Existing studies on transportation mode detection from global positioning system (GPS) trajectories mainly adopt handcrafted features. These features require researchers with a professional background and do not always work well because of the complexity of traffic behavior. To address these issues, we propose a model using a sparse autoencoder to extract point-level deep features from point-level handcrafted features. A convolution neural network then aggregates the point-level deep features and generates a trajectory-level deep feature. A deep neural network incorporates the trajectory-level handcrafted features and the trajectory-level deep feature for detecting the users' transportation modes. Experiments conducted on Microsoft's GeoLife data show that our model can automatically extract the effective features and improve the accuracy of transportation mode detection. Compared with the model using only handcrafted features and shallow classifiers, the proposed model increases the maximum accuracy by 6%.
Hao WANG
North China University of Technology
GaoJun LIU
North China University of Technology
Jianyong DUAN
North China University of Technology
Lei ZHANG
China University of Mining and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hao WANG, GaoJun LIU, Jianyong DUAN, Lei ZHANG, "Detecting Transportation Modes Using Deep Neural Network" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 5, pp. 1132-1135, May 2017, doi: 10.1587/transinf.2016EDL8252.
Abstract: Existing studies on transportation mode detection from global positioning system (GPS) trajectories mainly adopt handcrafted features. These features require researchers with a professional background and do not always work well because of the complexity of traffic behavior. To address these issues, we propose a model using a sparse autoencoder to extract point-level deep features from point-level handcrafted features. A convolution neural network then aggregates the point-level deep features and generates a trajectory-level deep feature. A deep neural network incorporates the trajectory-level handcrafted features and the trajectory-level deep feature for detecting the users' transportation modes. Experiments conducted on Microsoft's GeoLife data show that our model can automatically extract the effective features and improve the accuracy of transportation mode detection. Compared with the model using only handcrafted features and shallow classifiers, the proposed model increases the maximum accuracy by 6%.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8252/_p
Copy
@ARTICLE{e100-d_5_1132,
author={Hao WANG, GaoJun LIU, Jianyong DUAN, Lei ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Detecting Transportation Modes Using Deep Neural Network},
year={2017},
volume={E100-D},
number={5},
pages={1132-1135},
abstract={Existing studies on transportation mode detection from global positioning system (GPS) trajectories mainly adopt handcrafted features. These features require researchers with a professional background and do not always work well because of the complexity of traffic behavior. To address these issues, we propose a model using a sparse autoencoder to extract point-level deep features from point-level handcrafted features. A convolution neural network then aggregates the point-level deep features and generates a trajectory-level deep feature. A deep neural network incorporates the trajectory-level handcrafted features and the trajectory-level deep feature for detecting the users' transportation modes. Experiments conducted on Microsoft's GeoLife data show that our model can automatically extract the effective features and improve the accuracy of transportation mode detection. Compared with the model using only handcrafted features and shallow classifiers, the proposed model increases the maximum accuracy by 6%.},
keywords={},
doi={10.1587/transinf.2016EDL8252},
ISSN={1745-1361},
month={May},}
Copy
TY - JOUR
TI - Detecting Transportation Modes Using Deep Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 1132
EP - 1135
AU - Hao WANG
AU - GaoJun LIU
AU - Jianyong DUAN
AU - Lei ZHANG
PY - 2017
DO - 10.1587/transinf.2016EDL8252
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2017
AB - Existing studies on transportation mode detection from global positioning system (GPS) trajectories mainly adopt handcrafted features. These features require researchers with a professional background and do not always work well because of the complexity of traffic behavior. To address these issues, we propose a model using a sparse autoencoder to extract point-level deep features from point-level handcrafted features. A convolution neural network then aggregates the point-level deep features and generates a trajectory-level deep feature. A deep neural network incorporates the trajectory-level handcrafted features and the trajectory-level deep feature for detecting the users' transportation modes. Experiments conducted on Microsoft's GeoLife data show that our model can automatically extract the effective features and improve the accuracy of transportation mode detection. Compared with the model using only handcrafted features and shallow classifiers, the proposed model increases the maximum accuracy by 6%.
ER -