research-article

Public Access

Meta-learning over time for destination prediction tasks

Authors:

Zeeshan Rasheed,

Khurram Shafique, and

Nuno VasconcelosAuthors Info & Claims

SIGSPATIAL '22: Proceedings of the 30th International Conference on Advances in Geographic Information Systems

November 2022

Article No.: 45, Pages 1 - 10

https://doi.org/10.1145/3557915.3560980

Published: 22 November 2022 Publication History

Abstract

A need to understand and predict vehicles' behavior underlies both public and private goals in the transportation domain, including urban planning and management, ride-sharing services, and intelligent transportation systems. Individuals' preferences and intended destinations vary throughout the day, week, and year: for example, bars are most popular in the evenings, and beaches are most popular in the summer. Despite this principle, we note that recent studies on a popular benchmark dataset from Porto, Portugal have found, at best, only marginal improvements in predictive performance from incorporating temporal information. We propose an approach based on hypernetworks, a variant of meta-learning ("learning to learn") in which a neural network learns to change its own weights in response to an input. In our case, the weights responsible for destination prediction vary with the metadata, in particular the time, of the input trajectory. The time-conditioned weights notably improve the model's error relative to ablation studies and comparable prior work, and we confirm our hypothesis that knowledge of time should improve prediction of a vehicle's intended destination.

References

[1]

Sofiane Abbar, Rade Stanojevic, and Mohamed Mokbel. 2020. STAD: Spatio-temporal adjustment of traffic-oblivious travel-time estimation. In 2020 21st IEEE International Conference on Mobile Data Management (MDM). IEEE, 79--88.

[2]

Tal Altshuler, Yaniv Altshuler, Rachel Katoshevski, and Yoram Shiftan. 2019. Modeling and prediction of ride-sharing utilization dynamics. Journal of Advanced Transportation 2019 (2019).

[3]

Theodoros Anagnostopoulos. 2021. A Predictive Vehicle Ride Sharing Recommendation System for Smart Cities Commuting. Smart Cities 4, 1 (2021), 177--191.

[4]

Lorenzo Bracciale, Marco Bonola, Pierpaolo Loreti, Giuseppe Bianchi, Raul Amici, and Antonello Rabuffi. 2014. CRAWDAD dataset roma/taxi (v. 2014-07-17). Downloaded from https://crawdad.org/roma/taxi/20140717.

[5]

Oscar Chang, Lampros Flokas, and Hod Lipson. 2019. Principled weight initialization for hypernetworks. In International Conference on Learning Representations.

[6]

Soumi Das, Rajath Nandan Kalava, Kolli Kiran Kumar, Akhil Kandregula, Kalpam Suhaas, Sourangshu Bhattacharya, and Niloy Ganguly. 2019. Map enhanced route travel time prediction using deep neural networks. arXiv preprint arXiv:1911.02623 (2019).

[7]

Alexandre De Brébisson, Étienne Simon, Alex Auvolat, Pascal Vincent, and Yoshua Bengio. 2015. Artificial neural networks applied to taxi destination prediction. In Proceedings of the 2015th International Conference on ECML PKDD Discovery Challenge-Volume 1526. 40--51.

[8]

Ruizhi Deng, Yanshuai Cao, Bo Chang, Leonid Sigal, Greg Mori, and Marcus A Brubaker. 2020. Variational Hyper RNN for Sequence Modeling. arXiv preprint arXiv:2002.10501 (2020).

[9]

Patrick Ebel, Ibrahim Emre Göl, Christoph Lingenfelder, and Andreas Vogelsang. 2020. Destination prediction based on partial trajectory data. In 2020 IEEE Intelligent Vehicles Symposium (IV). IEEE, 1149--1155.

[10]

Yuki Endo, Kyosuke Nishida, Hiroyuki Toda, and Hiroshi Sawada. 2017. Predicting destinations from partial trajectories using recurrent neural network. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 160--172.

[11]

Flickr user "Deensel" at https://www.flickr.com/people/158619309@N03. 2017. Porto City Hall. https://www.flickr.com/photos/deensel/36248265634/ under Creative Commons Attribution 2.0 Generic License (CC BY 2.0).

[12]

Jorge Franganillo. 2017. Porto: Sè do Porto. https://www.flickr.com/photos/franganillo/36934656926/ under Creative Commons Attribution 2.0 Generic License (CC BY 2.0).

[13]

Tao-yang Fu and Wang-Chien Lee. 2019. DeepIST: Deep image-based spatio-temporal network for travel time estimation. In Proceedings of the 28th ACM International Conference on Information and Knowledge Management. 69--78.

[14]

Tomer Galanti and Lior Wolf. 2020. On the modularity of hypernetworks. Advances in Neural Information Processing Systems 33 (2020).

[15]

Geolink. 2015. Taxi Service Trajectory (TST) Prediction Challenge @ ECML/PKDD 2015. https://web.archive.org/web/20150715062001/http://www.geolink.pt/ecmlpkdd2015-challenge/dataset.html.

[16]

Bharat Gupta, Shivam Awasthi, Rudraksha Gupta, Likhama Ram, Pramod Kumar, Bakshi Rohit Prasad, and Sonali Agarwal. 2018. Taxi travel time prediction using ensemble-based random forest and gradient boosting model. In Advances in Big Data and Cloud Computing. Springer, 63--78.

[17]

David Ha, Andrew Dai, and Quoc V Le. 2017. Hypernetworks. International Conference of Learning Representations (2017).

[18]

Thomas Hoch. 2015. An Ensemble Learning Approach for the Kaggle Taxi Travel Time Prediction Challenge. In DC@ PKDD/ECML.

[19]

Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780.

Digital Library

[20]

John M Irvine, Laura Mariano, and Teal Guidici. 2018. Normalcy modeling using a dictionary of activities learned from motion imagery tracking data. In 2018 IEEE Applied Imagery Pattern Recognition Workshop (AIPR). IEEE, 1--9.

[21]

Siddhant M Jayakumar, Wojciech M Czarnecki, Jacob Menick, Jonathan Schwarz, Jack Rae, Simon Osindero, Yee Whye Teh, Tim Harley, and Razvan Pascanu. 2020. Multiplicative interactions and where to find them. In International Conference on Learning Representations.

[22]

Shaoxiong Ji and Pekka Marttinen. 2021. Patient Outcome and Zero-shot Diagnosis Prediction with Hypernetwork-guided Multitask Learning. arXiv preprint arXiv:2109.03062 (2021).

[23]

Renhe Jiang, Zhaonan Wang, Zekun Cai, Chuang Yang, Zipei Fan, Tianqi Xia, Go Matsubara, Hiroto Mizuseki, Xuan Song, and Ryosuke Shibasaki. 2021. Countrywide Origin-Destination Matrix Prediction and Its Application for COVID-19. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, 319--334.

Digital Library

[24]

Kevin R Keane. 2017. Detecting motion anomalies. In Proceedings of the 8th ACM SIGSPATIAL Workshop on GeoStreaming. 21--28.

Digital Library

[25]

David Krueger, Chin-Wei Huang, Riashat Islam, Ryan Turner, Alexandre Lacoste, and Aaron Courville. 2017. Bayesian hypernetworks. arXiv preprint arXiv:1710.04759 (2017).

[26]

John Krumm and Eric Horvitz. 2006. Predestination: Inferring destinations from partial trajectories. In International Conference on Ubiquitous Computing. Springer, 243--260.

Digital Library

[27]

Hoang Thanh Lam. 2016. A concise summary of spatial anomalies and its application in efficient real-time driving behaviour monitoring. In Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 1--9.

Digital Library

[28]

Hoang Thanh Lam, Ernesto Diaz-Aviles, Alessandra Pascale, Yiannis Gkoufas, and Bei Chen. 2015. (Blue) taxi destination and trip time prediction from partial trajectories. In Proceedings of the 2015th International Conference on ECML PKDD Discovery Challenge-Volume 1526. 63--74.

Digital Library

[29]

Wuwei Lan, Yanyan Xu, and Bin Zhao. 2019. Travel time estimation without road networks: an urban morphological layout representation approach. In Proceedings of the 28th International Joint Conference on Artificial Intelligence. 1772--1778.

[30]

Yassine Lassoued, Julien Monteil, Yingqi Gu, Giovanni Russo, Robert Shorten, and Martin Mevissen. 2017. A hidden Markov model for route and destination prediction. In 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC). IEEE, 1--6.

Digital Library

[31]

Tai Le Quy, Wolfgang Nejdl, Myra Spiliopoulou, and Eirini Ntoutsi. 2019. A neighborhood-augmented LSTM model for taxi-passenger demand prediction. In International Workshop on Multiple-Aspect Analysis of Semantic Trajectories. Springer, 100--116.

Digital Library

[32]

Xiang Li, Mengting Li, Yue-Jiao Gong, Xing-Lin Zhang, and Jian Yin. 2016. T-DesP: Destination prediction based on big trajectory data. IEEE Transactions on Intelligent Transportation Systems 17, 8 (2016), 2344--2354.

Digital Library

[33]

Yadong Li, Bailong Liu, Lei Zhang, Susong Yang, Changxing Shao, and Dan Son. 2020. Fast Trajectory Prediction Method With Attention Enhanced SRU. IEEE Access 8 (2020), 206614--206621.

[34]

Chengwu Liao, Chao Chen, Chaocan Xiang, Hongyu Huang, Hong Xie, and Songtao Guo. 2021. Taxi-Passenger's Destination Prediction via GPS Embedding and Attention-Based BiLSTM Model. IEEE Transactions on Intelligent Transportation Systems (2021).

[35]

Yiding Liu, Kaiqi Zhao, Gao Cong, and Zhifeng Bao. 2020. Online anomalous trajectory detection with deep generative sequence modeling. In 2020 IEEE 36th International Conference on Data Engineering (ICDE). IEEE, 949--960.

[36]

Jianming Lv, Qing Li, Qinghui Sun, and Xintong Wang. 2018. T-CONV: A convolutional neural network for multi-scale taxi trajectory prediction. In 2018 IEEE international conference on big data and smart computing (bigcomp). IEEE, 82--89.

[37]

Rabeeh Karimi Mahabadi, Sebastian Ruder, Mostafa Dehghani, and James Henderson. 2021. Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. arXiv preprint arXiv:2106.04489 (2021).

[38]

Christian Manasseh and Raja Sengupta. 2013. Predicting driver destination using machine learning techniques. In 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013). IEEE, 142--147.

[39]

Tiago Miranda. 2014. CP 3400 - Porto Campanhã. https://www.flickr.com/photos/tiago_miranda94/14277888315/ under Creative Commons Attribution 2.0 Generic License (CC BY 2.0).

[40]

Eduardo Moratinos. 2005. Casa da musica - llegaron los marcianos. https://commons.wikimedia.org/wiki/File:Casa_da_Musica_3_(Porto).jpg under Creative Commons Attribution 2.0 Generic License (CC BY 2.0).

[41]

Luis Moreira-Matias, Joao Gama, Michel Ferreira, Joao Mendes-Moreira, and Luis Damas. 2013. Predicting taxi-passenger demand using streaming data. IEEE Transactions on Intelligent Transportation Systems 14, 3 (2013), 1393--1402.

Digital Library

[42]

Francisco Dantas Nobre Neto, Cláudio de Souza Baptista, and Claudio EC Campelo. 2018. Combining Markov model and prediction by partial matching compression technique for route and destination prediction. Knowledge-Based Systems 154 (2018), 81--92.

Digital Library

[43]

NYC Taxi & Limousine Commission. n.d. TLC Trip Record Data. https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page.

[44]

Philip Pecher, Michael Hunter, and Richard Fujimoto. 2016. Data-driven vehicle trajectory prediction. In Proceedings of the 2016 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation. 13--22.

Digital Library

[45]

Michal Piorkowski, Natasa Sarafijanovic-Djukic, and Matthias Grossglauser. 2009. CRAWDAD dataset epfl/mobility (v. 2009-02-24). Downloaded from https://crawdad.org/epfl/mobility/20090224.

[46]

Pedro Rodrigues, Ana Martins, Sofia Kalakou, and Filipe Moura. 2020. Spatiotemporal variation of taxi demand. Transportation Research Procedia 47 (2020), 664--671.

[47]

Alberto Rossi, Gianni Barlacchi, Monica Bianchini, and Bruno Lepri. 2019. Modelling taxi drivers' behaviour for the next destination prediction. IEEE Transactions on Intelligent Transportation Systems 21, 7 (2019), 2980--2989.

Digital Library

[48]

Amal Saadallah, Luis Moreira-Matias, Ricardo Sousa, Jihed Khiari, Erik Jenelius, and Joao Gama. 2018. BRIGHT---drift-aware demand predictions for taxi networks. IEEE Transactions on Knowledge and Data Engineering 32, 2 (2018), 234--245.

Digital Library

[49]

Tim Salimans and Durk P Kingma. 2016. Weight normalization: A simple reparameterization to accelerate training of deep neural networks. Advances in neural information processing systems 29 (2016).

[50]

Elad Sarafian, Shai Keynan, and Sarit Kraus. 2021. Recomposing the Reinforcement Learning Building Blocks with Hypernetworks. In International Conference on Machine Learning. PMLR, 9301--9312.

[51]

Falong Shen, Shuicheng Yan, and Gang Zeng. 2018. Neural style transfer via meta networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8061--8069.

[52]

Reid Simmons, Brett Browning, Yilu Zhang, and Varsha Sadekar. 2006. Learning to predict driver route and destination intent. In 2006 IEEE Intelligent Transportation Systems Conference. IEEE, 127--132.

[53]

Li Song, Ruijia Wang, Ding Xiao, Xiaotian Han, Yanan Cai, and Chuan Shi. 2018. Anomalous trajectory detection using recurrent neural network. In International Conference on Advanced Data Mining and Applications. Springer, 263--277.

[54]

Jinjun Tang, Jian Liang, Tianjian Yu, Yong Xiong, and Guoliang Zeng. 2021. Trip destination prediction based on a deep integration network by fusing multiple features from taxi trajectories. IET Intelligent Transport Systems 15, 9 (2021), 1131--1141.

[55]

Athanasios Tsiligkaridis, Jing Zhang, Hiroshi Taguchi, and Daniel Nikovski. 2020. Personalized destination prediction using transformers in a contextless data setting. In 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, 1--7.

[56]

Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research 9, 11 (2008).

[57]

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017).

[58]

Johannes von Oswald, Christian Henning, João Sacramento, and Benjamin F Grewe. 2020. Continual learning with hypernetworks. International Conference on Learning Representations (2020).

[59]

Ruohan Wang, Pierluigi V Amadori, and Yiannis Demiris. 2018. Real-time workload classification during driving using hypernetworks. In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 3060--3065.

Digital Library

[60]

Wei Wang, Xiaofeng Zhao, Zhiguo Gong, Zhikui Chen, Ning Zhang, and Wei Wei. 2020. An attention-based deep learning framework for trip destination prediction of sharing bike. IEEE Transactions on Intelligent Transportation Systems 22, 7 (2020), 4601--4610.

Digital Library

[61]

Zhu Xiao, Shenyuan Xu, Tao Li, Hongbo Jiang, Rui Zhang, Amelia C Regan, and Hongyang Chen. 2020. On extracting regular travel behavior of private cars based on trajectory data analysis. IEEE Transactions on Vehicular Technology 69, 12 (2020), 14537--14549.

[62]

Andy Yuan Xue, Jianzhong Qi, Xing Xie, Rui Zhang, Jin Huang, and Yuan Li. 2015. Solving the data sparsity problem in destination prediction. The VLDB Journal 24, 2 (2015), 219--243.

Digital Library

[63]

Jing Yuan, Yu Zheng, Chengyang Zhang, Wenlei Xie, Xing Xie, Guangzhong Sun, and Yan Huang. 2010. T-Drive: Driving Directions Based on Taxi Trajectories. In Proceedings of 18th ACM SIGSPATIAL Conference on Advances in Geographical Information Systems (proceedings of 18th acm sigspatial conference on advances in geographical information systems ed.). ACM SIGSPATIAL GIS 2010. https://www.microsoft.com/en-us/research/publication/t-drive-driving-directions-based-on-taxi-trajectories/ Best Paper Award.

[64]

Lei Zhang, Guoxing Zhang, Zhizheng Liang, and Ekene Frank Ozioko. 2018. Multi-features taxi destination prediction with frequency domain processing. PloS one 13, 3 (2018), e0194629.

[65]

Xiaocai Zhang, Zhixun Zhao, Yi Zheng, and Jinyan Li. 2019. Prediction of taxi destinations using a novel data embedding method and ensemble learning. IEEE Transactions on Intelligent Transportation Systems 21, 1 (2019), 68--78.

[66]

Bing Zhao, Yon Shin Teo, Wee Siong Ng, and Hai Heng Ng. 2019. Data-driven next destination prediction and ETA improvement for urban delivery fleets. IET Intelligent Transport Systems 13, 11 (2019), 1624--1635.

[67]

Guanjie Zheng, Chang Liu, Hua Wei, Chacha Chen, and Zhenhui Li. 2021. Rebuilding city-wide traffic origin destination from road speed data. In 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 301--312.

Cited By

Wang YJin SYang ZGuan HRen YCheng KZhao XLiu XChen MLiu YGuo Q(2024)TTSR: A Transformer-Based Topography Neural Network for Digital Elevation Model Super-ResolutionIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.336048962(1-19)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3360489
Graser AJalali ALampert JWeißenfeld AJanowicz K(2024)MobilityDL: a review of deep learning from trajectory dataGeoInformatica10.1007/s10707-024-00518-8Online publication date: 28-May-2024
https://doi.org/10.1007/s10707-024-00518-8
Mai GHu YGao SCai LMartins BScholz JGao JJanowicz K(2022) Symbolic and subsymbolic GeoAI : Geospatial knowledge graphs and spatially explicit machine learning Transactions in GIS10.1111/tgis.1301226:8(3118-3124)Online publication date: 18-Dec-2022
https://doi.org/10.1111/tgis.13012

Index Terms

Meta-learning over time for destination prediction tasks

Recommendations

From destination prediction to route prediction

A prediction of a vehicle's route would be useful for giving the driver advance warnings and alerts about upcoming situations and opportunities. This paper presents a new algorithm for predicting a driver's route based on a probabilistic prediction of ...
Read More
Data-Driven Vehicle Trajectory Prediction
SIGSIM-PADS '16: Proceedings of the 2016 ACM SIGSIM Conference on Principles of Advanced Discrete Simulation

Vehicle trajectory or route prediction is useful in online, data-driven transportation simulation to predict future traffic patterns and congestion, among other uses. The various approaches to route prediction have varying degrees of data required to ...
Read More
Cluster-Based Destination Prediction in Bike Sharing System
AICCC '18: Proceedings of the 2018 Artificial Intelligence and Cloud Computing Conference

Destination prediction not only helps to understand users' behavior, but also provides basic information for destination-related customized service. This paper studies the destination prediction in the public bike sharing system, which is now blooming ...
Read More

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SIGSPATIAL '22: Proceedings of the 30th International Conference on Advances in Geographic Information Systems

November 2022

806 pages

ISBN:9781450395298

DOI:10.1145/3557915

General Chairs:
Matthias Renz
Kiel University, Germany
,
Mohamed Sarwat
Wherobots Inc. / Arizona State University

Copyright © 2022 ACM.

Publication rights licensed to ACM. ACM acknowledges that this contribution was authored or co-authored by an employee, contractor or affiliate of the United States government. As such, the Government retains a nonexclusive, royalty-free right to publish or reproduce this article, or to allow others to do so, for Government purposes only.

Sponsors

SIGSPATIAL: ACM Special Interest Group on Spatial Information

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 November 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Defense Advanced Research Projects Agency

Conference

SIGSPATIAL '22

Sponsor:

SIGSPATIAL

SIGSPATIAL '22: The 30th International Conference on Advances in Geographic Information Systems

November 1 - 4, 2022

Washington, Seattle

Acceptance Rates

Overall Acceptance Rate 220 of 1,116 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
217
Total Downloads

Downloads (Last 12 months)111
Downloads (Last 6 weeks)7

Other Metrics

View Author Metrics

Citations

Cited By

Wang YJin SYang ZGuan HRen YCheng KZhao XLiu XChen MLiu YGuo Q(2024)TTSR: A Transformer-Based Topography Neural Network for Digital Elevation Model Super-ResolutionIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.336048962(1-19)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3360489
Graser AJalali ALampert JWeißenfeld AJanowicz K(2024)MobilityDL: a review of deep learning from trajectory dataGeoInformatica10.1007/s10707-024-00518-8Online publication date: 28-May-2024
https://doi.org/10.1007/s10707-024-00518-8
Mai GHu YGao SCai LMartins BScholz JGao JJanowicz K(2022) Symbolic and subsymbolic GeoAI : Geospatial knowledge graphs and spatially explicit machine learning Transactions in GIS10.1111/tgis.1301226:8(3118-3124)Online publication date: 18-Dec-2022
https://doi.org/10.1111/tgis.13012

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents