A multi-task analysis and modelling paradigm using LSTM for multi-source monitoring data of inland vessels

Abstract The vessel monitoring data provide important information for people to understand the vessel dynamic status in real time and make appropriate decisions in vessel management and operations. However, some of the essential data may be incomplete or unavailable. In order to recover or predict the missing information and best exploit the vessels monitoring data, this paper combines statistical analysis, data mining and neural network methods to propose a multi-task analysis and modelling framework for multi-source monitoring data of inland vessels. Specifically, an advanced neural network, Long Short-Term Memory (LSTM) was tailored and employed to tackle three important tasks, including vessel trajectory repair, engine speed modelling and fuel consumption prediction. The developed models have been validated using the real-life vessel monitoring data and shown to outperform some other widely used modelling methods. In addition, statistics and data technologies were employed for data extraction, classification and cleaning, and an algorithm was designed for identification of the vessel navigational state.

[1]  Witold Abramowicz,et al.  Big Data for Anomaly Detection in Maritime Surveillance: Spatial AIS Data Analysis for Tankers , 2018, Zeszyty Naukowe Akademii Marynarki Wojennej.

[2]  Xuelin Wang,et al.  Research on the Development Path of Blockchain in Shipping Industry , 2018, APCIM & ICTTE 2018.

[3]  Dong Ryeol Shin,et al.  A Survey of Intelligent Transportation Systems , 2011, 2011 Third International Conference on Computational Intelligence, Communication Systems and Networks.

[4]  Silvio Savarese,et al.  Social LSTM: Human Trajectory Prediction in Crowded Spaces , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Maria Riveiro,et al.  Maritime anomaly detection: A review , 2018, WIREs Data Mining Knowl. Discov..

[6]  Xinping Yan,et al.  A novel method for restoring the trajectory of the inland waterway ship by using AIS data , 2015 .

[7]  B.J. Rhodes,et al.  Maritime situation monitoring and awareness using learning mechanisms , 2005, MILCOM 2005 - 2005 IEEE Military Communications Conference.

[8]  Davide Anguita,et al.  Vessels fuel consumption forecast and trim optimisation: A data analytics perspective , 2017 .

[9]  Jarke J. van Wijk,et al.  Eurographics/ Ieee-vgtc Symposium on Visualization 2009 Visualization of Vessel Movements , 2022 .

[10]  Naixue Xiong,et al.  A Dimensionality Reduction-Based Multi-Step Clustering Method for Robust Vessel Trajectory Analysis , 2017, Sensors.

[11]  Yu Huang,et al.  Trajectory compression-guided visualization of spatio-temporal AIS vessel density , 2016, 2016 8th International Conference on Wireless Communications & Signal Processing (WCSP).

[12]  Yang Wang,et al.  Fuzzy logic based dynamic decision-making system for intelligent navigation strategy within inland traffic separation schemes , 2020 .

[13]  C. Guedes Soares,et al.  Fuzzy logic based approach for ship-bridge collision alert system , 2019, Ocean Engineering.

[14]  Rikard Laxhammar,et al.  Anomaly detection for sea surveillance , 2008, 2008 11th International Conference on Information Fusion.

[15]  Lily Rachmawati,et al.  An Automatic Identification System (AIS) Database for Maritime Trajectory Prediction and Data Mining , 2016, ArXiv.

[16]  J. Adams,et al.  Conservation science and policy applications of the marine vessel Automatic Identification System (AIS)—a review , 2016 .

[17]  Kevin B. Korb,et al.  Anomaly detection in vessel tracks using Bayesian networks , 2014, Int. J. Approx. Reason..

[18]  Alicja Kolasa-Wiecek,et al.  Stepwise multiple regression method of greenhouse gas emission modeling in the energy sector in Poland. , 2015, Journal of environmental sciences.

[19]  姜青山,et al.  Trajectory Clustering by Sampling and Density , 2014 .

[20]  T. Notteboom,et al.  Container barge network development in inland rivers: A comparison between the Yangtze River and the Rhine River , 2020 .

[21]  Naixue Xiong,et al.  Spatio-Temporal Vessel Trajectory Clustering Based on Data Mapping and Density , 2018, IEEE Access.

[22]  Leto Peel,et al.  Maritime anomaly detection using Gaussian Process active learning , 2012, 2012 15th International Conference on Information Fusion.

[23]  Ratna Babu Chinnam,et al.  An HMM and polynomial regression based approach for remaining useful life and health state estimation of cutting tools , 2019, Comput. Ind. Eng..

[24]  Lars Linsen,et al.  Comprehensive Analysis of Automatic Identification System (AIS) Data in Regard to Vessel Movement Prediction , 2014 .

[25]  Xinping Yan,et al.  Research and Development of Intelligent Transportation Systems , 2012, 2012 11th International Symposium on Distributed Computing and Applications to Business, Engineering & Science.

[26]  Jürgen Schmidhuber,et al.  Learning to Forget: Continual Prediction with LSTM , 2000, Neural Computation.

[27]  Qiang Meng,et al.  A novel ship trajectory reconstruction approach using AIS data , 2018, Ocean Engineering.

[28]  Giuliana Pallotta,et al.  Maritime Traffic Networks: From Historical Positioning Data to Unsupervised Maritime Traffic Monitoring , 2018, IEEE Transactions on Intelligent Transportation Systems.

[29]  Niklas Lavesson,et al.  Open data for anomaly detection in maritime surveillance , 2013, Expert Syst. Appl..

[30]  Peter C. Y. Chen,et al.  LSTM network: a deep learning approach for short-term traffic forecast , 2017 .

[31]  Mark R. Morelande,et al.  Statistical analysis of motion patterns in AIS Data: Anomaly detection and motion prediction , 2008, 2008 11th International Conference on Information Fusion.

[32]  Leto Peel,et al.  Fast Maritime Anomaly Detection using KD Tree Gaussian Processes , 2011 .

[33]  N. Jayadas,et al.  A Demand Forecast Model based on Moving Average and Markov Method , 2015 .