Cargando…

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Nawaz, Asif, Huang, Zhiqiu, Wang, Senzhang, Akbar, Azeem, AlSalman, Hussain, Gumaei, Abdu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7570549/
https://www.ncbi.nlm.nih.gov/pubmed/32916967
http://dx.doi.org/10.3390/s20185143
_version_ 1783596972425347072
author Nawaz, Asif
Huang, Zhiqiu
Wang, Senzhang
Akbar, Azeem
AlSalman, Hussain
Gumaei, Abdu
author_facet Nawaz, Asif
Huang, Zhiqiu
Wang, Senzhang
Akbar, Azeem
AlSalman, Hussain
Gumaei, Abdu
author_sort Nawaz, Asif
collection PubMed
description 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.
format Online
Article
Text
id pubmed-7570549
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-75705492020-10-28 GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism Nawaz, Asif Huang, Zhiqiu Wang, Senzhang Akbar, Azeem AlSalman, Hussain Gumaei, Abdu Sensors (Basel) Article 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. MDPI 2020-09-09 /pmc/articles/PMC7570549/ /pubmed/32916967 http://dx.doi.org/10.3390/s20185143 Text en © 2020 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 (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Nawaz, Asif
Huang, Zhiqiu
Wang, Senzhang
Akbar, Azeem
AlSalman, Hussain
Gumaei, Abdu
GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism
title GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism
title_full GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism
title_fullStr GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism
title_full_unstemmed GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism
title_short GPS Trajectory Completion Using End-to-End Bidirectional Convolutional Recurrent Encoder-Decoder Architecture with Attention Mechanism
title_sort gps trajectory completion using end-to-end bidirectional convolutional recurrent encoder-decoder architecture with attention mechanism
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7570549/
https://www.ncbi.nlm.nih.gov/pubmed/32916967
http://dx.doi.org/10.3390/s20185143
work_keys_str_mv AT nawazasif gpstrajectorycompletionusingendtoendbidirectionalconvolutionalrecurrentencoderdecoderarchitecturewithattentionmechanism
AT huangzhiqiu gpstrajectorycompletionusingendtoendbidirectionalconvolutionalrecurrentencoderdecoderarchitecturewithattentionmechanism
AT wangsenzhang gpstrajectorycompletionusingendtoendbidirectionalconvolutionalrecurrentencoderdecoderarchitecturewithattentionmechanism
AT akbarazeem gpstrajectorycompletionusingendtoendbidirectionalconvolutionalrecurrentencoderdecoderarchitecturewithattentionmechanism
AT alsalmanhussain gpstrajectorycompletionusingendtoendbidirectionalconvolutionalrecurrentencoderdecoderarchitecturewithattentionmechanism
AT gumaeiabdu gpstrajectorycompletionusingendtoendbidirectionalconvolutionalrecurrentencoderdecoderarchitecturewithattentionmechanism