanjunyan arecognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT xianghui arecognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT lihao arecognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT zhangyang arecognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT lishangqing arecognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT wanghanqing recognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT wangxiaoyuan recognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT hanjunyan recognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT xianghui recognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT lihao recognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT zhangyang recognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning
AT lishangqing recognitionmethodofaggressivedrivingbehaviorbasedonensemblelearning