short-paper

A Demonstration of KAMEL: A Scalable BERT-based System for Trajectory Imputation

Authors:

Mashaal Musleh,

Mohamed MokbelAuthors Info & Claims

SIGMOD '23: Companion of the 2023 International Conference on Management of Data

Pages 191 - 194

https://doi.org/10.1145/3555041.3589733

Published: 05 June 2023 Publication History

Abstract

This demo presents KAMEL; a novel trajectory imputation framework that aims to impute sparse trajectories as a means of increasing their accuracy, and hence the accuracy of their applications. Unlike the large majority of current trajectory imputation techniques, KAMEL does not require the knowledge or the availability of the underlying road network, which makes it applicable to important applications like map inference that need to infer the road network itself. Audience will experience KAMEL through various scenarios that show the imputation accuracy as well as KAMEL internals.

Supplemental Material

MP4 File

This demo presents KAMEL; a novel trajectory imputation framework that aims to impute sparse trajectories as a means of increasing their accuracy, and hence the accuracy of their applications. Unlike the large majority of current trajectory imputation techniques, KAMEL does not require the knowledge or the availability of the underlying road network, which makes it applicable to important applications like map inference that need to infer the road network itself. Audience will experience KAMEL through various scenarios that show the imputation accuracy as well as KAMEL internals.

Download
119.29 MB

References

[1]

S. Abbar, M. Alizadeh, F. Bastani, S. Chawla, S. He, H. Balakrishnan, and S. Madden. The Science of Algorithmic Map Inference (Tutorial). In KDD, 2018.

[2]

S. Brakatsoulas, D. Pfoser, R. Salas, and C. Wenk. On Map-Matching Vehicle Tracking Data. In VLDB, 2005.

Digital Library

[3]

I. Brodsky. H3: Uber's Hexagonal Hierarchical Spatial Index. https://eng.uber.com/h3/.

[4]

J. Devlin, M. Chang, K. Lee, and K. Toutanova. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR, abs/1810.04805, 2018.

[5]

M. M. Elshrif, K. Isufaj, and M. F. Mokbel. Network-less trajectory imputation. In SIGSPATIAL, 2022.

Digital Library

[6]

Y. Li, Y. Li, D. Gunopulos, and L. J. Guibas. Knowledge-based Trajectory Completion from Sparse GPS Samples. In SIGSPATIAL, 2016.

Digital Library

[7]

Mapillary. Unveiling the Mapping in Logistics Report: The Impact of Broken Maps on Last-Mile Deliveries. https://blog.mapillary.com/update/2020/02/14/mapping-in-logistics.html.

[8]

Discover New Roads with Bing Maps. https://blogs.bing.com/maps/2022--12/Bing-Maps-is-bringing-new-roads/.

[9]

M. Musleh, S. Abbar, R. Stanojevic, and M. F. Mokbel. QARTA: An ML-based System for Accurate Map Services. PVLDB, 14(11), 2021.

Digital Library

[10]

M. Musleh and M. F. Mokbel. RASED: A Scalable Dashboard for Monitoring Road Network Updates in OSM. In MDM, 2022.

[11]

M. Musleh, M. F. Mokbel, and S. Abbar. Let's Speak Trajectories. In SIGSPATIAL, pages 37:1--37:4, Seattle, WA, USA, Nov. 2022.

Digital Library

[12]

Taxi Service Trajectory. Prediction Challenge. ECML PKDD 2015. http://www.geolink.pt/ecmlpkdd2015-challenge/dataset.html.

[13]

S. Ruan, C. Long, J. Bao, C. Li, Z. Yu, R. Li, Y. Liang, T. He, and Y. Zheng. Learning to Generate Maps from Trajectories. In AAAI, 2020.

[14]

Traffic Technology Today. Poor maps costing delivery companies US $6bn annually. https://www.traffictechnologytoday.com/news/mapping/poor-maps-costing-delivery-companies-us6bn-annually.html.

[15]

K. Zheng, Y. Zheng, X. Xie, and X. Zhou. Reducing Uncertainty of Low-Sampling- Rate Trajectories. In ICDE, 2012.

Digital Library

Cited By

Musleh MMokbel M(2024)Let's Speak Trajectories: A Vision to Use NLP Models for Trajectory Analysis TasksACM Transactions on Spatial Algorithms and Systems10.1145/365647010:2(1-25)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1145/3656470
Mohammed HNascimento MBarbosa D(2024)Effective Trajectory Imputation using Simple Probabilistic Language Models2024 25th IEEE International Conference on Mobile Data Management (MDM)10.1109/MDM61037.2024.00027(51-60)Online publication date: 24-Jun-2024
https://doi.org/10.1109/MDM61037.2024.00027
Najjar A(2024)Pre-trained Transformer Uncovers Meaningful Patterns in Human Mobility Data2024 IEEE International Conference on Big Data (BigData)10.1109/BigData62323.2024.10825246(5819-5828)Online publication date: 15-Dec-2024
https://doi.org/10.1109/BigData62323.2024.10825246
Show More Cited By

Index Terms

A Demonstration of KAMEL: A Scalable BERT-based System for Trajectory Imputation
1. Computing methodologies
  1. Artificial intelligence
    1. Knowledge representation and reasoning
      1. Spatial and physical reasoning
2. Information systems
  1. Information systems applications
    1. Spatial-temporal systems

Recommendations

Kamel: A Scalable BERT-Based System for Trajectory Imputation

Numerous important applications rely on detailed trajectory data. Yet, unfortunately, trajectory datasets are typically sparse with large spatial and temporal gaps between each two points, which is a major hurdle for their accuracy. This paper presents ...
Network-less trajectory imputation
SIGSPATIAL '22: Proceedings of the 30th International Conference on Advances in Geographic Information Systems

The ability to collect large numbers of trajectory data through GPS-enabled devices have enabled a myriad of very important applications that are widely used on a daily basis. This includes urban computing, transportation, and map APIs for routing and ...
GTI: A Scalable Graph-based Trajectory Imputation
SIGSPATIAL '23: Proceedings of the 31st ACM International Conference on Advances in Geographic Information Systems

GPS-enabled devices, including vehicles, smartphones, wearable and tracking devices, as well as various check-in and social network data are continuously producing tremendous amounts of trajectory data, which are used consistently in many applications ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

SIGMOD '23: Companion of the 2023 International Conference on Management of Data

June 2023

330 pages

ISBN:9781450395076

DOI:10.1145/3555041

General Chairs:
Sudipto Das
Amazon Web Services, USA
,
Ippokratis Pandis
Amazon Web Services, USA
,
Program Chairs:
K. Selçuk Candan
Arizona State University, USA
,
Sihem Amer-Yahia
CNRS, Université Grenoble Alpes, France

Copyright © 2023 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGMOD: ACM Special Interest Group on Management of Data

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 June 2023

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Badges

Best Demo

Author Tags

Qualifiers

Short-paper

Data Availability

This demo presents KAMEL; a novel trajectory imputation framework that aims to impute sparse trajectories as a means of increasing their accuracy, and hence the accuracy of their applications. Unlike the large majority of current trajectory imputation techniques, KAMEL does not require the knowledge or the availability of the underlying road network, which makes it applicable to important applications like map inference that need to infer the road network itself. Audience will experience KAMEL through various scenarios that show the imputation accuracy as well as KAMEL internals. https://dl.acm.org/doi/10.1145/3555041.3589733#23_01_SIGMOD_KAMEL_DEMO.mp4

Funding Sources

NSF

Conference

SIGMOD/PODS '23

Sponsor:

SIGMOD

SIGMOD/PODS '23: International Conference on Management of Data

June 18 - 23, 2023

WA, Seattle, USA

Acceptance Rates

Overall Acceptance Rate 785 of 4,003 submissions, 20%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

6
Total Citations
View Citations
291
Total Downloads

Downloads (Last 12 months)89
Downloads (Last 6 weeks)12

Reflects downloads up to 03 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Musleh MMokbel M(2024)Let's Speak Trajectories: A Vision to Use NLP Models for Trajectory Analysis TasksACM Transactions on Spatial Algorithms and Systems10.1145/365647010:2(1-25)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1145/3656470
Mohammed HNascimento MBarbosa D(2024)Effective Trajectory Imputation using Simple Probabilistic Language Models2024 25th IEEE International Conference on Mobile Data Management (MDM)10.1109/MDM61037.2024.00027(51-60)Online publication date: 24-Jun-2024
https://doi.org/10.1109/MDM61037.2024.00027
Najjar A(2024)Pre-trained Transformer Uncovers Meaningful Patterns in Human Mobility Data2024 IEEE International Conference on Big Data (BigData)10.1109/BigData62323.2024.10825246(5819-5828)Online publication date: 15-Dec-2024
https://doi.org/10.1109/BigData62323.2024.10825246
Wu YYu HDu JGe C(2023)Trajectory-BERT: Trajectory Estimation Based on BERT Trajectory Pre-Training Model and Particle Filter AlgorithmSensors10.3390/s2322912023:22(9120)Online publication date: 11-Nov-2023
https://doi.org/10.3390/s23229120
Musleh MMokbel M(2023)Kamel: A Scalable BERT-Based System for Trajectory ImputationProceedings of the VLDB Endowment10.14778/3632093.363211317:3(525-538)Online publication date: 1-Nov-2023
https://dl.acm.org/doi/10.14778/3632093.3632113
Najjar A(2023)Towards A Foundation Model For Trajectory Intelligence2023 IEEE International Conference on Data Mining Workshops (ICDMW)10.1109/ICDMW60847.2023.00112(832-835)Online publication date: 4-Dec-2023
https://doi.org/10.1109/ICDMW60847.2023.00112

View Options

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

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Figures

Tables

Media

View Table of Conten