Search

Vessel trajectory prediction plays a pivotal role in numerous maritime applications and services. While the Automatic Identification System (AIS) offers a rich source of information to address this task, forecasting vessel trajectory using AIS data remains challenging, even for modern machine learning techniques, because of the inherent heterogeneous and multimodal nature of motion data. In this paper, we propose a novel approach to tackle these challenges. We introduce a discrete, high-dimensional representation of AIS data and a new loss function designed to explicitly address heterogeneity and multimodality. The proposed model—referred to as TrAISformer —is a modified transformer network that extracts long-term temporal patterns in AIS vessel trajectories in the proposed enriched space to forecast the positions of vessels several hours ahead. We report experimental results on real, publicly available AIS data. TrAISformer significantly outperforms state-of-the-art methods, with an average prediction performance below 10 nautical miles up to ~10 hours.

In recent years, the Poisson multi-Bernoulli mixture (PMBM) filter has been established among the state-of-the art methods in target tracking. We present a method for including target-provided measurements in said filter, both when using it to track extended objects and point targets. We use messages from the Automatic identification system as an example of target-provided measurements, and radar and LiDAR as examples of exteroceptive sensors. In the point target case, we utilize several different kinematic models in parallel through the interacting multiple models framework, and compare the presented method to several common trackers and other PMBM filter configurations. The results show that our method outperforms similar methods when target-provided measurements are available. The point target variant is also shown to work in a closed-loop collision avoidance experiment in a maritime environment, demonstrating its feasibility for use in real-world applications. For the extended object tracking case, we expand upon the Gaussian process PMBM filter. The extended object method is evaluated on both simulated and experimental data, and is shown to improve the tracking performance when including target-provided measurements in comparison to when it only uses exteroceptive measurements.

The study of sea area accessibility is often overlooked despite the fact that vessel routes’ density at sea can reflect human activity patterns. Using AIS point data for 2014 and 2018, this paper constructed global daily vessel routes and applied the kernel density estimation method to obtain the probability distribution function of route density for over 700,000 sea grids under a global 0.25° regular grid. An accessibility model for sea areas was then proposed and applied to the grid, resulting in the accessibility assessment of global sea areas in 2014 and 2018. The results indicated that the average global maritime accessibility value increased from 5.2% in 2014 to 14.4% in 2018. Accessibility to various international trade routes, such as those through the Cape of Good Hope and polar regions, significantly increased. However, accessibility to sea areas such as the Mediterranean and sea areas near the Pacific Islands decreased. This study explored the temporal and spatial variation of maritime traffic accessibility, which could enhance our understanding of global vessel activity characteristics and guide maritime rescue resource allocation, marine species protection, and marine spatial planning.

In response to the limitations of the DQN algorithm in adaptability, which result in a low success rate in ship path planning, this paper introduces an improved algorithm based on Deep Q-learning (DQN) to enhance path planning. The proposed algorithm aims to plan a reasonable and cost-effective route to the destination based on all historical track, regardless of the current location of ship within the environment. Firstly, the k-means clustering algorithm is employed to cluster the historical ship locations. The value of k is progressively increased to include more locations, allowing the model to interact with the environment of increasing complexity. This approach enhances the generalization capability of the model by enabling it to autonomously devise a route from any starting point to the destination port. On the other hand, for the ship path problem, the DQN algorithm is enhanced through the optimization of the reward function. This improvement targets the challenges of convergence difficulty and low learning efficiency, which greatly improves the rate of convergence for the model. Finally, the effectiveness of the method is verified by comparing it experimentally in terms of the effectiveness of path planning and model convergence trend. The results demonstrate that the improved DQN algorithm achieves a convergence speed improvement of over 25%. Additionally, with the same training time, the success rate of path planning from any position to destination within the environment is enhanced by 44%. It has better effect on the path planning of ships.

To increase situational awareness of maritime vessels and other entities and to enable their exchange of various information, the International Maritime Organization mandated the use of the Automatic Identification System (AIS) in 2004. The AIS is a self-reporting system that uses the VHF radio link. However, any radio-based self-reporting system is prone to forgery, especially in situations where authentication of the message is not designed into the architecture. As AIS was designed in the 1990s when cyberattacks were in their infancy, it does not implement authentication or encryption; thus, it can be seen as fundamentally vulnerable against cyberattacks. This paper demonstrates and evaluates the impact of multiple cyberattacks on AIS via remote radio frequency (RF) links using transmission-enabled software-defined radio (SDR). Overall, we implemented and tested a total of 11 different tests/attacks on 19 AIS setups, using a controlled environment. The tested configurations were derived from heterogeneous platforms such as Windows, Android, generic receivers, and commercial transponders. Our aim is to enhance the early discovery of new vulnerabilities in AIS to effectively address AIS attacks in the nearest future. The results showed that approximately 89% of the setups were affected by Denial-of-Service (DoS) attacks at the AIS protocol level. Besides implementing some existing attack ideas (e.g., spoofing, DoS, and flooding), we showed some novel attack concepts in the AIS context such as a coordinated attack, overwhelming alerts, and logical vulnerabilities, all of which have the potential to cause software/system crashes in the worst-case scenarios. Moreover, an implementation/specification flaw related to the AIS preamble was identified during the experiments, which may affect the interoperability of different AIS devices. The error-handling system in AIS was also investigated. Unlike the aviation sector’s Automatic Dependent Surveillance-Broadcast (ADS-B), the maritime sector’s AIS does not effectively support any error correction method, which may contribute to RF pollution and less effective use of the overall system. The consistency of our results for a comprehensive range of hardware-software configurations indicated the reliability of our approach, test system, and evaluation results.

True Random Number Generator (TRNG) is used in many applications, generally for generating random cryptography keys. In this way, the trust of the cryptography system depends on the quality of the random numbers generated. However, the entropy fluctuations produced by external perturbations generate some false positives in the random sequence. These false positives can generate a disastrous scenario, depending on the application. This work presents the results of different tests to demonstrate the robustness and health of the TRNG based on frequency collapse. The TRNG passed all entropy tests provided for NIST SP800-90B and AIS31. The entropy test denotes a 0.9789 minimum normalized entropy and 7.998 Shannon entropy. In addition, the TRNG passes the health tests provided for NIST SP800-90B. The health test shows a number of identical values $I_{v}=0\%$ , $I_{v-1} < 0.004\%$ and a maximum cutoff value $MC_{v}=10$ with $LMC_{v}=13$ in the repetition count and adaptive proportion tests, respectively. The implementation passed all the statistical tests provided for NIST SP800-22 and AIS20. Besides, the implementation passes the different tests with Process, Voltage, and Temperature (PVT) variations. The TRNG is implemented in a $0.18~\mu m$ General Purpose (GP) CMOS technology, occupying $25600~\mu m^{2}$ with four entropy sources. Finally, the implementation presents a 7.3 until 9.2-Mb/s of bit rate, 0.56 until 1.88-mW of power consumption, and 77.2 until 204.3-pJ/bit of energy per bit using an entropy source with 16 and 2 delay stages, respectively.

Tracking multiple moving objects in real-time in a dynamic threat environment is an important element in national security and surveillance system. It helps pinpoint and distinguish potential candidates posing threats from other normal objects and monitor the anomalous trajectories until intervention. To locate the anomalous pattern of movements, one needs to have an accurate data association algorithm that can associate the sequential observations of locations and motion with the underlying moving objects, and therefore, build the trajectories of the objects as the objects are moving. In this work, we develop a spatio-temporal approach for tracking maritime vessels as the vessel’s location and motion observations are collected by an Automatic Identification System. The proposed approach is developed as an effort to address a data association challenge in which the number of vessels as well as the vessel identification are purposely withheld and time gaps are created in the datasets to mimic the real-life operational complexities under a threat environment. Three training datasets and five test sets are provided in the challenge and a set of quantitative performance metrics is devised by the data challenge organizer for evaluating and comparing resulting methods developed by participants. When our proposed track association algorithm is applied to the five test sets, the algorithm scores a very competitive performance. [ABSTRACT FROM AUTHOR]

Maritime Autonomous Surface Ships (MASSs) will reshape the fast-evolving ecosystem for their attractive socio-economic benefits and potential to improve safety. However, their new systems and technology need thorough verifications to identify unintended components of risk. The interaction between MASS cyber-physical systems and the existing regulatory framework is currently unpredictable; AI-powered intelligent situation awareness and autonomous navigation algorithms must safely and efficiently adhere to the regulations which are only designed for human interpretation without MASSs consideration. This paper contributes to algorithmic regulations and particularly algorithmic COLREGs in real-world MASS applications. It focuses on codifying COLREGs into a machine-executable system applicable to MASSs. This fullest COLREGs evaluation is modelled in form of a fuzzy expert system based on ordinary seamanship practice. The full input space spans 21 features derived from maneuverability-dependent risk, AIS traffic data, vessel information, maps and nautical charts, water-depth, visibility, and sea conditions. The model assesses pairwise vessel encounters over the full time-window of a situation from entrance to exit. 42 fuzzy rules are designed in 6 criteria that represent COLREGs Rules 2–19 and model their logical connections, priorities, and relationships. This algorithmic COLREGs form satisfies the crucial needs in simulation, collision-avoidance, complexity monitoring, and compliance quantification in MASS applications. The fullest COLREGs evaluation model is verified on a large database of historical encounters using real data from multiple sources. [ABSTRACT FROM AUTHOR]

Representing maritime traffic patterns and detecting anomalies from them are key to vessel monitoring and maritime situational awareness. We propose a novel approach—referred to as GeoTrackNet—for maritime anomaly detection from AIS data streams. Our model exploits state-of-the-art neural network schemes to learn a probabilistic representation of AIS tracks and a contrario detection to detect abnormal events. The neural network provides a new means to capture complex and heterogeneous patterns in vessels’ behaviours, while the a contrario detector takes into account the fact that the learnt distribution may be location-dependent. Experiments on a real AIS dataset comprising more than 4.2 million AIS messages demonstrate the relevance of the proposed method compared with state-of-the-art schemes. [ABSTRACT FROM AUTHOR]

When designed, technologies and frameworks are not created to be as dynamic and flexible as to cater to the requirements of other domains, and so is the case with Blockchain technology. Specifically designed for cryptocurrency, Blockchain was not intended to be used in other domains. However, during the past few years, critics argued that Blockchain has the potential to deal with some unique requirements like confidentiality and immutability and can therefore be deployed in several areas other than cryptocurrency. The use of Blockchain to support Accounting Information Systems (AIS) through enterprise resource planning (ERP) is another motivating domain to investigate in this research. ERP is another promising technology that has gained significant attention across the globe. In this research, a hybrid solution is proposed to ensure AIS data integrity against any deliberate attempt or mala-fide intention for alteration or deletion from the database that can be verified at any later stage. Since Blockchain can be used to prevent any mutability in the stored data, the proposed solution presents a concept of Data Vaults backed by the Blockchain. To this end, we apply cryptographic primitives like SHA256 on the data inside the block and then chain that block to secure data vaults. So far, Blockchain has not yet proven itself as an alternative to any traditional database system. However, it can be applied in conjunction with the Relational Database Management Systems (RDBMS) to provide cost-effective yet robust solutions. This research demonstrates the application of a simple and lean version of Blockchain to assist enterprises in storing their financial and accounting data into data vaults, ensuring their data integrity against any alterations. The suggested cost-effective framework can be easily integrated into AIS and ERP systems to identify data breaches.

Autonomous ships are promoted as the future of the maritime transport industry aiming to overcome conventional vessels in terms of performance, safety and environmental impact. Yet their tangled cyber-physical-social interactions and new emerging properties induce questions regarding their liability and trustworthiness. Digital simulations and sea trials are launched to assure the safety requirements and social expectations are met a priori. This paper presents the design of realistic testbed scenarios from huge historical data through a high-performance computational method to recommend a complete set of navigation scenarios for autonomy tests. The developed approach integrates traffic big data from Automatic Identification System (AIS) with high-resolution digital maps, vessel information registry, and digital nautical charts. All historical vessel-to-ground and vessel-to-vessel interactions are efficiently analyzed through a hierarchical method for collision and grounding conflicts assessment with a 15-minutes prediction horizon. Relative risk is evaluated accurately over full periods of predicted close-quarters situations subject to physical limits and sea-room availability for evasive maneuverers under COLREG rules and traffic separation schemes. Spatial dependencies among multiple conflicts define risky momentary traffic situations modelled through directed graph representation of nested interactions. Their temporal dependencies describe navigation scenarios through dynamic co-behaviors between multiple participating vessels over a period of time. Finally, we analyze negative/positive actions that increase/decrease the complexity. The presented algorithms are computationally very efficient, they scale to several (country*year)s where millions of scenarios are extracted, classified, and scored by their relative risk, complexity, and likelihood for firm post-test conclusions. [ABSTRACT FROM AUTHOR]

Assortativity, one of the mixing patterns of complex networks, is characterized by measuring whether the nodes are preferentially connected to the nodes with a similar scale. While numerous studies have examined the assortative characteristics of various real-world networks, few studies have attempted to analyze the assortativity of networks in which the subject of trade is bulk. The novelty of this research is that, for the first time, the assortative coefficient method in physics is introduced into the bulk trade network, and the Automatic Identification System (AIS) data is used to explore the assortative mixing characteristics of the network. From the perspective of multi-scale (port and country) and multi-dimensional (node, link, and network) structure, this paper reveals the tendency of trade connection and explores the trade rules of bulk in networks. The results show that: (1) The trade network of bulk on the Maritime Silk Road is assortative. With the increase of spatial scale, the extent of assortativity is also gradually increasing; (2) In the bulk network of ports, trade cooperation shows the rule of distance attenuation; In the national bulk network, it shows the rule of preferential connection; (3) Ports with high out-degree will export bulk to the ports with high out-degree with broad market, while countries with high out-degree export to high in-degree countries with strong demand. The present study is expected to provide valuable references for port planning, national formulation of scientific bulk trade strategy, and promotion of coordinated development of bulk trade network along the Maritime Silk Road.

In this work we propose a novel spatial knowledge discovery pipeline capable of automatically unravelling the “roads of the sea” and maritime traffic patterns by analysing voluminous vessel tracking data, as collected through the Automatic Identification System (AIS). We present a computationally efficient and highly accurate solution, based on a MapReduce approach and unsupervised learning methods, capable of identifying the spatiotemporal dynamics of ship routes and most crucially their characteristics, thus deriving maritime “patterns of life” at a global scale, without the reliance on any additional information sources or a priori expert knowledge. Experimental results confirm high accuracy of results and superior performance in comparison to other methods, with the entire processing duration completing in less than 3 hours for more than a terabyte of non-uniform spatial data. Finally, to clearly demonstrate the applicability and impact of our proposed method, we evaluate its ability to detect real world “anomalies”, such as maritime incidents reported in the European Marine Casualty Information Platform. Numerical results show the advantages of our scheme in terms of accuracy, with an achieved anomaly detection accuracy of higher than 93%, by detecting 313 out of 335 relevant maritime incidents.

Shipping containers are tokens of multimodal international transportation and rapid logistics. Container deliveries are scheduled to satisfy rapidly changing requirements. Unpredictable increases in costs and unforeseeable events such as pandemics compel ship owners and managers to adopt risk minimization measures. This study addresses one issue: how to determine an alternative port of call from massive data to offer a realistic destination change recommendation for a container vessel. Recommendation algorithms have become ubiquitous and are used effectively in other fields, but there is no such model for the port of call selection or recommendation. Large scale automatic identification system (AIS) data are readily available. We developed a computational framework based on a novel natural language programming algorithm that was tailored to support port recommendation rather than use a conventional adjacency matrix method. We mined large scale AIS data to construct sequential berth records for container vessels and mapped each port onto a vector in an embedded space. The natural language neural programming algorithm can suggest ports similar to the scheduled ports of call that were unable to offer service. The recommendations were validated with geo-analysis of sailing distance and could offer viable alternative ports to shipping managers.

Deep learning provides appropriate mechanisms to predict vessel trajectories for safer and efficient shipping, but still existing models are mainly oriented to longer-term prediction trends and do not fully support real time navigation needs. While most recent works have been largely exploiting Automatic Identification System (AIS), the complete semantics of these data haven't so far fully exploited. The research presented in this paper introduced an extended sequence-to-sequence model using AIS data. A Gated Recurrent Unit (GRU) network encodes historical spatio-temporal sequences as a context vector, which not only preserves the sequential relationships among trajectory locations, but also alleviates the gradient descent problem. The GRU network acts as a decoder, outputting target trajectory location sequences. Real AIS data from the Chongqing and Wuhan sections of the Yangzi River were selected as typical experimental areas for evaluation purposes. The proposed ST-Seq2Seq model has been tested against the LSTM-RNN and GRU-RNN baseline models for short term trajectory prediction experiments. A 10-minute historical trajectory sequence was used to predict the trajectory sequence for the next five minutes. Overall, the findings show that LSTM and GRU networks, while applying a recursive method to predict a sequence of continuous trajectory points, when the number of predicted trajectory points increases accuracy decreases. Conversely, the extended sequence-to-sequence model shows satisfactory stability on different ship channels.

It is an effective method to analyze the maritime traffic risk using near miss model, but there are no works from the temporal perspective. The duration of near miss shows the maritime traffic risk. The longer the duration is, the higher the risk is. The influence of the ship maneuvering capability, speed, size, and Convention on the International Regulations for Preventing Collisions at Sea (COLREGS) on the safety of ship navigation are considered in this article, the navigation safety domain is used to detect near misses, and the duration of a single near miss is defined, which is the time from target ship sailing into the navigation safety domain of own ship to leaving, and then an algorithm for calculating duration of near misses is proposed. To measure the similarity of two ships' lengths, the similarity coefficient model of ships' lengths is defined. Based on the k -means algorithm, different parameters k are selected to cluster the duration of near misses. According to the clustering results, the connections between the duration of near misses and the ship type, length, and speed were analyzed to identify a series of time characteristics of near misses, that is high frequencies of short-duration near misses and the strong connections between the long-duration near misses, ship length, and ship speed. The method is first proposed for doing research of near misses in temporal dimension. The findings of this article help researchers and maritime traffic management agencies to better understand the importance of maritime traffic risk from the temporal perspective.

The large maritime traffic volume and its implications in economy, environment, safety, and security require an unsupervised system to monitor maritime traffic. In this paper, a method is proposed to automatically produce synthetic maritime traffic representations from historical self-reporting positioning data, more specifically from automatic identification system data. The method builds a two-layer network that represents the maritime traffic in the monitored area, where the external layer presents the network’s basic structure and the inner layer provides precision and granularity to the representation. The method is tested in a specific scenario with high traffic density, the Baltic Sea. Experimental results reveal a decrease of over 99% storage data with a negligible precision drop. Finally, the novel method presents a light and structured representation of the maritime traffic, which sets the foundations to real-time automatic maritime traffic monitoring, anomaly detection, and situation prediction. [ABSTRACT FROM PUBLISHER]

IEEE Software editor-in-chief Forrest Shull discusses the software sustainability and his interview with Girish Seshagiri, the CEO of AIS, an organization that offers "firm fixed-price contracting with performance guarantees, including a lifetime warranty on software defects" in government contracts. In addition, he discusses the best paper award at the 21st Annual IEEE International Requirements Engineering Conference and the best research paper award at the Agile Conference. The first Web extra at http://youtu.be/L1XN0R4koRk is an audio interview highlighting IEEE Software editor in chief Forrest Shull's discussion with Girish Seshagiri, the CEO of AIS, about the organization's philosophy of offering "firm fixed-price contracting with performance guarantees, including a lifetime warranty on software defects" in government contracts. The second Web extra at http://youtu.be/iFsZlrhSM9E is the complete audio interview in which IEEE Software editor in chief Forrest Shull's speaks with Girish Seshagiri, the CEO of AIS, about the organization's philosophy of offering "firm fixed-price contracting with performance guarantees, including a lifetime warranty on software defects" in government contracts. [ABSTRACT FROM PUBLISHER]