CNN and KPCA-based automated feature extraction for real time driving pattern recognition

Liang Xie; Jili Tao; Qianni Zhang; Huiyu Zhou

doi:10.1109/ACCESS.2019.2938768

CNN and KPCA-based automated feature extraction for real time driving pattern recognition

Liang Xie, Jili Tao^*, Qianni Zhang, Huiyu Zhou

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

17 Citations (Scopus)

178 Downloads (Pure)

Abstract

Driving conditions greatly affect the energy control and the fuel economy of a hybrid electric vehicle (HEV). In this paper, an automated feature extraction scheme based on convolution neural networks (CNNs) and Kernel PCA (KPCA) for real time driving pattern recognition (RTDPR) is proposed in order to achieve consistent performance of the energy management. Firstly, a dimension expanding strategy is performed to transform one-dimensional speed sequences to generate a two-dimensional dataset. Then, the transformed data is sent to the CNN and KPCA based feature extractor. Finally, the feature extractor automatically selects the most representative features for classification. To improve the generalization of CNN to a small sample dataset, the structure of the typical CNN is adjusted by adding the KPCA layer in order to reduce model parameters. The model is well trained and evaluated in simulation, and it is tested for RTDPR in the real world. Simulation and experimental results show that the proposed automated feature extraction strategy outperforms the conventional driving pattern recognition algorithms based on manually feature extraction, which has achieved the state-of-the-art recognition accuracy.

Original language	English
Pages (from-to)	123765-123775
Number of pages	11
Journal	IEEE Access
Volume	7
Early online date	02 Sept 2019
DOIs	https://doi.org/10.1109/ACCESS.2019.2938768
Publication status	Published - 13 Sept 2019

Bibliographical note

Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61603337, in part by the Zhejiang Province Natural Science Fund under Grant LY19F030009, and in part by the Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China (ICT1900362). The work of H. Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union’s Horizon 2020 Research and Innovation Program through the Marie-Sklodowska-Curie under Grant 720325.

Publisher Copyright:
© 2013 IEEE.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

Convolution neural network
driving pattern recognition
feature selection
kernel principle component analysis

ASJC Scopus subject areas

General Computer Science
General Materials Science
General Engineering

Access to Document

10.1109/ACCESS.2019.2938768Licence: CC BY

CNN and KPCA-Based Automated Feature Extraction for Real Time Driving Pattern Recognition
Copyright 2019 the authors. This is an open access article published under a Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium, provided the author and source are cited.
Final published version, 2.83 MBLicence: CC BY

Cite this

@article{d3edc6c0d3a94324928fcdafdfd4b35c,

title = "CNN and KPCA-based automated feature extraction for real time driving pattern recognition",

abstract = "Driving conditions greatly affect the energy control and the fuel economy of a hybrid electric vehicle (HEV). In this paper, an automated feature extraction scheme based on convolution neural networks (CNNs) and Kernel PCA (KPCA) for real time driving pattern recognition (RTDPR) is proposed in order to achieve consistent performance of the energy management. Firstly, a dimension expanding strategy is performed to transform one-dimensional speed sequences to generate a two-dimensional dataset. Then, the transformed data is sent to the CNN and KPCA based feature extractor. Finally, the feature extractor automatically selects the most representative features for classification. To improve the generalization of CNN to a small sample dataset, the structure of the typical CNN is adjusted by adding the KPCA layer in order to reduce model parameters. The model is well trained and evaluated in simulation, and it is tested for RTDPR in the real world. Simulation and experimental results show that the proposed automated feature extraction strategy outperforms the conventional driving pattern recognition algorithms based on manually feature extraction, which has achieved the state-of-the-art recognition accuracy.",

keywords = "Convolution neural network, driving pattern recognition, feature selection, kernel principle component analysis",

author = "Liang Xie and Jili Tao and Qianni Zhang and Huiyu Zhou",

note = "Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 61603337, in part by the Zhejiang Province Natural Science Fund under Grant LY19F030009, and in part by the Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China (ICT1900362). The work of H. Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union{\textquoteright}s Horizon 2020 Research and Innovation Program through the Marie-Sklodowska-Curie under Grant 720325. Publisher Copyright: {\textcopyright} 2013 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.",

year = "2019",

month = sep,

day = "13",

doi = "10.1109/ACCESS.2019.2938768",

language = "English",

volume = "7",

pages = "123765--123775",

journal = "IEEE Access",

issn = "2169-3536",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - CNN and KPCA-based automated feature extraction for real time driving pattern recognition

AU - Xie, Liang

AU - Tao, Jili

AU - Zhang, Qianni

AU - Zhou, Huiyu

N1 - Funding Information: This work was supported in part by the National Natural Science Foundation of China under Grant 61603337, in part by the Zhejiang Province Natural Science Fund under Grant LY19F030009, and in part by the Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China (ICT1900362). The work of H. Zhou was supported in part by the U.K. EPSRC under Grant EP/N011074/1, in part by the Royal Society-Newton Advanced Fellowship under Grant NA160342, and in part by the European Union’s Horizon 2020 Research and Innovation Program through the Marie-Sklodowska-Curie under Grant 720325. Publisher Copyright: © 2013 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2019/9/13

Y1 - 2019/9/13

N2 - Driving conditions greatly affect the energy control and the fuel economy of a hybrid electric vehicle (HEV). In this paper, an automated feature extraction scheme based on convolution neural networks (CNNs) and Kernel PCA (KPCA) for real time driving pattern recognition (RTDPR) is proposed in order to achieve consistent performance of the energy management. Firstly, a dimension expanding strategy is performed to transform one-dimensional speed sequences to generate a two-dimensional dataset. Then, the transformed data is sent to the CNN and KPCA based feature extractor. Finally, the feature extractor automatically selects the most representative features for classification. To improve the generalization of CNN to a small sample dataset, the structure of the typical CNN is adjusted by adding the KPCA layer in order to reduce model parameters. The model is well trained and evaluated in simulation, and it is tested for RTDPR in the real world. Simulation and experimental results show that the proposed automated feature extraction strategy outperforms the conventional driving pattern recognition algorithms based on manually feature extraction, which has achieved the state-of-the-art recognition accuracy.

AB - Driving conditions greatly affect the energy control and the fuel economy of a hybrid electric vehicle (HEV). In this paper, an automated feature extraction scheme based on convolution neural networks (CNNs) and Kernel PCA (KPCA) for real time driving pattern recognition (RTDPR) is proposed in order to achieve consistent performance of the energy management. Firstly, a dimension expanding strategy is performed to transform one-dimensional speed sequences to generate a two-dimensional dataset. Then, the transformed data is sent to the CNN and KPCA based feature extractor. Finally, the feature extractor automatically selects the most representative features for classification. To improve the generalization of CNN to a small sample dataset, the structure of the typical CNN is adjusted by adding the KPCA layer in order to reduce model parameters. The model is well trained and evaluated in simulation, and it is tested for RTDPR in the real world. Simulation and experimental results show that the proposed automated feature extraction strategy outperforms the conventional driving pattern recognition algorithms based on manually feature extraction, which has achieved the state-of-the-art recognition accuracy.

KW - Convolution neural network

KW - driving pattern recognition

KW - feature selection

KW - kernel principle component analysis

U2 - 10.1109/ACCESS.2019.2938768

DO - 10.1109/ACCESS.2019.2938768

M3 - Article

AN - SCOPUS:85077978853

SN - 2169-3536

VL - 7

SP - 123765

EP - 123775

JO - IEEE Access

JF - IEEE Access

ER -

CNN and KPCA-based automated feature extraction for real time driving pattern recognition

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this