CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data
This paper aims to establish a driving style recognition method that is highly accurate, fast and generalizable, considering the lack of data types in driving style classification task and the low recognition accuracy of widely used unsupervised clustering algorithms and single convolutional neural...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10044645/ |
| _version_ | 1828009619449970688 |
|---|---|
| author | Yingfeng Cai Ruidong Zhao Hai Wang Long Chen Yubo Lian Yilin Zhong |
| author_facet | Yingfeng Cai Ruidong Zhao Hai Wang Long Chen Yubo Lian Yilin Zhong |
| author_sort | Yingfeng Cai |
| collection | DOAJ |
| description | This paper aims to establish a driving style recognition method that is highly accurate, fast and generalizable, considering the lack of data types in driving style classification task and the low recognition accuracy of widely used unsupervised clustering algorithms and single convolutional neural network methods. First, we propose a method to collect the information on driver’s operation time sequence in view of the imperfect driving data, and then extract the driver’s style features through convolutional neural network. Then, for the collected temporal data, the Long Short Term Memory networks (LSTM) module is added to encode and transform the driving features, to achieve the driving style classification. The results show that the accuracy of driving style recognition reaches over 93%, while the speed is improved significantly. |
| first_indexed | 2024-04-10T08:42:26Z |
| format | Article |
| id | doaj.art-43e0e9ec228d4ad0a07ca7fdea0842ce |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T08:42:26Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-43e0e9ec228d4ad0a07ca7fdea0842ce2023-02-23T00:01:02ZengIEEEIEEE Access2169-35362023-01-0111162031621210.1109/ACCESS.2023.324514610044645CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series DataYingfeng Cai0https://orcid.org/0000-0002-0633-9887Ruidong Zhao1https://orcid.org/0000-0001-5086-5182Hai Wang2https://orcid.org/0000-0002-9136-8091Long Chen3https://orcid.org/0000-0002-2079-3867Yubo Lian4Yilin Zhong5Automotive Engineering Research Institute, Jiangsu University, Zhenjiang, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang, ChinaSchool of Automotive and Traffic Engineering, Jiangsu University, Zhenjiang, ChinaAutomotive Engineering Research Institute, Jiangsu University, Zhenjiang, ChinaBYD Auto Industry Company Ltd., Shenzhen, ChinaBYD Auto Industry Company Ltd., Shenzhen, ChinaThis paper aims to establish a driving style recognition method that is highly accurate, fast and generalizable, considering the lack of data types in driving style classification task and the low recognition accuracy of widely used unsupervised clustering algorithms and single convolutional neural network methods. First, we propose a method to collect the information on driver’s operation time sequence in view of the imperfect driving data, and then extract the driver’s style features through convolutional neural network. Then, for the collected temporal data, the Long Short Term Memory networks (LSTM) module is added to encode and transform the driving features, to achieve the driving style classification. The results show that the accuracy of driving style recognition reaches over 93%, while the speed is improved significantly.https://ieeexplore.ieee.org/document/10044645/Convolutional neural network (CNN)driving style classificationLSTMneural networktime series data |
| spellingShingle | Yingfeng Cai Ruidong Zhao Hai Wang Long Chen Yubo Lian Yilin Zhong CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data IEEE Access Convolutional neural network (CNN) driving style classification LSTM neural network time series data |
| title | CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data |
| title_full | CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data |
| title_fullStr | CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data |
| title_full_unstemmed | CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data |
| title_short | CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data |
| title_sort | cnn lstm driving style classification model based on driver operation time series data |
| topic | Convolutional neural network (CNN) driving style classification LSTM neural network time series data |
| url | https://ieeexplore.ieee.org/document/10044645/ |
| work_keys_str_mv | AT yingfengcai cnnlstmdrivingstyleclassificationmodelbasedondriveroperationtimeseriesdata AT ruidongzhao cnnlstmdrivingstyleclassificationmodelbasedondriveroperationtimeseriesdata AT haiwang cnnlstmdrivingstyleclassificationmodelbasedondriveroperationtimeseriesdata AT longchen cnnlstmdrivingstyleclassificationmodelbasedondriveroperationtimeseriesdata AT yubolian cnnlstmdrivingstyleclassificationmodelbasedondriveroperationtimeseriesdata AT yilinzhong cnnlstmdrivingstyleclassificationmodelbasedondriveroperationtimeseriesdata |