scholarly journals Improving Near Miss Detection in Maritime Traffic in the Northern Baltic Sea from AIS Data

2021 ◽  
Vol 9 (2) ◽  
pp. 180
Author(s):  
Lei Du ◽  
Osiris A. Valdez Banda ◽  
Floris Goerlandt ◽  
Pentti Kujala ◽  
Weibin Zhang
Keyword(s):  
Baltic Sea ◽  
Perceived Risk ◽  
Maritime Transportation ◽  
Near Miss ◽  
Automatic Identification ◽  
Identification System ◽  
Collision Risk ◽  
Ship Collision ◽  
The Impact ◽  
Ship Behavior

Ship collision is the most common type of accident in the Northern Baltic Sea, posing a risk to the safety of maritime transportation. Near miss detection from automatic identification system (AIS) data provides insight into maritime transportation safety. Collision risk always triggers a ship to maneuver for safe passing. Some frenetic rudder actions occur at the last moment before ship collision. However, the relationship between ship behavior and collision risk is not fully clarified. Therefore, this work proposes a novel method to improve near miss detection by analyzing ship behavior characteristic during the encounter process. The impact from the ship attributes (including ship size, type, and maneuverability), perceived risk of a navigator, traffic complexity, and traffic rule are considered to obtain insights into the ship behavior. The risk severity of the detected near miss is further quantified into four levels. This proposed method is then applied to traffic data from the Northern Baltic Sea. The promising results of near miss detection and the model validity test suggest that this work contributes to the development of preventive measures in maritime management to enhance to navigational safety, such as setting a precautionary area in the hotspot areas. Several advantages and limitations of the presented method for near miss detection are discussed.

scholarly journals A Framework of A Ship Domain-Based Near-Miss Detection Method Using Mamdani Neuro-Fuzzy Classification

2018 ◽  
Vol 25 (s1) ◽  
pp. 14-21 ◽  
Author(s):  
Rafał Szłapczyński ◽  
Tacjana Niksa-Rynkiewicz
Keyword(s):  
Risk Measures ◽  
Risk Measure ◽  
Near Miss ◽  
Fuzzy Classification ◽  
Automatic Identification ◽  
Identification System ◽  
Collision Risk ◽  
Neuro Fuzzy ◽  
Fuzzy Network

Abstract Safety analysis of navigation over a given area may cover application of various risk measures for ship collisions. One of them is percentage of the so called near-miss situations (potential collision situations). In this article a method of automatic detection of such situations based on the data from Automatic Identification System (AIS), is proposed. The method utilizes input parameters such as: collision risk measure based on ship’s domain concept, relative speed between ships as well as their course difference. For classification of ships encounters, there is used a neuro-fuzzy network which estimates a degree of collision hazard on the basis of a set of rules. The worked out method makes it possibile to apply an arbitrary ship’s domain as well as to learn the classifier on the basis of opinions of experts interpreting the data from the AIS.

scholarly journals A Novel Framework of Real-Time Regional Collision Risk Prediction Based on the RNN Approach

2020 ◽  
Vol 8 (3) ◽  
pp. 224 ◽  
Author(s):  
Dapei Liu ◽  
Xin Wang ◽  
Yao Cai ◽  
Zihao Liu ◽  
Zheng-Jiang Liu
Keyword(s):  
Real Time ◽  
Shapley Value ◽  
Spatial Clustering ◽  
Risk Identification ◽  
Maritime Transportation ◽  
Automatic Identification ◽  
Identification System ◽  
Collision Risk ◽  
Short Time ◽  
Sea Area

Regional collision risk identification and prediction is important for traffic surveillance in maritime transportation. This study proposes a framework of real-time prediction for regional collision risk by combining Density-Based Spatial Clustering of Applications with Noise (DBSCAN) technique, Shapley value method and Recurrent Neural Network (RNN). Firstly, the DBSCAN technique is applied to cluster vessels in specific sea area. Then the regional collision risk is quantified by calculating the contribution of each vessel and each cluster with Shapley value method. Afterwards, the optimized RNN method is employed to predict the regional collision risk of specific seas in short time. As a result, the framework is able to determine and forecast the regional collision risk precisely. At last, a case study is carried out with actual Automatic Identification System (AIS) data, the results show that the proposed framework is an effective tool for regional collision risk identification and prediction.

Simulation-Based Estimation of Collision Risk During Ship Maneuvering in Two-Lane Canal Using Mathematical Maneuvering Group Model and Automatic Identification System Data

2014 ◽  
Author(s):  
I. Putu Sindhu Asmara ◽  
Eiichi Kobayashi ◽  
Ketut Buda Artana ◽  
Agoes A. Masroeri ◽  
Nobukazu Wakabayashi
Keyword(s):  
Research Area ◽  
Automatic Identification ◽  
Identification System ◽  
Group Model ◽  
Collision Risk ◽  
Ship Maneuvering ◽  
Automatic Identification System ◽  
Mmg Model ◽  
Simulation Based ◽  
The Impact

This paper proposes a simulation-based method to estimate collision risk for a ship operating in a two-lane canal. According to rule 9 of the Colreg-72 navigation rules, in a narrow canal, a vessel shall keep as near to the wall that lies on its starboard side. However, a busy harbor entered through a narrow canal still presents impact hazards. Certain conditions in a two-lane canal, such as a head-on situation in the straight part of the canal during an overtaking maneuver and large curvature of a turning maneuver in the bend part of the canal, could lead to accidents. In the first condition, the ship alters its own course to the port side to overtake another ship in the same lane but the course altered is too large and hits the wall of the canal. In the second condition, the target ship may take an excessively large turn on the bend part of the canal, causing collision with the ship on the opposite lane. Collision risk is represented as the risk of damage to the ship structure and includes the probability of impact accident and severity of structural damage. Predictions of collision probabilities in a two-lane canal have been developed based on a simulation of ship maneuvering using a mathematical maneuvering group (MMG) model and automatic identification system (AIS) data. First, the propeller revolution and rudder angle of the subject ship are simulated to determine safe trajectories in both parts of the canal. Second, impact accidents are simulated for both conditions. The ship’s speed, and current and wind velocity are randomly simulated based on the distribution of the AIS and environment data for the research area. The structural consequences of the impact accident are measured as collision energy losses, based on the external dynamics of ship collision. The research area of the two-lane canal is located at the Madura Strait between the Java and Madura islands in East Java of Indonesia, as shown by the red line in Figure 1. A project for developing a new port and dredging a new two-lane canal to facilitate an increase in the number of ship calls is currently underway in the research area. Figure 1 shows the ships’ trajectories plotted using the AIS data as on January 1, 2011. The trajectories are mostly seen to be coming out of the canal, confirming that it is shallow and needs to be dredged.

Use of AIS Data to Characterise Marine Traffic Patterns and Ship Collision Risk off the Coast of Portugal

2013 ◽  
Vol 66 (6) ◽  
pp. 879-898 ◽  
Author(s):  
P.A.M. Silveira ◽  
A.P. Teixeira ◽  
C. Guedes Soares
Keyword(s):  
Automatic Identification ◽  
Identification System ◽  
Relative Importance ◽  
Traffic Patterns ◽  
Collision Risk ◽  
Expected Number ◽  
Maritime Traffic ◽  
Marine Traffic ◽  
Control Centre ◽  
Ship Collision

This paper studies the risk of ship collision off the coast of Portugal based on Automatic Identification System (AIS) data, which is recorded and maintained by the Portuguese coastal Vessel Traffic Service (VTS) control centre (CCTMC). Computer programs for decoding, visualization and analysis of the AIS data have been developed. From analysis of the AIS data available, maritime traffic off the coast of Portugal is characterized and a statistical analysis of traffic in the Traffic Separation Schemes is provided. An algorithm has been developed to assess the risk profile and the relative importance of routes associated with ports. A method is proposed to calculate the collision risk from the assessment of the number of collision candidates by estimating future distances between ships based on their previous positions, courses and speeds, and comparing those distances with a defined collision diameter. Values of causation probability suggested in several studies are used to calculate the expected number of collisions in the period of time under investigation based on the number of collision candidates. The results of this study are then compared with the number of collisions that have occurred between 1997–2006, registered and maintained by the Portuguese Maritime Authority.

Automatic identification system data-driven model for analysis of ship domain near bridge-waters

2021 ◽  
pp. 1-22
Author(s):  
Lei Jinyu ◽  
Liu Lei ◽  
Chu Xiumin ◽  
He Wei ◽  
Liu Xinglong ◽  
...  
Keyword(s):  
Least Squares Method ◽  
Automatic Identification ◽  
Identification System ◽  
Collision Risk ◽  
Automatic Identification System ◽  
Domain Models ◽  
System Data ◽  
Quantification Model ◽  
Highly Correlated

Abstract The ship safety domain plays a significant role in collision risk assessment. However, few studies take the practical considerations of implementing this method in the vicinity of bridge-waters into account. Therefore, historical automatic identification system data is utilised to construct and analyse ship domains considering ship–ship and ship–bridge collisions. A method for determining the closest boundary is proposed, and the boundary of the ship domain is fitted by the least squares method. The ship domains near bridge-waters are constructed as ellipse models, the characteristics of which are discussed. Novel fuzzy quaternion ship domain models are established respectively for inland ships and bridge piers, which would assist in the construction of a risk quantification model and the calculation of a grid ship collision index. A case study is carried out on the multi-bridge waterway of the Yangtze River in Wuhan, China. The results show that the size of the ship domain is highly correlated with the ship's speed and length, and analysis of collision risk can reflect the real situation near bridge-waters, which is helpful to demonstrate the application of the ship domain in quantifying the collision risk and to characterise the collision risk distribution near bridge-waters.

Performance Bounds for VDES R-mode

2019 ◽  
Vol 73 (1) ◽  
pp. 92-114 ◽  
Author(s):  
Jan Šafář ◽  
Alan Grant ◽  
Paul Williams ◽  
Nick Ward
Keyword(s):  
Data Exchange ◽  
Estimation Error ◽  
Additive White Gaussian Noise ◽  
Automatic Identification ◽  
Identification System ◽  
Performance Bounds ◽  
Radio Communication ◽  
Very High Frequency ◽  
Radio Communication System ◽  
The Impact

The Very High Frequency (VHF) Data Exchange System (VDES) is a new radio communication system being developed by the international maritime community, with the principal objectives to safeguard existing Automatic Identification System (AIS) core functions and enhance maritime communication applications, based on robust, efficient and secure data transmission with wider bandwidth than the AIS. VDES is also being considered as a potential component of the R-mode concept, where the same signals used for communication are also used for ranging, thus mitigating the impact of disruptions to satellite positioning services. This paper establishes statistical performance bounds on the ranging precision of VDES R-mode, assuming an additive white Gaussian noise propagation channel. Modified Cramér-Rao bounds on the pseudorange estimation error are provided for all waveforms currently proposed for use in terrestrial VDES communications. These are then used to estimate the maximum usable ranges for AIS/VDES R-mode stations. The results show that, under the assumed channel conditions, all of the new VDES waveforms provide better ranging performance than the AIS waveform, with the best performance being achieved using the 100 kHz bandwidth terrestrial VDE waveforms.

scholarly journals Deep Learning in Unmanned Surface Vehicles Collision-Avoidance Pattern Based on AIS Big Data with Double GRU-RNN

2020 ◽  
Vol 8 (9) ◽  
pp. 682
Author(s):  
Jia-hui Shi ◽  
Zheng-jiang Liu
Keyword(s):  
Big Data ◽  
Collision Avoidance ◽  
Difficult Problem ◽  
Automatic Identification ◽  
Identification System ◽  
Unmanned Surface Vehicle ◽  
Effective Learning ◽  
Maritime Navigation ◽  
Ship Collision ◽  
Gated Recurrent Unit

There is a collection of a large amount of automatic identification system (AIS) data that contains ship encounter information, but mining the collision avoidance knowledge from AIS big data and carrying out effective machine learning is a difficult problem in current maritime field. Herein, first the Douglas–Peucker (DP) algorithm was used to preprocess the AIS data. Then, based on the ship domain the risk of collision was identified. Finally, a double-gated recurrent unit neural network (GRU-RNN) was constructed to learn unmanned surface vehicle (USV) collision avoidance decision from the extracted data of successful encounters of ships. The double GRU-RNN was trained on the 2015 Tianjin Port AIS dataset to realize the effective learning of ship encounter data. The results indicated that the double GRU-RNN could effectively learn the collision avoidance pattern hidden in AIS big data, and generate corresponding ship collision-avoidance decisions for different maritime navigation states. This study contributes significantly to the increased efficiency and safety of sea operations. The proposed method could be potentially applied to USV technology and intelligence collision avoidance.

scholarly journals Ship-Collision Avoidance Decision-Making Learning of Unmanned Surface Vehicles with Automatic Identification System Data Based on Encoder—Decoder Automatic-Response Neural Networks

2020 ◽  
Vol 8 (10) ◽  
pp. 754
Author(s):  
Miao Gao ◽  
Guo-You Shi
Keyword(s):  
Neural Networks ◽  
Decision Making ◽  
Time Series ◽  
Collision Avoidance ◽  
Time Series Data ◽  
Series Data ◽  
Automatic Identification ◽  
Identification System ◽  
Automatic Response ◽  
Ship Collision

Intelligent unmanned surface vehicle (USV) collision avoidance is a complex inference problem based on current navigation status. This requires simultaneous processing of the input sequences and generation of the response sequences. The automatic identification system (AIS) encounter data mainly include the time-series data of two AIS sets, which exhibit a one-to-one mapping relation. Herein, an encoder–decoder automatic-response neural network is designed and implemented based on the sequence-to-sequence (Seq2Seq) structure to simultaneously process the two AIS encounter trajectory sequences. Furthermore, this model is combined with the bidirectional long short-term memory recurrent neural networks (Bi-LSTM RNN) to obtain a network framework for processing the time-series data to obtain ship-collision avoidance decisions based on big data. The encoder–decoder neural networks were trained based on the AIS data obtained in 2018 from Zhoushan Port to achieve ship collision avoidance decision-making learning. The results indicated that the encoder–decoder neural networks can be used to effectively formulate the sequence of the collision avoidance decision of the USV. Thus, this study significantly contributes to the increased efficiency and safety of maritime transportation. The proposed method can potentially be applied to the USV technology and intelligent collision-avoidance systems.

Sign in / Sign up

Export Citation Format

Share Document