LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization

Yuxin Yao; Liang Han; Jiangyun Wang

doi:10.1109/GNCC42960.2018.9018688

LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization

Yuxin Yao
, Liang Han
, Jiangyun Wang

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

32 Scopus citations

Abstract

According to the nonlinear characteristic of ship motion, the ship motion pose will be disturbed by coupling, indefinite period, noise signals, chaotic and some other factors, which leads that it is hard to predict ship motion in the future precisely. Based on the above, and considering the sequence of ship movement, many neural networks have been applied in ship motion prediction, such as LSTM (Long Short-Term Memory, LSTM) and ESN (Echo State Network, ESN). However, there are problems in the parameter setting of ANN (Artificial Neural Network) algorithm, that how to update network parameters during training iterations of the network to avoid iterates getting into local optimum. LSTM with PSO optimization is proposed in this paper. Testing simulation results show that the combination LSTM and PSO improves the accuracy of ship motion prediction.

Original language	English
Title of host publication	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538611715
DOIs	https://doi.org/10.1109/GNCC42960.2018.9018688
State	Published - Aug 2018
Event	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018 - Xiamen, China Duration: 10 Aug 2018 → 12 Aug 2018

Publication series

Name	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

Conference

Conference	2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018
Country/Territory	China
City	Xiamen
Period	10/08/18 → 12/08/18

Access to Document

10.1109/GNCC42960.2018.9018688

Cite this

Yao, Y., Han, L., & Wang, J. (2018). LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization. In 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018 Article 9018688 (2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/GNCC42960.2018.9018688

@inproceedings{3606a32eb75b4f27ab02404ec1eaf6d6,

title = "LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization",

abstract = "According to the nonlinear characteristic of ship motion, the ship motion pose will be disturbed by coupling, indefinite period, noise signals, chaotic and some other factors, which leads that it is hard to predict ship motion in the future precisely. Based on the above, and considering the sequence of ship movement, many neural networks have been applied in ship motion prediction, such as LSTM (Long Short-Term Memory, LSTM) and ESN (Echo State Network, ESN). However, there are problems in the parameter setting of ANN (Artificial Neural Network) algorithm, that how to update network parameters during training iterations of the network to avoid iterates getting into local optimum. LSTM with PSO optimization is proposed in this paper. Testing simulation results show that the combination LSTM and PSO improves the accuracy of ship motion prediction.",

author = "Yuxin Yao and Liang Han and Jiangyun Wang",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018 ; Conference date: 10-08-2018 Through 12-08-2018",

year = "2018",

month = aug,

doi = "10.1109/GNCC42960.2018.9018688",

language = "英语",

series = "2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018",

address = "美国",

}

Yao, Y, Han, L & Wang, J 2018, LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization. in 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018., 9018688, 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018, Institute of Electrical and Electronics Engineers Inc., 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018, Xiamen, China, 10/08/18. https://doi.org/10.1109/GNCC42960.2018.9018688

LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization. / Yao, Yuxin; Han, Liang ; Wang, Jiangyun.
2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 9018688 (2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - LSTM-PSO

T2 - 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

AU - Yao, Yuxin

AU - Han, Liang

AU - Wang, Jiangyun

PY - 2018/8

Y1 - 2018/8

N2 - According to the nonlinear characteristic of ship motion, the ship motion pose will be disturbed by coupling, indefinite period, noise signals, chaotic and some other factors, which leads that it is hard to predict ship motion in the future precisely. Based on the above, and considering the sequence of ship movement, many neural networks have been applied in ship motion prediction, such as LSTM (Long Short-Term Memory, LSTM) and ESN (Echo State Network, ESN). However, there are problems in the parameter setting of ANN (Artificial Neural Network) algorithm, that how to update network parameters during training iterations of the network to avoid iterates getting into local optimum. LSTM with PSO optimization is proposed in this paper. Testing simulation results show that the combination LSTM and PSO improves the accuracy of ship motion prediction.

AB - According to the nonlinear characteristic of ship motion, the ship motion pose will be disturbed by coupling, indefinite period, noise signals, chaotic and some other factors, which leads that it is hard to predict ship motion in the future precisely. Based on the above, and considering the sequence of ship movement, many neural networks have been applied in ship motion prediction, such as LSTM (Long Short-Term Memory, LSTM) and ESN (Echo State Network, ESN). However, there are problems in the parameter setting of ANN (Artificial Neural Network) algorithm, that how to update network parameters during training iterations of the network to avoid iterates getting into local optimum. LSTM with PSO optimization is proposed in this paper. Testing simulation results show that the combination LSTM and PSO improves the accuracy of ship motion prediction.

UR - https://www.scopus.com/pages/publications/85082467483

U2 - 10.1109/GNCC42960.2018.9018688

DO - 10.1109/GNCC42960.2018.9018688

M3 - 会议稿件

AN - SCOPUS:85082467483

T3 - 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

BT - 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 10 August 2018 through 12 August 2018

ER -

Yao Y, Han L , Wang J. LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization. In 2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 9018688. (2018 IEEE CSAA Guidance, Navigation and Control Conference, CGNCC 2018). doi: 10.1109/GNCC42960.2018.9018688

LSTM-PSO: Long Short-Term Memory Ship Motion Prediction Based on Particle Swarm Optimization

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this