An Improved Ship Trajectory Prediction Based on AIS Data Using MHA-BiGRU

Bao, Kexin; Bi, Jinqiang; Gao, Miao; Sun, Yue; Zhang, Xuefeng; Zhang, Wenjia

doi:10.3390/jmse10060804

Cited by 31 publications

(23 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this approach is highly accurate, the complexity of the calculations is high and the results are influenced by the quality and size of the dataset. Bao (Bao et al, 2022) et al used the MHA-BiGRU method based on the multi-head self-attention mechanism and the bidirectional gated cyclic unit model, which was experimentally proved to be effective in reducing the error of trajectory prediction, but the quality requirements of the data were high, and the interpretability was poor, which was difficult to understand.…”

Section: Related Workmentioning

confidence: 99%

M-STCP: an online ship trajectory cleaning and prediction algorithm using matrix neural networks

Guo,

Sun,

Xue

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Accurate prediction of ship trajectories is crucial to guarantee the safety of maritime navigation. In this paper, a matrix neural network-based online ship track cleaning and prediction algorithm called M-STCP is suggested to forecast ship tracks. Firstly, the GPS-provided historical ship trajectory data is cleaned, and the data cleaning process is finished using the anomaly point algorithm. Secondly, the trajectory is input into the matrix neural network for training and prediction, and the algorithm is improved by using Kalman filtering, which reduces the influence of noise on the prediction results and improves the prediction accuracy. In the end, the effectiveness of the method is verified using real GPS trajectory data, and compared with the GRU model and long-short-term memory networks. The M-STCP method can improve the prediction accuracy of ship trajectory to 89.44%, which is 5.17% higher than LSTM and 1.82% higher than GRU, effectively improving the prediction accuracy and time efficiency.

show abstract

Section: Related Workmentioning

confidence: 99%

M-STCP: an online ship trajectory cleaning and prediction algorithm using matrix neural networks

Guo,

Sun,

Xue

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

show abstract

“…A point worth emphasizing is that in terms of time-series prediction, compared with using RNN and its variants alone, some research work has combined the RNN model prediction output with the attention mechanism in deep learning. These results show that the introduction of attention mechanism can improve the accuracy of timing prediction to a large extent [30][31][32]. The attention mechanism is a method for rapidly selecting high-value information from huge amounts of information.…”

Section: Introductionmentioning

confidence: 98%

A Spatial-Reduction Attention-Based BiGRU Network for Water Level Prediction

Bao

et al. 2023

Water

Self Cite

View full text Add to dashboard Cite

According to the statistics of ship traffic accidents on inland waterways, potential safety hazards such as stranding, hitting rocks, and suspending navigation are on the increase because of the sudden rise and fall of the water level, which may result in fatalities, environmental devastation, and massive economic losses. In view of this situation, the purpose of this paper is to propose a high-accuracy water-level-prediction model based on the combination of the spatial-reduction attention and bidirectional gate recurrent unit (SRA-BiGRU), which provides support for ensuring the safe navigation of ships, guiding the reasonable stowage of ships, and flood prevention. The first contribution of this model is that it makes use of its strong fitting ability to capture nonlinear characteristics, and it fully considers the time series of water-level data. Secondly, the bidirectional recurrent neural network structure makes full use of past and future water-level information in the mapping process between input and output sequences. Thirdly, and most importantly, the introduction of spatial-reduction attention on the basis of BiGRU can not only automatically capture the correlations between the hidden vectors generated by BiGRU to address the issue of precision degradation due to the extended time span in water-level-forecasting tasks but can also make full use of the spatial information between water-level stations by emphasizing the influence of significant features on the prediction results. It is noteworthy that comparative experiments gradually prove the superiority of GRU, bidirectional recurrent neural network structure, and spatial-reduction attention, demonstrating that SRA-BiGRU is a water-level-prediction model with high availability, high accuracy, and high robustness.

show abstract

“…Furthermore, to pay more attention to important bidirectional temporal features so as to effectively improve the prediction performance, we add an attention mechanism to BiGRU. The attention mechanism adaptively calculates the weights for features, assigning greater weights to important features to allow them to play a larger role in prediction [17][18]. Recent studies have shown that adding attention mechanisms to models can significantly improve performance [19][20][21].…”

Section: Background Introductionmentioning

confidence: 99%

CGAOA-AttBiGRU: A novel deep learning framework for forecasting CO 2 emissions

Liu,

Wu,

Shan

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Accurately predicting carbon dioxide (CO2) emissions is crucial for environmental protection. Currently, there are two main issues with predicting CO2 emissions: (1) existing CO2 emission prediction models mainly rely on such as Long Short-Term Memory (LSTM) and Gate Recurrent Unit (GRU), which can only model unidirectional temporal features, resulting in insufficient accuracy: (2) existing research on CO2 emissions mainly focuses on designing predictive models, without paying attention to model optimization, resulting in models being unable to achieve their optimal performance. Methods: To address the aforementioned issues, this paper proposed a framework for predicting CO2 emissions, named as CGAOA-AttBiGRU. In this framework, Attentional-Bidirectional Gate Recurrent Unit (AttBiGRU) is a prediction model that uses BiGRU units to extract bidirectional temporal features from the data, and adopts an attention mechanism to adaptively weight the bidirectional temporal features, thereby improving prediction accuracy. CGAOA is an improved Arithmetic Optimization Algorithm (AOA) used to optimize the 5 key hyperparameters of the AttBiGRU. Results: We first validated the optimization performance of the improved CGAOA algorithm on 24 benchmark functions. Then, CGAOA was used to optimize AttBiGRU and compared with 12 optimization algorithms. The results indicate that the AttBiGRU optimized by CGAOA has the best predictive performance. Finally, the optimized AttBiGRU was compared with the BiGRU, LSTM, GRU, ANN, and SVM on predicting CO2 emissions from 4 sectors in China. The experimental results showed that AttBiGRU is significantly better than the comparison models. Conclusions: This paper proposed a novel framework, CGAOA-AttBiGRU, for predicting CO2 emissions. This framework not only includes predictive models, but also optimization method for the models. This study will guide researchers to not only focus on proposing new predictive models, but also on model optimization.

show abstract

An Improved Ship Trajectory Prediction Based on AIS Data Using MHA-BiGRU

Cited by 31 publications

References 35 publications

M-STCP: an online ship trajectory cleaning and prediction algorithm using matrix neural networks

M-STCP: an online ship trajectory cleaning and prediction algorithm using matrix neural networks

A Spatial-Reduction Attention-Based BiGRU Network for Water Level Prediction

CGAOA-AttBiGRU: A novel deep learning framework for forecasting CO 2 emissions

Contact Info

Product

Resources

About