Visualization and visual analysis of vessel trajectory data: A survey

Current fifth-generation (5G) networks do not cover maritime areas, causing difficulties in developing maritime Internet of Things (IoT). To tackle this problem, we establish a nearshore network by collaboratively using on-shore terrestrial base stations (TBSs) and tethered unmanned aerial vehicles (UAVs). These TBSs and UAVs form virtual clusters in a user-centric manner. Within each virtual cluster, non-orthogonal multiple access (NOMA) is adopted for agilely including various maritime IoT devices, which are sparsely distributed over the vast ocean. The nearshore network also shares the spectrum with marine satellites. In such a NOMA-based hybrid satellite-UAV-terrestrial network, interference among different network segments, different clusters, and different users occurs. We thereby formulate a joint power allocation problem to maximize the sum rate of the network. Different from existing studies, we use large-scale channel state information (CSI) only for optimization to reduce system overhead. The large-scale CSI is obtained by using the position information of maritime IoT devices. The problem is non-convex with intractable non-linear constraints. We tackle these difficulties by adopting max-min optimization, the auxiliary function method, and the successive convex approximation technique. An iterative power allocation algorithm is accordingly proposed, which is shown to be effective for coverage enhancement by simulations. This shows the potential of NOMA-based hybrid satellite-UAV-terrestrial networks for maritime on-demand coverage. 

/pdf/noma-based-hybrid-satellite-uav-terrestrial-networks-for-6g-3rrhslti.pdf

NOMA-Based Hybrid Satellite-UAV-Terrestrial Networks for 6G Maritime Coverage

The convergence of Maritime Transportation Systems (MTS) and Internet of Things (IoT) has led to the promising IoT-empowered MTS (IoT-MTS). However, abnormal trajectories of maritime transportation ships can have highly negative impacts on the management of IoT-MTS. Therefore, anomaly detection of trajectories is important for the successful deployment of IoT-MTS. In this paper, we propose a Transfer Learning based Trajectory Anomaly Detection strategy, named TLTAD, for IoT-MTS. Specifically, a variational autoencoder is used to discover the potential connections between each dimension of the normal trajectory, while a graph variational autoencoder is used to explore the spatial similarity between normal trajectories. Based on internal connection of trajectories, a deep reinforcement learning algorithm, Twin Delayed Deep Deterministic policy gradient (TD3), is employed to train the trajectory anomaly detection model. To reduce the model training time, transfer learning is used to migrate the trained anomaly detection model between different regions of an ocean area or between similar ocean areas. Moreover, an efficient data transformation module is designed to improve the efficiency of model transfer. The experiments were conducted on a real-world automatic identification system (AIS) dataset. The results indicate that the proposed TLTAD can provide accurate anomaly detection on ships’ trajectories in IoT-MTS with reduced model training times.

Intelligent Anomaly Detection of Trajectories for IoT Empowered Maritime Transportation Systems

The convergence of Maritime Transportation Systems (MTS) and Internet of Things (IoT) has led to the promising IoT-empowered MTS (IoT-MTS). However, abnormal trajectories of maritime transportation ships can have highly negative impacts on the management of IoT-MTS. Therefore, anomaly detection of trajectories is important for the successful deployment of IoT-MTS. In this paper, we propose a Transfer Learning based Trajectory Anomaly Detection strategy, named TLTAD, for IoT-MTS. Specifically, a variational autoencoder is used to discover the potential connections between each dimension of the normal trajectory, while a graph variational autoencoder is used to explore the spatial similarity between normal trajectories. Based on internal connection of trajectories, a deep reinforcement learning algorithm, Twin Delayed Deep Deterministic policy gradient (TD3), is employed to train the trajectory anomaly detection model. To reduce the model training time, transfer learning is used to migrate the trained anomaly detection model between different regions of an ocean area or between similar ocean areas. Moreover, an efficient data transformation module is designed to improve the efficiency of model transfer. The experiments were conducted on a real-world automatic identification system (AIS) dataset. The results indicate that the proposed TLTAD can provide accurate anomaly detection on ships’ trajectories in IoT-MTS with reduced model training times. 

As popular as the application of Proportional Integral Derivative (PID) controller is, issues relating to saturation effects are still being addressed using different techniques.  Amongst such techniques are clamping anti-windup technique and back-calculation anti-windup techniques which primary prevent the integral term of the PID control action from reaching saturation. Separate tracking time technique was applied to both cases of anti-windup techniques investigated in this research unlike the conventional tracking time.  These anti-windup controllers were used to control the operation of a motorized globe valve.  The results obtained after simulation in MATLAB Simulink environment showed that both techniques gave similar outputs with a stable response of magnitude 0.95 at 1.5 seconds settling time when a unit step reference input signal was applied as compared to conventional PID controller that had an overshoot of 1.04 before settling to a magnitude of 1.0 at 1.5 seconds. Vibration, instability, and operational distortion were experienced when the anti-windup techniques were cascaded.  The same responses were obtained when their outputs were combined to control the motorized globe valve.  Other interesting mathematical models of important components are contained in the full paper.

/pdf/performance-and-configuration-analysis-of-tracking-time-anti-4152vhyend.pdf

Performance and Configuration Analysis of Tracking Time Anti-Windup PID Controllers

Tide variations are affected not only by periodic movement of celestial bodies but also by time-varying interference from the external environment. To improve the accuracy of tide prediction, a modular tide level prediction model (HA-NARX) is proposed. This model divides tide data into two parts: astronomical tide data affected by celestial tide-generating forces and nonastronomical tide data affected by various environmental factors. Final tide prediction results are obtained using a nonlinear autoregressive exogenous model (NARX) neural network combined with harmonic analysis (HA) data. To verify the feasibility of the model, tide data under different climatic and geographical conditions are used to simulate the prediction of tide levels, and the results are compared with those of traditional HA, the genetic algorithm-back propagation (GA-BP) neural network and the wavelet neural network (WNN). The results show that the greater the influence of meteorological factors on tides, the more obvious is the improvement in accuracy and stability of HA-NARX prediction results compared to traditional models, with the highest prediction accuracy improvement of 234%. The proposed model not only has a simple structure but can also effectively improve the stability and accuracy of tide prediction.

/pdf/a-modular-tide-level-prediction-method-based-on-a-narx-8fmm9ex2cg.pdf

A Modular Tide Level Prediction Method Based on a NARX Neural Network

For analyzing the distribution characteristics of maritime traffic dangers and ensure the safety of ships navigating at sea, plotting the ship’s trajectory and making statistic based on the relevant dynamic data that can be extracted and analyzed from the Automatic Indentification System (AIS) information, the Distance to Closet Point of Approach (DCPA) between any two ships have been computed and applied. Through constructing the innovative three-dimensional bubbles chart to reflect the spatial characteristics from the DCPA matrix. Utilizing the Kernel Density Estimation (KDE) method, draws the heat map in the vicinity of San Diego sea area, measures the traffic danger characteristics of the costal sea area, and compares the analysis results with ArcGIS Pro 2.3. It reflects that the analysis results are consistent with the actual situation. The heat map has the powerful scientificity and practicability, can accurately measure the traffic distribution in the sea area, and provides auxiliary references for the planning and design of the ship's routing system and maritime traffic safety management.

AIS Data-Based for Statistics and Analysis of Maritime Traffic Dangerous Features: A Case Study of San Diego Costal Water

The control of the ship's course determines the correctness of navigation, ensures the correct destination, and plays a significant role in the navigation of the ship. Based on RBF neural network and ship mathematical model, a predictive controller using Euclidean distance to calculate center vector for network learning is designed to predict and adjust the three parameters of PID in real time and online, so as to obtain the optimal PID parameters faster. By supervised learning ensuring the course to meet the requirements and the stable navigation of the ship. Then the simulation experiment is carried out to verify the accuracy of the designed controller in Simulink environment of MATLAB software. Compared with the traditional PID controller, this method of this paper reduces the overshoot of the system and the setting time, and improves the accuracy of the ship's course automatic control simultaneously. In addition, the simulation results of ship course control simulation demonstrate the better adaptability, robustness and anti-interference ability of the intelligent PID control strategy.

Lianbo Li

Papers

A Modular Tide Level Prediction Method Based on a NARX Neural Network

AIS Data-Based for Statistics and Analysis of Maritime Traffic Dangerous Features: A Case Study of San Diego Costal Water

RBF-Network-Based Predictive Ship Course Control