Traffic Pattern Mining and Forecasting Technologies in Maritime Traffic Service Networks: A Comprehensive Survey
01 May 2020-IEEE Transactions on Intelligent Transportation Systems (IEEE)-Vol. 21, Iss: 5, pp 1796-1825
TL;DR: The development of maritime traffic research in pattern mining and traffic forecasting affirms the importance of advanced maritime traffic studies and the great potential in maritime traffic safety and intelligence enhancement to accommodate the implementation of the Internet of Things, artificial intelligence technologies, and knowledge engineering and big data computing solution.
Abstract: Maritime traffic service networks and information systems play a vital role in maritime traffic safety management. The data collected from the maritime traffic networks are essential for the perception of traffic dynamics and predictive traffic regulation. This paper is devoted to surveying the key processing components in maritime traffic networks. Specifically, the latest progress on maritime traffic data mining technologies for maritime traffic pattern extraction and the recent effort on vessels’ motion forecasting for better situation awareness are reviewed. Through the review, we highlight that the traffic pattern knowledge presents valued insights for wide-spectrum domain application purposes, and serves as a prerequisite for the knowledge based forecasting techniques that are growing in popularity. The development of maritime traffic research in pattern mining and traffic forecasting reviewed in this paper affirms the importance of advanced maritime traffic studies and the great potential in maritime traffic safety and intelligence enhancement to accommodate the implementation of the Internet of Things, artificial intelligence technologies, and knowledge engineering and big data computing solution.
Citations
More filters
TL;DR: A survey on the demand for maritime communications enabled by state-of-the-art hybrid satellite-terrestrial maritime communication networks (MCNs), and envision the use of external auxiliary information to build up an environment-aware, service-driven, and integrated satellite-air-ground MCN.
Abstract: With the rapid development of marine activities, there has been an increasing number of Internet-of-Things (IoT) devices on the ocean. This leads to a growing demand for high-speed and ultrareliable maritime communications. It has been reported that a large performance loss is often inevitable if the existing fourth-generation (4G), fifth-generation (5G), or satellite communication technologies are used directly on the ocean. Hence, conventional theories and methods need to be tailored to this maritime scenario to match its unique characteristics, such as dynamic electromagnetic propagation environments, geometrically limited available base station (BS) sites and rigorous service demands from mission-critical applications. Toward this end, we provide a survey on the demand for maritime communications enabled by state-of-the-art hybrid satellite-terrestrial maritime communication networks (MCNs). We categorize the enabling technologies into three types based on their aims: 1) enhancing transmission efficiency; 2) extending network coverage; and 3) provisioning maritime-specific services. Future developments and open issues are also discussed. Based on this discussion, we envision the use of external auxiliary information, such as sea state and atmosphere conditions, to build up an environment-aware, service-driven, and integrated satellite-air-ground MCN.
122 citations
Additional excerpts
...In addition to using the above-mentioned satellite-based systems, navigational communication services can also be provided by shore-based systems, such as terrestrial AIS and coastal radars [229]....
[...]
TL;DR: This work proposes to develop a two-phase data-driven machine learning framework for vessel trajectory reconstruction that has the capacity of promoting intelligent vessel traffic services in 6G-enabled maritime IoT systems.
Abstract: Future generation communication systems, such as 5G and 6G wireless systems, exploit the combined satellite-terrestrial communication infrastructures to extend network coverage and data throughput for data-driven applications. These ground-breaking techniques have promoted the rapid development of Internet of Things (IoT) in maritime industries. In maritime IoT applications, intelligent vessel traffic services can be guaranteed by collecting and analyzing high volume of spatial data flows from automatic identification system (AIS). This AIS system includes a highly integrated automatic equipment, including functionalities of core communication, tracking, and sensing. The increased utilization of shipboard AIS devices allows the collection of massive trajectory data. However, the received raw AIS data often suffers from undesirable outliers (i.e., poorly tracked timestamped points for vessel trajectories ) during signal acquisition and analog-to-digital conversion. The degraded AIS data will bring negative effects on vessel traffic services (e.g., maritime traffic monitoring, intelligent maritime navigation, vessel collision avoidance, etc.) in maritime IoT scenarios. To improve the quality of vessel trajectory records from AIS networks, we propose to develop a two-phase data-driven machine learning framework for vessel trajectory reconstruction. In particular, a density-based clustering method is introduced in the first phase to automatically recognize the undesirable outliers. The second phase proposes a bidirectional long short-term memory (BLSTM)-based supervised learning technique to restore the timestamped points degraded by random outliers in vessel trajectories. Comprehensive experiments on simulated and realistic data sets have verified the dominance of our two-phase vessel reconstruction framework compared to other competing methods. It thus has the capacity of promoting intelligent vessel traffic services in 6G-enabled maritime IoT systems.
120 citations
Cites background from "Traffic Pattern Mining and Forecast..."
...In maritime IoT systems, the automatic identification system (AIS), which is an automated vessel selfreporting system, has been devoted to enabling intelligent vessel traffic services, such as maritime traffic monitoring, intelligent maritime navigation, and vessel collision avoidance, etc [1], [2]....
[...]
Posted Content•
TL;DR: In this article, the authors provide a survey on the demand for maritime communications, the state-of-the-art MCNs, and key technologies for enhancing transmission efficiency, extending network coverage, and provisioning maritime-specific services.
Abstract: With the rapid development of marine activities, there has been an increasing number of maritime mobile terminals, as well as a growing demand for high-speed and ultra-reliable maritime communications to keep them connected. Traditionally, the maritime Internet of Things (IoT) is enabled by maritime satellites. However, satellites are seriously restricted by their high latency and relatively low data rate. As an alternative, shore & island-based base stations (BSs) can be built to extend the coverage of terrestrial networks using fourth-generation (4G), fifth-generation (5G), and beyond 5G services. Unmanned aerial vehicles can also be exploited to serve as aerial maritime BSs. Despite of all these approaches, there are still open issues for an efficient maritime communication network (MCN). For example, due to the complicated electromagnetic propagation environment, the limited geometrically available BS sites, and rigorous service demands from mission-critical applications, conventional communication and networking theories and methods should be tailored for maritime scenarios. Towards this end, we provide a survey on the demand for maritime communications, the state-of-the-art MCNs, and key technologies for enhancing transmission efficiency, extending network coverage, and provisioning maritime-specific services. Future challenges in developing an environment-aware, service-driven, and integrated satellite-air-ground MCN to be smart enough to utilize external auxiliary information, e.g., sea state and atmosphere conditions, are also discussed.
82 citations
TL;DR: Experimental results illustrated that: 1) the proposed GPU-based parallel implementation frameworks could significantly reduce the computational time for both trajectory compression and visualization; 2) the influence of compressed vessel trajectories on trajectory visualization could be negligible if the compression threshold was selected suitably; and the Gaussian kernel was capable of generating more appropriate KDE-based visualization performance by comparing with other seven kernel functions.
Abstract: The automatic identification system (AIS), an automatic vessel-tracking system, has been widely adopted to perform intelligent traffic management and collision avoidance services in maritime Internet-of-Things (IoT) industries. With the rapid development of maritime transportation, tremendous numbers of AIS-based vessel trajectory data have been collected, which make trajectory data compression imperative and challenging. This article mainly focuses on the compression and visualization of large-scale vessel trajectories and their graphics processing unit (GPU)-accelerated implementations. The visualization was implemented to investigate the influence of compression on vessel trajectory data quality. In particular, the Douglas–Peucker (DP) and kernel density estimation (KDE) algorithms, respectively, utilized for trajectory compression and visualization, were significantly accelerated through the massively parallel computation capabilities of the GPU architecture. Comprehensive experiments on trajectory compression and visualization have been conducted on large-scale AIS data of recording ship movements collected from three different water areas, i.e., the South Channel of Yangtze River Estuary, the Chengshan Jiao Promontory, and the Zhoushan Islands. Experimental results illustrated that: 1) the proposed GPU-based parallel implementation frameworks could significantly reduce the computational time for both trajectory compression and visualization; 2) the influence of compressed vessel trajectories on trajectory visualization could be negligible if the compression threshold was selected suitably; and 3) the Gaussian kernel was capable of generating more appropriate KDE-based visualization performance by comparing with other seven kernel functions.
76 citations
TL;DR: A deep learning framework to support regional ship behavior prediction using historical AIS data is presented, suggesting to cluster historical trajectories using a variational recurrent autoencoder and the Hierarchical Density-Based Spatial Clustering of Applications with Noise algorithm.
64 citations
Cites methods from "Traffic Pattern Mining and Forecast..."
...The data from such real-time observations are used by VTS operators to support proactive traffic management [8]....
[...]
References
More filters
[...]
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
79,257 citations
"Traffic Pattern Mining and Forecast..." refers methods in this paper
...Random forest [180], [181] is an ensemble learning method that relies on a combination of tree predictors(or classifiers)...
[...]
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Abstract: The support-vector network is a new learning machine for two-group classification problems. The machine conceptually implements the following idea: input vectors are non-linearly mapped to a very high-dimension feature space. In this feature space a linear decision surface is constructed. Special properties of the decision surface ensures high generalization ability of the learning machine. The idea behind the support-vector network was previously implemented for the restricted case where the training data can be separated without errors. We here extend this result to non-separable training data.
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated. We also compare the performance of the support-vector network to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
37,861 citations
"Traffic Pattern Mining and Forecast..." refers methods in this paper
...supervised machine learning methods that can be used for classification purpose [172]....
[...]
Book•
28 Jul 2013TL;DR: In this paper, the authors describe the important ideas in these areas in a common conceptual framework, and the emphasis is on concepts rather than mathematics, with a liberal use of color graphics.
Abstract: During the past decade there has been an explosion in computation and information technology. With it have come vast amounts of data in a variety of fields such as medicine, biology, finance, and marketing. The challenge of understanding these data has led to the development of new tools in the field of statistics, and spawned new areas such as data mining, machine learning, and bioinformatics. Many of these tools have common underpinnings but are often expressed with different terminology. This book describes the important ideas in these areas in a common conceptual framework. While the approach is statistical, the emphasis is on concepts rather than mathematics. Many examples are given, with a liberal use of color graphics. It is a valuable resource for statisticians and anyone interested in data mining in science or industry. The book's coverage is broad, from supervised learning (prediction) to unsupervised learning. The many topics include neural networks, support vector machines, classification trees and boosting---the first comprehensive treatment of this topic in any book.
This major new edition features many topics not covered in the original, including graphical models, random forests, ensemble methods, least angle regression and path algorithms for the lasso, non-negative matrix factorization, and spectral clustering. There is also a chapter on methods for ``wide'' data (p bigger than n), including multiple testing and false discovery rates.
Trevor Hastie, Robert Tibshirani, and Jerome Friedman are professors of statistics at Stanford University. They are prominent researchers in this area: Hastie and Tibshirani developed generalized additive models and wrote a popular book of that title. Hastie co-developed much of the statistical modeling software and environment in R/S-PLUS and invented principal curves and surfaces. Tibshirani proposed the lasso and is co-author of the very successful An Introduction to the Bootstrap. Friedman is the co-inventor of many data-mining tools including CART, MARS, projection pursuit and gradient boosting.
19,261 citations
Proceedings Article•
02 Aug 1996TL;DR: In this paper, a density-based notion of clusters is proposed to discover clusters of arbitrary shape, which can be used for class identification in large spatial databases and is shown to be more efficient than the well-known algorithm CLAR-ANS.
Abstract: Clustering algorithms are attractive for the task of class identification in spatial databases. However, the application to large spatial databases rises the following requirements for clustering algorithms: minimal requirements of domain knowledge to determine the input parameters, discovery of clusters with arbitrary shape and good efficiency on large databases. The well-known clustering algorithms offer no solution to the combination of these requirements. In this paper, we present the new clustering algorithm DBSCAN relying on a density-based notion of clusters which is designed to discover clusters of arbitrary shape. DBSCAN requires only one input parameter and supports the user in determining an appropriate value for it. We performed an experimental evaluation of the effectiveness and efficiency of DBSCAN using synthetic data and real data of the SEQUOIA 2000 benchmark. The results of our experiments demonstrate that (1) DBSCAN is significantly more effective in discovering clusters of arbitrary shape than the well-known algorithm CLAR-ANS, and that (2) DBSCAN outperforms CLARANS by a factor of more than 100 in terms of efficiency.
17,056 citations
Proceedings Article•
01 Jan 1996TL;DR: DBSCAN, a new clustering algorithm relying on a density-based notion of clusters which is designed to discover clusters of arbitrary shape, is presented which requires only one input parameter and supports the user in determining an appropriate value for it.
Abstract: Clustering algorithms are attractive for the task of class identification in spatial databases. However, the application to large spatial databases rises the following requirements for clustering algorithms: minimal requirements of domain knowledge to determine the input parameters, discovery of clusters with arbitrary shape and good efficiency on large databases. The well-known clustering algorithms offer no solution to the combination of these requirements. In this paper, we present the new clustering algorithm DBSCAN relying on a density-based notion of clusters which is designed to discover clusters of arbitrary shape. DBSCAN requires only one input parameter and supports the user in determining an appropriate value for it. We performed an experimental evaluation of the effectiveness and efficiency of DBSCAN using synthetic data and real data of the SEQUOIA 2000 benchmark. The results of our experiments demonstrate that (1) DBSCAN is significantly more effective in discovering clusters of arbitrary shape than the well-known algorithm CLARANS, and that (2) DBSCAN outperforms CLARANS by a factor of more than 100 in terms of efficiency.
14,297 citations
"Traffic Pattern Mining and Forecast..." refers methods in this paper
...methodology [90], of which the patterns can be expanded and updated by incremental DBSCAN [91]....
[...]
...In TREAD, waypoints are defined as stationary objects like ports and offshore platforms and entry and exit points [90], are clustered using DBSCAN...
[...]