A Survey on Big Data for Trajectory Analytics

Almeida, Damião Ribeiro de; Baptista, Cláudio de Souza; Andrade, Fabio Gomes de; Soares, Amílcar

doi:10.3390/ijgi9020088

Cited by 35 publications

(14 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it was the first time that BCC_MSSR was applied to geo-referenced time series, in the future there are the following directions to work on: (1) in this study we only used this co-clustering algorithm for a small dataset, in the next, we plan to apply BCC_MSSR to a larger spatio-temporal dataset to test its scalability; (2) besides geo-referenced time series, we plan to apply this algorithm to other types of spatio-temporal data, e.g., trajectories;…”

Section: Discussionmentioning

confidence: 99%

“…Thanks to the advancement of earth observation and model simulation systems, unprecedented amounts of spatio-temporal data with various resolutions have been accumulated [1,2]. On one hand, these massive amounts of data provide opportunities to investigate complex patterns and knowledge to help decision-making [3]; on the other hand, how to extract patterns from these data becomes a challenging issue [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Co-Clusters with Coherent Trends in Geo-Referenced Time Series

2022

IJGI

View full text Add to dashboard Cite

Several studies have worked on co-clustering analysis of spatio-temporal data. However, most of them search for co-clusters with similar values and are unable to identify co-clusters with coherent trends, defined as exhibiting similar tendencies in the attributes. In this study, we present the Bregman co-clustering algorithm with minimum sum-squared residue (BCC_MSSR), which uses the residue to quantify coherent trends and enables the identification of co-clusters with coherent trends in geo-referenced time series. Dutch monthly temperatures over 20 years at 28 stations were used as the case study dataset. Station-clusters, month-clusters, and co-clusters in the BCC_MSSR results were showed and compared with co-clusters of similar values. A total of 112 co-clusters with different temperature variations were identified in the Results, and 16 representative co-clusters were illustrated, and seven types of coherent temperature trends were summarized: (1) increasing; (2) decreasing; (3) first increasing and then decreasing; (4) first decreasing and then increasing; (5) first increasing, then decreasing, and finally increasing; (6) first decreasing, then increasing, and finally decreasing; and (7) first decreasing, then increasing, decreasing, and finally increasing. Comparisons with co-clusters of similar values show that BCC_MSSR explored coherent spatio-temporal patterns in regions and certain time periods. However, the selection of the suitable co-clustering methods depends on the objective of specific tasks.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Identification of Co-Clusters with Coherent Trends in Geo-Referenced Time Series

2022

IJGI

View full text Add to dashboard Cite

show abstract

“…Over the years, we have been experiencing massive maritime vessel trajectory network 1 expansion powered by globalization and the evolution of transportation [1]. Maritime navigation has an essential role in passenger transportation, tourism, and fishing [2][3][4][5][6][7]. Besides, it has been historically used for trading between territories and countries worldwide [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning

Spadon¹,

Ferreira²,

Soares³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

This paper aims to model the Automatic Identification System (AIS) message transmission behavior through neural networks for forecasting the upcoming AIS messages' content for multiple vessels simultaneously in the face of messages' irregular timing. We present a set of experiments comprising tens of algorithms used for forecasting tasks with horizon sizes of varying lengths. Deep learning models revealed themselves to adequately capture the temporal irregularity while preserving the spatial awareness of different vessels. We show how a multi-directional and multi-layer long-shortterm memory network and a convolution feature-extraction layer improve such a task by up to 20.01%.

show abstract

“…There are reviews and surveys that cover this problem of summarisation in the literature, [7][8][9][10][11][12][13][14] although most reviews address this problem in a tangential way as they focus on more generic problems. The ones that explore this problem are brief and leave aside the compression or segmentation branches.…”

Section: Introductionmentioning

confidence: 99%

Review and classification of trajectory summarisation algorithms: From compression to segmentation

Amigo

Pedroche

García

et al. 2021

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

With the continuous development and cost reduction of positioning and tracking technologies, a large amount of trajectories are being exploited in multiple domains for knowledge extraction. A trajectory is formed by a large number of measurements, where many of them are unnecessary to describe the actual trajectory of the vehicle, or even harmful due to sensor noise. This not only consumes large amounts of memory, but also makes the extracting knowledge process more difficult. Trajectory summarisation techniques can solve this problem, generating a smaller and more manageable representation and even semantic segments. In this comprehensive review, we explain and classify techniques for the summarisation of trajectories according to their search strategy and point evaluation criteria, describing connections with the line simplification problem. We also explain several special concepts in trajectory summarisation problem. Finally, we outline the recent trends and best practices to continue the research in next summarisation algorithms.

show abstract

A Survey on Big Data for Trajectory Analytics

Cited by 35 publications

References 72 publications

Identification of Co-Clusters with Coherent Trends in Geo-Referenced Time Series

Identification of Co-Clusters with Coherent Trends in Geo-Referenced Time Series

Unfolding AIS transmission behavior for vessel movement modeling on noisy data leveraging machine learning

Review and classification of trajectory summarisation algorithms: From compression to segmentation

Contact Info

Product

Resources

About