GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism

GPS datasets in the big data regime provide rich contextual information that enable efficient implementation of advanced features such as navigation, tracking, and security in urban computing systems. Understanding the hidden patterns in large amount of GPS data is critically important in ubiquitous computing. The quality of GPS data is the fundamental key problem to produce high quality results. In real world applications, certain GPS trajectories are sparse and incomplete; this increases the complexity of inference algorithms. Few of existing studies have tried to address this problem using complicated algorithms that are based on conventional heuristics; this requires extensive domain knowledge of underlying applications. Our contribution in this paper are two-fold. First, we proposed deep learning based bidirectional convolutional recurrent encoder-decoder architecture to generate the missing points of GPS trajectories over occupancy grid-map. Second, we interfaced attention mechanism between enconder and decoder, that further enhance the performance of our model. We have performed the experiments on widely used Microsoft geolife trajectory dataset, and perform the experiments over multiple level of grid resolutions and multiple lengths of missing GPS segments. Our proposed model achieved better results in terms of average displacement error as compared to the state-of-the-art benchmark methods.

[1]  Xing Xie,et al.  GeoLife: A Collaborative Social Networking Service among User, Location and Trajectory , 2010, IEEE Data Eng. Bull..

[2]  Huang Zhiqiu,et al.  Mode Inference using enhanced Segmentation and Pre-processing on raw Global Positioning System data , 2020, Measurement and Control.

[3]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[4]  Joshua Greenfeld,et al.  A method for constructing 3D traveling routes from GPS navigation data , 2012, IWGS '12.

[5]  Zhoujun Li,et al.  Estimating Urban Traffic Congestions with Multi-sourced Data , 2016, 2016 17th IEEE International Conference on Mobile Data Management (MDM).

[6]  Hanghang Tong,et al.  Activity recognition with smartphone sensors , 2014 .

[7]  R.M. Alkan,et al.  GPS, GALILEO and GLONASS satellite navigation systems & GPS modernization , 2005, Proceedings of 2nd International Conference on Recent Advances in Space Technologies, 2005. RAST 2005..

[8]  Ahmad Asadi,et al.  The Encoder-Decoder Framework and Its Applications , 2019, Deep Learning: Concepts and Architectures.

[9]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[10]  Zhitao Huang,et al.  A System of Mining Semantic Trajectory Patterns from GPS Data of Real Users , 2019, Symmetry.

[11]  Syed Aziz Shah,et al.  Utilizing a 5G spectrum for health care to detect the tremors and breathing activity for multiple sclerosis , 2018, Trans. Emerg. Telecommun. Technol..

[12]  Alexandre M. Bayen,et al.  The Path Inference Filter: Model-Based Low-Latency Map Matching of Probe Vehicle Data , 2011, IEEE Transactions on Intelligent Transportation Systems.

[13]  Xing Xie,et al.  Reducing Uncertainty of Low-Sampling-Rate Trajectories , 2012, 2012 IEEE 28th International Conference on Data Engineering.

[14]  Philip S. Yu,et al.  Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classification , 2019, IEEE Transactions on Knowledge and Data Engineering.

[15]  Leonidas J. Guibas,et al.  Large-scale joint map matching of GPS traces , 2013, SIGSPATIAL/GIS.

[16]  Zhoujun Li,et al.  DTRP: A Flexible Deep Framework for Travel Route Planning , 2017, WISE.

[17]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[18]  Gao Cong,et al.  An Experimental Evaluation of Point-of-interest Recommendation in Location-based Social Networks , 2017, Proc. VLDB Endow..

[19]  Syed Aziz Shah,et al.  Cognitive health care system and its application in pill‐rolling assessment , 2019, International Journal of Numerical Modelling: Electronic Networks, Devices and Fields.

[20]  Jiannong Cao,et al.  TrafficGAN: Network-Scale Deep Traffic Prediction With Generative Adversarial Nets , 2019, IEEE Transactions on Intelligent Transportation Systems.

[21]  Xing Xie,et al.  Learning transportation mode from raw gps data for geographic applications on the web , 2008, WWW.

[22]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Jianhua Wang,et al.  An Enhanced Transportation Mode Detection Method Based on GPS Data , 2017, ICPCSEE.

[24]  Syed Aziz Shah,et al.  Seizure episodes detection via smart medical sensing system , 2018, J. Ambient Intell. Humaniz. Comput..

[25]  Xing Xie,et al.  Mining interesting locations and travel sequences from GPS trajectories , 2009, WWW '09.

[26]  Leonidas J. Guibas,et al.  Knowledge-based trajectory completion from sparse GPS samples , 2016, SIGSPATIAL/GIS.

[27]  Hao Wang,et al.  Detecting Transportation Modes Using Deep Neural Network , 2017, IEICE Trans. Inf. Syst..

[28]  Wang Senzhang,et al.  Convolutional LSTM based transportation mode learning from raw GPS trajectories , 2020 .

[29]  Qingquan Li,et al.  A Review of GPS Trajectories Classification Based on Transportation Mode , 2018, Sensors.

[30]  Zhen Li,et al.  High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[31]  Shaohe Lv,et al.  End-to-End Mandarin Speech Recognition Combining CNN and BLSTM , 2019, Symmetry.

[32]  Yu Zheng,et al.  Trajectory Data Mining , 2015, ACM Trans. Intell. Syst. Technol..

[33]  Syed Aziz Shah,et al.  Impact of Relay Location of STANC Bi-Directional Transmission for Future Autonomous Internet of Things Applications , 2020, IEEE Access.

[34]  Mauro Femminella,et al.  A Zero-Configuration Tracking System for First Responders Networks , 2017, IEEE Systems Journal.

[35]  Wei-Ying Ma,et al.  Understanding mobility based on GPS data , 2008, UbiComp.

[36]  Philip S. Yu,et al.  Enhancing Traffic Congestion Estimation with Social Media by Coupled Hidden Markov Model , 2016, ECML/PKDD.

[37]  Syed Aziz Shah,et al.  Radar for Health Care: Recognizing Human Activities and Monitoring Vital Signs , 2019, IEEE Potentials.

[38]  Philip S. Yu,et al.  Deep Learning for Spatio-Temporal Data Mining: A Survey , 2019, IEEE Transactions on Knowledge and Data Engineering.

[39]  Md Zakirul Alam Bhuiyan,et al.  Deep Irregular Convolutional Residual LSTM for Urban Traffic Passenger Flows Prediction , 2020, IEEE Transactions on Intelligent Transportation Systems.

[40]  Chung Choo Chung,et al.  Probabilistic vehicle trajectory prediction over occupancy grid map via recurrent neural network , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[41]  Xiaoming Zhang,et al.  Computing Urban Traffic Congestions by Incorporating Sparse GPS Probe Data and Social Media Data , 2017, ACM Trans. Inf. Syst..

[42]  Yu Zheng,et al.  Constructing popular routes from uncertain trajectories , 2012, KDD.

[43]  Zhoujun Li,et al.  Citywide traffic congestion estimation with social media , 2015, SIGSPATIAL/GIS.

[44]  Kevin Heaslip,et al.  Inferring transportation modes from GPS trajectories using a convolutional neural network , 2018, ArXiv.

[45]  Yu Zheng Urban computing: enabling urban intelligence with big data , 2016, Frontiers of Computer Science.

[46]  Jiannong Cao,et al.  GCGAN: Generative Adversarial Nets with Graph CNN for Network-Scale Traffic Prediction , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[47]  Guicheng Shen,et al.  An Area-Based Method for Missing Trajectory Completion: A STZ Algorithm , 2015, 2015 8th International Symposium on Computational Intelligence and Design (ISCID).

[48]  Philip S. Yu,et al.  Efficient Traffic Estimation With Multi-Sourced Data by Parallel Coupled Hidden Markov Model , 2019, IEEE Transactions on Intelligent Transportation Systems.

[49]  Ryan M. Gibson,et al.  WiFreeze: Multiresolution Scalograms for Freezing of Gait Detection in Parkinson’s Leveraging 5G Spectrum with Deep Learning , 2019, Electronics.