Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition

Jeya Vikranth Jeyakumar; Eun Sun Lee; Zhengxu Xia; Sandeep Singh Sandha; Nathan Tausik; Mani Srivastava

doi:10.1145/3267305.3267529

Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition

Jeya Vikranth Jeyakumar, Eun Sun Lee, Zhengxu Xia, Sandeep Singh Sandha, Nathan Tausik, Mani Srivastava

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

32 Scopus citations

Abstract

Traditional machine learning approaches for recognizing modes of transportation rely heavily on hand-crafted feature extraction methods which require domain knowledge. So, we propose a hybrid deep learning model: Deep Convolutional Bidirectional-LSTM (DCBL) which combines convolutional and bidirectional LSTM layers and is trained directly on raw sensor data to predict the transportation modes. We compare our model to the traditional machine learning approaches of training Support Vector Machines and Multilayer Perceptron models on extracted features. In our experiments, DCBL performs better than the feature selection methods in terms of accuracy and simplifies the data processing pipeline. The models are trained on the Sussex-Huawei Locomotion-Transportation (SHL) dataset. The submission of our team, Vahan, to SHL recognition challenge uses an ensemble of DCBL models trained on raw data using the different combination of sensors and window sizes and achieved an F1-score of 0.96 on our test data.

Original language	English (US)
Title of host publication	Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers
Publisher	ASSOC COMPUTING MACHINERY
Pages	1606-1615
Number of pages	10
ISBN (Print)	9781450359665
DOIs	https://doi.org/10.1145/3267305.3267529
State	Published - Oct 8 2018
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2022-06-24
Acknowledgements: This research was supported in part by the NIH Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) under award 1-U54EB020404-01, the U.S. Army Research Laboratory and the UK Ministry of Defence under Agreement Number W911 NF-16-3-0001, the National Science Foundation under awards #CNS-1636916 and 1640813, and the King Abdullah University of Science and Technology (KAUST) through its Sensor Innovation research program. Any findings in this material are those of the author(s) and do not reflect the views of any of the above funding agencies. The U.S. and U.K. Governments are authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

Access to Document

10.1145/3267305.3267529

Cite this

Jeyakumar, J. V., Sun Lee, E., Xia, Z., Sandha, S. S., Tausik, N., & Srivastava, M. (2018). Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers (pp. 1606-1615). ASSOC COMPUTING MACHINERY. https://doi.org/10.1145/3267305.3267529

@inproceedings{076be7b6062b47c0afb7778bc01a438d,

title = "Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition",

abstract = "Traditional machine learning approaches for recognizing modes of transportation rely heavily on hand-crafted feature extraction methods which require domain knowledge. So, we propose a hybrid deep learning model: Deep Convolutional Bidirectional-LSTM (DCBL) which combines convolutional and bidirectional LSTM layers and is trained directly on raw sensor data to predict the transportation modes. We compare our model to the traditional machine learning approaches of training Support Vector Machines and Multilayer Perceptron models on extracted features. In our experiments, DCBL performs better than the feature selection methods in terms of accuracy and simplifies the data processing pipeline. The models are trained on the Sussex-Huawei Locomotion-Transportation (SHL) dataset. The submission of our team, Vahan, to SHL recognition challenge uses an ensemble of DCBL models trained on raw data using the different combination of sensors and window sizes and achieved an F1-score of 0.96 on our test data.",

author = "Jeyakumar, {Jeya Vikranth} and {Sun Lee}, Eun and Zhengxu Xia and Sandha, {Sandeep Singh} and Nathan Tausik and Mani Srivastava",

note = "KAUST Repository Item: Exported on 2022-06-24 Acknowledgements: This research was supported in part by the NIH Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) under award 1-U54EB020404-01, the U.S. Army Research Laboratory and the UK Ministry of Defence under Agreement Number W911 NF-16-3-0001, the National Science Foundation under awards #CNS-1636916 and 1640813, and the King Abdullah University of Science and Technology (KAUST) through its Sensor Innovation research program. Any findings in this material are those of the author(s) and do not reflect the views of any of the above funding agencies. The U.S. and U.K. Governments are authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2018",

month = oct,

day = "8",

doi = "10.1145/3267305.3267529",

language = "English (US)",

isbn = "9781450359665",

pages = "1606--1615",

booktitle = "Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers",

publisher = "ASSOC COMPUTING MACHINERY",

}

Jeyakumar, JV, Sun Lee, E, Xia, Z, Sandha, SS, Tausik, N & Srivastava, M 2018, Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition. in Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers. ASSOC COMPUTING MACHINERY, pp. 1606-1615. https://doi.org/10.1145/3267305.3267529

Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition. / Jeyakumar, Jeya Vikranth; Sun Lee, Eun; Xia, Zhengxu et al.
Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers. ASSOC COMPUTING MACHINERY, 2018. p. 1606-1615.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition

AU - Jeyakumar, Jeya Vikranth

AU - Sun Lee, Eun

AU - Xia, Zhengxu

AU - Sandha, Sandeep Singh

AU - Tausik, Nathan

AU - Srivastava, Mani

N1 - KAUST Repository Item: Exported on 2022-06-24 Acknowledgements: This research was supported in part by the NIH Center of Excellence for Mobile Sensor Data-to-Knowledge (MD2K) under award 1-U54EB020404-01, the U.S. Army Research Laboratory and the UK Ministry of Defence under Agreement Number W911 NF-16-3-0001, the National Science Foundation under awards #CNS-1636916 and 1640813, and the King Abdullah University of Science and Technology (KAUST) through its Sensor Innovation research program. Any findings in this material are those of the author(s) and do not reflect the views of any of the above funding agencies. The U.S. and U.K. Governments are authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation hereon. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2018/10/8

Y1 - 2018/10/8

N2 - Traditional machine learning approaches for recognizing modes of transportation rely heavily on hand-crafted feature extraction methods which require domain knowledge. So, we propose a hybrid deep learning model: Deep Convolutional Bidirectional-LSTM (DCBL) which combines convolutional and bidirectional LSTM layers and is trained directly on raw sensor data to predict the transportation modes. We compare our model to the traditional machine learning approaches of training Support Vector Machines and Multilayer Perceptron models on extracted features. In our experiments, DCBL performs better than the feature selection methods in terms of accuracy and simplifies the data processing pipeline. The models are trained on the Sussex-Huawei Locomotion-Transportation (SHL) dataset. The submission of our team, Vahan, to SHL recognition challenge uses an ensemble of DCBL models trained on raw data using the different combination of sensors and window sizes and achieved an F1-score of 0.96 on our test data.

AB - Traditional machine learning approaches for recognizing modes of transportation rely heavily on hand-crafted feature extraction methods which require domain knowledge. So, we propose a hybrid deep learning model: Deep Convolutional Bidirectional-LSTM (DCBL) which combines convolutional and bidirectional LSTM layers and is trained directly on raw sensor data to predict the transportation modes. We compare our model to the traditional machine learning approaches of training Support Vector Machines and Multilayer Perceptron models on extracted features. In our experiments, DCBL performs better than the feature selection methods in terms of accuracy and simplifies the data processing pipeline. The models are trained on the Sussex-Huawei Locomotion-Transportation (SHL) dataset. The submission of our team, Vahan, to SHL recognition challenge uses an ensemble of DCBL models trained on raw data using the different combination of sensors and window sizes and achieved an F1-score of 0.96 on our test data.

UR - http://hdl.handle.net/10754/679304

UR - https://dl.acm.org/doi/10.1145/3267305.3267529

UR - http://www.scopus.com/inward/record.url?scp=85058339978&partnerID=8YFLogxK

U2 - 10.1145/3267305.3267529

DO - 10.1145/3267305.3267529

M3 - Conference contribution

SN - 9781450359665

SP - 1606

EP - 1615

BT - Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers

PB - ASSOC COMPUTING MACHINERY

ER -

Jeyakumar JV, Sun Lee E, Xia Z, Sandha SS, Tausik N, Srivastava M. Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition. In Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers. ASSOC COMPUTING MACHINERY. 2018. p. 1606-1615 doi: 10.1145/3267305.3267529

Deep Convolutional Bidirectional LSTM Based Transportation Mode Recognition

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this