Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning
With the increasing number of vehicles, the usage of technology has also been increased in the transportation system. Although automobile companies are using advanced technologies to develop high performing transports, traffic safety still remains to be a concerning issue. Drivers’ drivin...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9455147/ |
id |
doaj-66341da1eecf4d9f9184e8f0ca4a6930 |
---|---|
record_format |
Article |
spelling |
doaj-66341da1eecf4d9f9184e8f0ca4a69302021-06-21T23:00:26ZengIEEEIEEE Access2169-35362021-01-019865908660610.1109/ACCESS.2021.30896609455147Driving Maneuver Classification Using Domain Specific Knowledge and Transfer LearningSupriya Sarker0https://orcid.org/0000-0002-4148-254XMd. Mokammel Haque1https://orcid.org/0000-0003-3396-6568M. Ali Akber Dewan2https://orcid.org/0000-0001-6347-7509Department of Computer Science and Engineering, Chittagong University of Engineering and Technology, Chattogram, BangladeshDepartment of Computer Science and Engineering, Chittagong University of Engineering and Technology, Chattogram, BangladeshFaculty of Science and Technology, School of Computing and Information Systems, Athabasca University, Athabasca, AB, CanadaWith the increasing number of vehicles, the usage of technology has also been increased in the transportation system. Although automobile companies are using advanced technologies to develop high performing transports, traffic safety still remains to be a concerning issue. Drivers’ driving behavior is considered as one of the key factors of the traffic safety, which could be monitored from their individual driving maneuvers. In this paper, we present a supervised learning model and a semi-supervised transfer learning model for the classification of driving maneuvers from the sensor fusion time series data. The semi-supervised model consists of an unsupervised long-short term memory (LSTM) autoencoder and a supervised LSTM classifier. The supervised model consists of a supervised LSTM model. Because of using LSTM, both of the models can analyze time-series data. In the semi-supervised model, the LSTM encoder learns from unlabeled data as a compressed low dimensional feature vector, which then transfers the learning to the supervised LSTM classifier to classify the driving maneuvers. With the proposed models, we use domain specific knowledge data of the driving environment, such as data changing rules of various driving maneuvers as well as the temporal features over time. We use class functions for seven driving maneuver types and convert those into binary feature vector to use with the LSTM models. We present a comparative analysis of the per class accuracy of the proposed semi-supervised and supervised models with and without using domain-specific knowledge, where the models with the domain specific knowledge outperform. Our proposed semi-supervised and supervised models are compared with the other existing approaches, where our models trained with the domain specific knowledge provided better performance. We also compared the per class accuracy for both the supervised and semi-supervised models, where all the maneuver class accuracy for supervised model was above 98% and semi-supervised model was above 95%. Although the supervised model outperforms the semi-supervised model, the semi-supervised model would be more beneficial in applications where the labeled driving maneuvers data are hard to capture or insufficient.https://ieeexplore.ieee.org/document/9455147/Driving maneuver classificationdomain specific knowledgeLSTM autoencodersemi-supervised learningtransfer learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Supriya Sarker Md. Mokammel Haque M. Ali Akber Dewan |
spellingShingle |
Supriya Sarker Md. Mokammel Haque M. Ali Akber Dewan Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning IEEE Access Driving maneuver classification domain specific knowledge LSTM autoencoder semi-supervised learning transfer learning |
author_facet |
Supriya Sarker Md. Mokammel Haque M. Ali Akber Dewan |
author_sort |
Supriya Sarker |
title |
Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning |
title_short |
Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning |
title_full |
Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning |
title_fullStr |
Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning |
title_full_unstemmed |
Driving Maneuver Classification Using Domain Specific Knowledge and Transfer Learning |
title_sort |
driving maneuver classification using domain specific knowledge and transfer learning |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2021-01-01 |
description |
With the increasing number of vehicles, the usage of technology has also been increased in the transportation system. Although automobile companies are using advanced technologies to develop high performing transports, traffic safety still remains to be a concerning issue. Drivers’ driving behavior is considered as one of the key factors of the traffic safety, which could be monitored from their individual driving maneuvers. In this paper, we present a supervised learning model and a semi-supervised transfer learning model for the classification of driving maneuvers from the sensor fusion time series data. The semi-supervised model consists of an unsupervised long-short term memory (LSTM) autoencoder and a supervised LSTM classifier. The supervised model consists of a supervised LSTM model. Because of using LSTM, both of the models can analyze time-series data. In the semi-supervised model, the LSTM encoder learns from unlabeled data as a compressed low dimensional feature vector, which then transfers the learning to the supervised LSTM classifier to classify the driving maneuvers. With the proposed models, we use domain specific knowledge data of the driving environment, such as data changing rules of various driving maneuvers as well as the temporal features over time. We use class functions for seven driving maneuver types and convert those into binary feature vector to use with the LSTM models. We present a comparative analysis of the per class accuracy of the proposed semi-supervised and supervised models with and without using domain-specific knowledge, where the models with the domain specific knowledge outperform. Our proposed semi-supervised and supervised models are compared with the other existing approaches, where our models trained with the domain specific knowledge provided better performance. We also compared the per class accuracy for both the supervised and semi-supervised models, where all the maneuver class accuracy for supervised model was above 98% and semi-supervised model was above 95%. Although the supervised model outperforms the semi-supervised model, the semi-supervised model would be more beneficial in applications where the labeled driving maneuvers data are hard to capture or insufficient. |
topic |
Driving maneuver classification domain specific knowledge LSTM autoencoder semi-supervised learning transfer learning |
url |
https://ieeexplore.ieee.org/document/9455147/ |
work_keys_str_mv |
AT supriyasarker drivingmaneuverclassificationusingdomainspecificknowledgeandtransferlearning AT mdmokammelhaque drivingmaneuverclassificationusingdomainspecificknowledgeandtransferlearning AT maliakberdewan drivingmaneuverclassificationusingdomainspecificknowledgeandtransferlearning |
_version_ |
1721364026691158016 |