Predicting Ships Estimated Time of Arrival based on AIS Data

Mekkaoui, Sara El; Benabbou, Loubna; Berrado, Abdelaziz

doi:10.1145/3419604.3419768

Cited by 10 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Analisando a aplicação de técnicas de regressão no contexto de embarcações marítimas, Mekkaoui et al (2020) apresentam abordagens existentes para prever o tempo estimado de chegada (ETA) dos navios, utilizando modelos de Redes Neurais (NN) para realizar a previsão. O modelo que apresentou melhor desempenho foi uma rede neural recorrente Long-Short Term Memory (LSTM).…”

Section: Revisão Da Literaturaunclassified

Previsão da duração de carregamentos de embarcações PLSV

Ventriglia

Bastos

Figueiredo

et al. 2022

Anais Do XIX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2022)

View full text Add to dashboard Cite

As embarcações Pipe-laying Support Vessel (PLSV) realizam tarefas de interligação submarinas, que necessitam de diversos recursos materiais. Estes recursos são carregados nos navios, e atualmente o planejamento dos carregamentos é resolvido de forma heurística, com taxas de erros altas, em torno de 84%. Com o objetivo de auxiliar neste planejamento operacional, este trabalho propôs a investigação e seleção de diversos modelos de aprendizado de máquina para prever a duração dos carregamentos. Os modelos que apresentaram melhor desempenho na base de teste foram o Gradient Boosting, Regressão Linear e o Stacking Regressor, com um erro percentual médio absoluto de no máximo 36% nos dados de teste.

show abstract

Section: Revisão Da Literaturaunclassified

Previsão da duração de carregamentos de embarcações PLSV

Ventriglia

Bastos

Figueiredo

et al. 2022

Anais Do XIX Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2022)

View full text Add to dashboard Cite

show abstract

“…Until now, a number of studies have employed various data sources (e.g., AIS, GPS or sonar data) to classify ships' movements (Pallotta et al, 2013;Wijaya and Nakamura, 2013;Yuan et al, 2019;El Mekkaoui et al, 2020;Gao et al, 2021). In this section, we specifically review the studies that have used the AIS data for collision avoidance model development.…”

Section: Related Workmentioning

confidence: 99%

A semi-supervised deep learning model for ship encounter situation classification

et al. 2021

View full text Add to dashboard Cite

“…The other means for inland ship surveillance include automatic identification system (AIS) [6,7], video surveillance [8][9][10], wireless sensor network [11], and synthetic aperture radar (SAR) imaging [12][13][14]. Limitations are obvious in these methods.…”

Section: Introductionmentioning

confidence: 99%

A Grid-Based Gradient Descent Extended Target Clustering Method and Ship Target Inverse Synthetic Aperture Radar Imaging for UHF Radar

Zhang,

Zhou,

Bai

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Inland shipping is of great significance in economic development, and ship surveillance and classification are of great importance for ship management and dispatch. For river ship detection, ultrahigh-frequency (UHF) radar is an effective equipment owing to its wide coverage and easy deployment. The extension in range, Doppler, and azimuth and target recognition are two main problems in UHF ship detection. Clustering is a necessary step to get the center of an extended target. However, it is difficult to distinguish between different target echoes when they overlap each other in range, Doppler, and azimuth and so far practical methods for extended target recognition with UHF radar have been rarely discussed. In this study, a two-stage target classification method is proposed for UHF radar ship detection. In the first stage, grid-based gradient descent (GBGD) clustering is proposed to distinguish targets with three-dimensional (3D) information. Then in the second stage, the inverse synthetic aperture radar (ISAR) imaging algorithm is employed to differentiate ships of different types. The simulation results show that the proposed method achieves a 20% higher clustering accuracy than other methods when the targets have close 3D information. The feasibility of ISAR imaging for target classification using UHF radar is also validated via simulation. Some experimental results are also given to show the effectiveness of the proposed method.

show abstract

Predicting Ships Estimated Time of Arrival based on AIS Data

Cited by 10 publications

References 13 publications

Previsão da duração de carregamentos de embarcações PLSV

Previsão da duração de carregamentos de embarcações PLSV

A semi-supervised deep learning model for ship encounter situation classification

A Grid-Based Gradient Descent Extended Target Clustering Method and Ship Target Inverse Synthetic Aperture Radar Imaging for UHF Radar

Contact Info

Product

Resources

About