Convolutional Neural Network-Based Travel Mode Recognition Based on Multiple Smartphone Sensors
Abstract
:1. Introduction
- (1)
- We designed a CNN-based travel mode recognition system, which consisted of data collection, data segmentation, and deep learning model. It could provide accurate and energy-efficient transportation mode detection ability based on multiple smartphone sensors.
- (2)
- We evaluated the classification performance of the proposed CNN model under different hyperparameters and combinations of sensors. We also discussed the impact of different sensor combinations on the accuracy of travel pattern recognition. Experimental analysis provided a constructive and helpful reference for sensors data selection and fusion in future research.
2. Related Works
3. Methods
3.1. Architecture
- (1)
- Mobile terminal
- (2)
- Server terminal
3.2. Data Collection
3.3. Data Segmentation
3.4. Travel Mode Detection Model
3.4.1. Preprocessing
3.4.2. CNN Model
3.4.3. Evaluations
4. Results
4.1. Dataset and Experimental Setup
4.2. Hyperparameters Analysis
4.3. The Impact of Different Combinations of Sensors
4.4. Result of Travel Mode Detection
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Dabiri, S.; Heaslip, K. Inferring transportation modes from GPS trajectories using a convolutional neural network. Transp. Res. Part C Emerg. Technol. 2018, 86, 360–371. [Google Scholar] [CrossRef] [Green Version]
- Hemminki, S.; Nurmi, P.; Tarkoma, S. Accelerometer-based transportation mode detection on smartphones. In Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems, Roma, Italy, 11–15 November 2013; pp. 1–14. [Google Scholar]
- Ashbrook, D.; Starner, T. Using GPS to learn significant locations and predict movement across multiple users. Pers. Ubiquitous Comput. 2003, 7, 275–286. [Google Scholar] [CrossRef]
- Fang, S.H.; Fei, Y.X.; Xu, Z.; Tsao, Y. Learning transportation modes from smartphone sensors based on deep neural network. IEEE Sens. J. 2017, 17, 6111–6118. [Google Scholar] [CrossRef]
- Ma, W.; Li, Q.; Zhou, B.; Huang, Z. Location and 3-D visual awareness-based dynamic texture updating for indoor 3-D model. IEEE Internet Things J. 2020, 7, 7612–7624. [Google Scholar] [CrossRef]
- Cornacchia, M.; Ozcan, K.; Zheng, Y.; Velipasalar, S. A survey on activity detection and classification using wearable sensors. IEEE Sens. J. 2016, 17, 386–403. [Google Scholar] [CrossRef]
- Zhou, B.; Li, Q.; Mao, Q.; Tu, W.; Zhang, X. Activity sequence-based indoor pedestrian localization using smartphones. IEEE Trans. Hum.-Mach. Syst. 2014, 45, 562–574. [Google Scholar] [CrossRef]
- Zhou, B.; Li, Q.; Mao, Q.; Tu, W.; Zhang, X.; Chen, L. ALIMC: Activity landmark-based indoor mapping via crowdsourcing. IEEE Trans. Intell. Transp. Syst. 2015, 16, 2774–2785. [Google Scholar] [CrossRef]
- Zhou, B.; Zheng, T.; Huang, J.; Zhang, Y.; Tu, W.; Li, Q.; Deng, M. A pedestrian network construction system based on crowdsourced walking trajectories. IEEE Internet Things J. 2020, 8, 7203–7213. [Google Scholar] [CrossRef]
- Zhou, B.; Li, Q.; Zhai, G.; Mao, Q.; Chen, L. A graph optimization-based indoor map construction method via crowdsourcing. IEEE Access 2018, 6, 33692–33701. [Google Scholar] [CrossRef]
- Zhou, B.; Yang, J.; Li, Q. Smartphone-based activity recognition for indoor localization using a convolutional neural network. Sensors 2019, 19, 621. [Google Scholar] [CrossRef] [Green Version]
- Reddy, S.; Mun, M.; Burke, J.; Estrin, D.; Hansen, M.; Srivastava, M. Using mobile phones to determine transportation modes. ACM Trans. Sens. Netw. (TOSN) 2010, 6, 1–27. [Google Scholar] [CrossRef]
- Shin, D.; Aliaga, D.; Tunçer, B.; Arisona, S.M.; Kim, S.; Zund, D.; Schmitt, G. Urban sensing: Using smartphones for transportation mode classification. Comput. Environ. Urban Syst. 2015, 53, 76–86. [Google Scholar] [CrossRef]
- Zhou, X.; Yu, W.; Sullivan, W.C. Making pervasive sensing possible: Effective travel mode sensing based on smartphones. Comput. Environ. Urban Syst. 2016, 58, 52–59. [Google Scholar] [CrossRef]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 2012, 25, 1097–1105. [Google Scholar] [CrossRef]
- Xu, Y.; Du, J.; Dai, L.R.; Lee, C.H. An experimental study on speech enhancement based on deep neural networks. IEEE Signal Process. Lett. 2013, 21, 65–68. [Google Scholar] [CrossRef]
- Wang, X.; Gao, L.; Mao, S.; Pandey, S. CSI-based fingerprinting for indoor localization: A deep learning approach. IEEE Trans. Veh. Technol. 2016, 66, 763–776. [Google Scholar] [CrossRef] [Green Version]
- Lecun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef]
- Deng, M.; Huang, J.; Zhang, Y.; Liu, H.; Tang, L.; Tang, J.; Yang, X. Generating urban road intersection models from low-frequency GPS trajectory data. Int. J. Geogr. Inf. Sci. 2018, 32, 2337–2361. [Google Scholar] [CrossRef]
- Huang, J.; Zhang, Y.; Deng, M.; He, Z. Mining crowdsourced trajectory and geo-tagged data for spatial-semantic road map construction. Trans. GIS 2022, 26, 735–754. [Google Scholar] [CrossRef]
- Li, J.; Pei, X.; Wang, X.; Yao, D.; Zhang, Y.; Yue, Y. Transportation mode identification with GPS trajectory data and GIS information. Tsinghua Sci. Technol. 2021, 26, 403–416. [Google Scholar] [CrossRef]
- Zheng, Y.; Liu, L.; Wang, L.; Xie, X. Learning transportation mode from raw gps data for geographic applications on the web. In Proceedings of the 17th International Conference on World Wide Web, Beijing, China, 21–25 April 2008; pp. 247–256. [Google Scholar]
- Mäenpää, H.; Lobov, A.; Lastra, J.L.M. Travel mode estimation for multi-modal journey planner. Transp. Res. Part C Emerg. Technol. 2017, 82, 273–289. [Google Scholar] [CrossRef]
- Bolbol, A.; Cheng, T.; Tsapakis, I.; Haworth, J. Inferring hybrid transportation modes from sparse GPS data using a moving window SVM classification. Comput. Environ. Urban Syst. 2012, 36, 526–537. [Google Scholar] [CrossRef] [Green Version]
- Xiao, G.; Juan, Z.; Zhang, C. Travel mode detection based on GPS track data and Bayesian networks. Comput. Environ. Urban Syst. 2015, 54, 14–22. [Google Scholar] [CrossRef]
- Gong, H.; Chen, C.; Bialostozky, E.; Lawson, C.T. A GPS/GIS method for travel mode detection in New York City. Comput. Environ. Urban Syst. 2012, 36, 131–139. [Google Scholar] [CrossRef]
- Wang, B.; Gao, L.; Juan, Z. Travel mode detection using GPS data and socioeconomic attributes based on a random forest classifier. IEEE Trans. Intell. Transp. Syst. 2017, 19, 1547–1558. [Google Scholar] [CrossRef]
- Feng, T.; Timmermans, H.J.P. Transportation mode recognition using GPS and accelerometer data. Transp. Res. Part C Emerg. Technol. 2013, 37, 118–130. [Google Scholar] [CrossRef]
- Han, Y.; Hong, B.W. Deep learning based on fourier convolutional neural network incorporating random kernels. Electronics 2021, 10, 2004. [Google Scholar] [CrossRef]
- Choi, J.; Kim, Y. Time-aware learning framework for over-the-top consumer classification based on machine-and deep-learning capabilities. Appl. Sci. 2020, 10, 8476. [Google Scholar] [CrossRef]
- Kim, C.I.; Cho, Y.; Jung, S.; Rew, J.; Hwang, E. Animal Sounds Classification Scheme Based on Multi-Feature Network with Mixed Datasets. KSII Trans. Internet Inf. Syst. (TIIS) 2020, 14, 3384–3398. [Google Scholar]
- Endo, Y.; Toda, H.; Nishida, K.; Kawanobe, A. Deep feature extraction from trajectories for transportation mode estimation. In Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, Auckland, New Zealand, 19–22 April 2016; Springer: Cham, Switzerland, 2016; pp. 54–66. [Google Scholar]
- Wang, H.; Liu, G.J.; Duan, J.; Zhang, L. Detecting transportation modes using deep neural network. IEICE Trans. Inf. Syst. 2017, 100, 1132–1135. [Google Scholar] [CrossRef] [Green Version]
- Ma, W.; Zhang, S.; Huang, J. Mobile augmented reality based indoor map for improving geo-visualization. PeerJ Comput. Sci. 2021, 7, e704. [Google Scholar] [CrossRef] [PubMed]
- Assemi, B.; Safi, H.; Mesbah, M.; Ferreira, L. Developing and validating a statistical model for travel mode identification on smartphones. IEEE Trans. Intell. Transp. Syst. 2016, 17, 1920–1931. [Google Scholar] [CrossRef]
- Su, X.; Caceres, H.; Tong, H.; He, Q. Online travel mode identification using smartphones with battery saving considerations. IEEE Trans. Intell. Transp. Syst. 2016, 17, 2921–2934. [Google Scholar] [CrossRef]
- Sadeghian, P.; Håkansson, J.; Zhao, X. Review and evaluation of methods in transport mode detection based on GPS tracking data. J. Traffic Transp. Eng. 2021, 8, 467–482. [Google Scholar] [CrossRef]
Hyperparameters | Range | Values |
---|---|---|
Number of convolutional layers | [2, 5] | 2, 3, 4, 5 |
Filter size | [2, 6] | 2, 3, 4, 5, 6 |
Number of feature maps | [40, 80] | 40, 50, 60, 70, 80 |
Pooling size | [2, 6] | 2, 3, 4, 5, 6 |
Learning rate | [0.0001, 0.005] | 0.0001, 0.0005, 0.001, 0.005 |
Batch size | [24, 28] | 16, 32, 64, 128, 256 |
Travel Mode | Bike | Bus | Car | Metro | Walk |
---|---|---|---|---|---|
Data size | 5572 | 5560 | 5567 | 5367 | 5392 |
Number of Sensors | Sensors | F-Measure |
---|---|---|
1 | Acc. | 0.978 |
Gyro. | 0.914 | |
Mag. | 0.852 | |
Baro. | Nan | |
2 | Acc. + Gyro. | 0.984 |
Acc. + Mag. | 0.983 | |
Acc. + Baro. | 0.973 | |
Gyro. + Mag. | 0.916 | |
Gyro. + Baro. | 0.812 | |
Mag. + Baro. | 0.867 | |
3 | Acc. + Gyro. + Mag. | 0.984 |
Acc. + Mag. + Baro. | 0.983 | |
Acc. + Gyro. + Baro. | 0.979 | |
Gyro. + Mag. + Baro. | 0.915 | |
4 | Acc. + Gyro. + Mag. + Baro. | 0.985 |
Predicted | Bike | Bus | Car | Metro | Walk | |
---|---|---|---|---|---|---|
Actual | ||||||
Bike | 2163 | 18 | 6 | 0 | 14 | |
Bus | 21 | 2189 | 6 | 2 | 11 | |
Car | 0 | 1 | 2101 | 3 | 0 | |
Metro | 0 | 11 | 6 | 2139 | 2 | |
Walk | 45 | 5 | 8 | 3 | 2130 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Guo, L.; Huang, J.; Ma, W.; Sun, L.; Zhou, L.; Pan, J.; Yang, W. Convolutional Neural Network-Based Travel Mode Recognition Based on Multiple Smartphone Sensors. Appl. Sci. 2022, 12, 6511. https://doi.org/10.3390/app12136511
Guo L, Huang J, Ma W, Sun L, Zhou L, Pan J, Yang W. Convolutional Neural Network-Based Travel Mode Recognition Based on Multiple Smartphone Sensors. Applied Sciences. 2022; 12(13):6511. https://doi.org/10.3390/app12136511
Chicago/Turabian StyleGuo, Lin, Jincai Huang, Wei Ma, Longzhi Sun, Lianjie Zhou, Jianping Pan, and Wentao Yang. 2022. "Convolutional Neural Network-Based Travel Mode Recognition Based on Multiple Smartphone Sensors" Applied Sciences 12, no. 13: 6511. https://doi.org/10.3390/app12136511
APA StyleGuo, L., Huang, J., Ma, W., Sun, L., Zhou, L., Pan, J., & Yang, W. (2022). Convolutional Neural Network-Based Travel Mode Recognition Based on Multiple Smartphone Sensors. Applied Sciences, 12(13), 6511. https://doi.org/10.3390/app12136511