Classifying transportation mode and speed from trajectory data via deep multi-scale learning
Introduction
Nowadays, population explosion has brought many problems to urban traffic management. The growing international trade activities are intensifying port congestion. Identifying and understanding the mobility of moving objects in cities and waters are helpful for managing traffic and meeting peopleâs traveling needs. For example, if we know that taxis are passing quickly on a certain road at a certain time, then we can choose appropriate means of traveling. Moreover, we can infer that the traffic on that road is smooth. Classifying transportation mode is an important method to uncover mobility of moving objects [1] or suspicious vehicle trajectories [2]. Because speed category mining can be seemed as a sub-question of transportation mode classification, this paper will focus on classifying transportation mode and speed. Accurate classification results can ensure that the mobility of moving objects mined from trajectory data is reliable and practical.
Our goal is to classify transportation modes and speed, help people understand the mobility of moving objects, thus making people’s life more convenient and traffic management easier. For instance, given a trajectory dataset in a region and a period, we use trajectory classifier to classify transportation modes and speed of the trajectory dataset. By Summarizing the classification results, we can infer that the objects of the trajectory dataset move at which speed in the region and the period, and can also further understand the traffic conditions.
Although there are some studies on trajectory classification, they mainly focus on the classification of transportation modes, and we want to classify transportation modes and speed at the same time, which can uncover the mobility of moving objects at different time and space granularities. Besides that, they are unsuitable for our tasks because none of them can meet the following two requirements at the same time:
- (1)
Extracting features automatically. Traditional machine learning algorithms for trajectory classification normally require feature engineering to extract features, such as motion parameters (speed, direction, accelerated speed) [1], [3], region-based and trajectory-based features [2]. For example, Zhang et. al. classify a trajectory into several traffic modes, compute feature values for each trajectory segment, and finally input these values into decision trees, SVMs, Bayesian networks and conditional random fields [1], [3]. Lee et. al. present a framework for frequent sequential pattern-based classification for trajectories on road networks, while frequent sequential patterns mean frequent combined features composed of single features which are traversed by at least one trajectory [4]. The mentioned above trajectory classification algorithms rely heavily on manual feature selection and cannot work automatically.
- (2)
Extracting features comprehensively. Some researchers use deep neural networks to automatically extract features for trajectory classification [5]. Endo et. al. map trajectories into grids, where each grid value indicates the time that the trajectory stays in this grid. Then, they convert the grids into vectors and obtain feature values through DNN. Finally, the feature values and the extracted mobility features are combined into new features which are fed to classifiers for classification [5]. However, their research only classifies transportation modes and fails to describe trajectories from the angles of moving object and speed. Although the mentioned above trajectory classification algorithms based on deep neural networks take into account the impact of space, yet they ignore the impact of time attributes on classification results. Moreover, as the input data to the DNN model is vector data, it is difficult to fully extract local spatial features. Hence, their classification results are less accurate.
To solve these problems, we propose Deep Multi-Scale Learning Model. We first map trajectory data onto girds and then design models for classification. Since trajectory data is mapped onto grids, there is no need to extract features through complex feature engineering. Furthermore, the error of features caused by trajectory point bias can be reduced. Then, we design a deep neural network to automatically learn features so as to fully automate the whole model. Inspired by attention mechanism [6] and the latest network structure [7], [8], [9], [10], [11], [12], [13], we design a Attention Dense Module by integrating attention mechanism, DenseNet [14] and residual learning [15]. Attention mechanism is able to capture long-term dependence and select some major features. The network structure of DenseNet is able to capture local features and spatial features and enhance the propagation of features throughout the network. Consequently, fewer network structure parameters are needed. Residual learning can enable the network to be as deep as possible. Besides, as the original trajectory data is mapped into grid data, different time granularities and space granularities will make difference in grid data, thus influencing classification results. Therefore, we build models for grid data under different time and space granularities, respectively. Finally, we fuse the feature representations outputted by the model as final classification results.
After training and optimizing the model, input the pre-processed real-time trajectory data, and we can get the corresponding transportation mode and speed category. The classification result is summarized, and it is possible to infer at what speed a particular type of moving object is traveling within a certain period in a given area. For example, given an area and a period, we obtain the classification results that a large number of taxis travel at high speed, it can be inferred that the road section is not congested. Therefore, the summary analysis based on the classification results of the model output can answer the questions related to traffic management. for example, (1) How different is the speed of several moving objects in the same location at the same time? (2) In different locations and at different times, what is the speed of the same type of moving objects? (3) With the speed of a given type of moving objects, can we find the time and location where this condition frequently happens? If the output classification results from our model can answer these questions, then it would be helpful for traffic management and personal travels. For instance, our model may be used to predict the time and location of bus congestion. By using this information, we can plan new bus routes and timetables so that the bus transportation system can be more efficient. Our model may be used to determine the speed of taxis in a certain region at a certain time so as help drivers choose a less congested route.
Our contributions are as follows:
- •
We design Attention Dense Module (ADM) by integrating attention mechanism and DenseNet structure. By stacking ADM modules, we can augment the propagation of features throughout the network and reduce the number of network parameters.
- •
We propose Deep Multi-Scale Learning Model that can model grid data under different space and time granularities as to fully capture the impact of time and space on classification results.
- •
We have evaluated our proposed model on two real datasets (Geolife and Ningbo AIS data). Results show that our model surpasses the currently advanced models in top-1 accuracy, recall and f1-score.
The rest of this paper is organized as follows. Section 2 gives definitions and describes our model. Section 3 presents the details of our model. Section 4, several experiments are conducted on real data with our model. Section 5 reviews the related work. Finally Section 6 concludes the whole paper.
Section snippets
Deep multi-scale learning model
Our proposed Deep Multi-Scale Learning Model is used to classify trajectories and output the moving object and its speed. As the input of our model is grid data, we need to convert original trajectory data to grid data. Since grid data under different time and space granularities have influence on classification results, we build a multi-scale model. Multi-scale means that our model is based on different temporal and spatial scale. The upper model deals with grid data with smaller spatial
Network structure
As Model Training Module shown in Fig. 1, our Deep Multi-Scale Learning Model is made of two parts to capture the impact of different space granularities on classification results. As the input to each part contains different time granularities, our model can also capture the impact of time on classification results. The whole model can be divided into four blocks, including shallow feature extraction block (SFEB), attention dense block (ADB), transition block (TB), and fusion block (FB). We
Experiments
In this section, we will use Geolife and Ningbo AIS data to evaluate the effectiveness of our automatic feature extraction and classification results. First, we compare our classification results with the latest network structures, including DenseNet, ResNet and their variant networks. The classification metrics include accuracy, precision, recall and f1-score. Then, under the same network structure, we analyze the classification results generated by single-scale and multi-scale models. For
Trajectory data mining
Over the past years, many trajectory data mining methods have been proposed, such as mobility pattern discovery, trajectory classification and traffic flow predication. As for mobility pattern discovery, Zheng et al. understand the mobility by inferring and classifying transportation modes [1]. Song et al. use DeepTransport to automatically simulate or predict the future movements of people and their transportation modes in large transportation networks, in order to explore and analyze people’s
Conclusion
In this paper, we propose Deep Multi-Scale Learning Model for trajectory classification and understand the mobility of moving objects based on classification results. Our model adopts the basic structure of DenseNet and introduces attention mechanism and residual learning. It is able to strengthen feature propagation and fusion, reduce the gradient vanishing problem and boost network performance. Furthermore, we enrich our network structure from multi-scale angle so that our model is able to
Conflict of interest
The authors declare that there is no conflict of interests regarding the publication of this article.
Acknowledgments
This work was supported in part by the National Natural Science Foundation of China under Grants 61872416, 51879210, 61671216, 61871436, 51479159, 51879210, 61702204 and 61872415; by the Fundamental Research Funds for the Central Universities of China under Grant 2019kfyXJJS017, 2722019PY052; and by the fund of Hubei Key Laboratory of Transportation Internet of Things under Grant 2018IOT004.
Rui Zhang is an Associate Professor in School of Computer Science and Technology at Wuhan University of Technology, China. She received the M.S. degree and Ph.D. degree in Computer Science from Huazhong University of Science and Technology, China. From 2013 to 2014, she was a Visiting Scholar with the School of Computer Science, Georgia Institute of Technology, USA. Her research interests include network analysis, mobile computing and data mining.
References (37)
- et al.
Dual path networks
Conference on Neural Information Processing Systems, NIPS 2017
(2017) - et al.
Wide residual networks
Proceedings of the British Machine Vision Conference 2016, BMVC 2016, York, UK, September 19–22, 2016
(2016) - et al.
Applying machine learning techniques to transportation mode recognition using mobile phone sensor data.
IEEE Trans. Intell. Transp. Syst.
(2015) - et al.
Dynamic routing between capsules
Advances in Neural Information Processing Systems
(2017) - et al.
Understanding mobility based on GPS data
Proceedings of the 10th International Conference on Ubiquitous Computing, UbiComp 2008
(2008) - et al.
Movemine:mining moving object databases
ACM SIGMOD International Conference on Management of Data, SIGMOD 2010, Indianapolis, Indiana, Usa, June
(2010) - et al.
Understanding transportation modes based on GPS data for web applications
ACM Trans. Web (TWEB)
(2010) - et al.
Mining discriminative patterns for classifying trajectories on road networks
IEEE Trans. Knowl. Data Eng.
(2011) - et al.
Deep feature extraction from trajectories for transportation mode estimation
Pacific-Asia Conference on Knowledge Discovery and Data Mining
(2016) - et al.
Self-attention generative adversarial networks
(2018)
Convolutional neural networks with alternately updated clique
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018
Residual attention network for image classification
2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21–26, 2017
Deep networks with stochastic depth
European Conference on Computer Vision, ECCV 2016
Illia: enabling k-anonymity-based privacy preserving against location injection attacks in continuous lbs queries
IEEE Internet Things J.
Multi-dimensional data indexing and range query processing via voronoi diagram for internet of things
Future Gener. Comput. Syst.
Residual dense network for image super-resolution
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018
Densely connected convolutional networks.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Deep residual learning for image recognition
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
Cited by (104)
PPDF-FedTMI: A Federated Learning-based Transport Mode Inference Model with Privacy-Preserving Data Fusion
2023, Simulation Modelling Practice and TheoryGenerating live commentary for marine traffic scenarios based on multi-model learning
2023, Computer CommunicationsA multi-stage fusion network for transportation mode identification with varied scale representation of GPS trajectories
2023, Transportation Research Part C: Emerging TechnologiesIdentifying the collaborative scheduling areas between ride-hailing and traditional taxi services based on vehicle trajectory data
2023, Journal of Transport GeographyA critical review of using Internet of Things technology for decarbonizing the shipping transportation industry in industrial revolution 4.0
2023, Recent Advancement of IoT Devices in Pollution Control and Health ApplicationsA deep learning approach for transportation mode identification using a transformation of GPS trajectory data features into an image representation
2024, International Journal of Data Science and Analytics
Rui Zhang is an Associate Professor in School of Computer Science and Technology at Wuhan University of Technology, China. She received the M.S. degree and Ph.D. degree in Computer Science from Huazhong University of Science and Technology, China. From 2013 to 2014, she was a Visiting Scholar with the School of Computer Science, Georgia Institute of Technology, USA. Her research interests include network analysis, mobile computing and data mining.
Peng Xie received the B.S. degree from Wuhan University of Science and Technology, China, in 2016. He is currently working toward the M.S. degree in Computer science and technology at Wuhan University of Technology, China. His research of interests are in the area of data mining and machine learning, especially deep learning in trajectory data mining.
Chen Wang received the B.S. and Ph.D. degrees from the Department of Automation, Wuhan University, China, in 2008 and 2013, respectively. From 2013 to 2017, he was a postdoctoral research fellow in the Networked and Communication Systems Research Lab, Huazhong University of Science and Technology, China. Thereafter, he joined the faculty of Huazhong University of Science and Technology where he is currently an associate professor. His research interests are in the broad areas of wireless networking, Internet of Things, and mobile computing, with a recent focus on privacy issues in wireless and mobile systems.
Gaoyang Liu received the B.S. degree of information engineering in 2015,and he is currently pursuing the Ph.D. degree at Huazhong University of Science and Technology, China. His research interests include mobile sensing and data privacy protection.
Shaohua Wan (SM'19) received his joint Ph.D degree from the School of Computer, Wuhan University, and the Department of Electrical Engineering and Computer Science, Northwestern University, USA, in 2010. Since 2015, he has been holding a post-doctoral position at the State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology. From 2016 to 2017, he was a visiting professor with the Department of Electrical and Computer Engineering, Technical University of Munich, Germany. He is currently an Associate Professor with the School of Information and Safety Engineering, Zhongnan University of Economics and Law. His main research interests include massive data computing for Internet of Things and edge computing.