A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention

Yunqiao Xi; Junping Zhang; Jian Liu; Linlin Wang; Hongfeng Xu; Linxiu Chen; Jixiang Jiang

doi:10.1109/EIECS59936.2023.10435465

A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention

Yunqiao Xi
, Junping Zhang^*
, Jian Liu
, Linlin Wang
, Hongfeng Xu
, Linxiu Chen
, Jixiang Jiang

^*Corresponding author for this work

School of Electronics and Information Engineering, Harbin Institute of Technology
National Key Laboratory of Complex System Control and Intelligent Agent Cooperation

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

2 Scopus citations

Abstract

To solve the problem that current dynamic intention recognition methods fail to make full use of time domain variation information between multi-temporal group targets, which leads to low accuracy of intention recognition. This paper proposes a bidirectional convolutional long short term memory-attention network for marine formation target intention recognition. The network takes the multi-source trajectory data of the marine ship formation target as the input, extracts and uses the target change rule and time domain characteristics of the Marine formation data, and trains the model to have the ability to independently learn the weight of information in different time periods. The simulation results show that the method has good performance and can meet the needs of practical application.

Original language	English
Title of host publication	2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	252-255
Number of pages	4
ISBN (Electronic)	9798350316674
DOIs	https://doi.org/10.1109/EIECS59936.2023.10435465
State	Published - 2023
Externally published	Yes
Event	3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023 - Hybrid, Changchun, China Duration: 22 Sep 2023 → 24 Sep 2023

Publication series

Name	2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023

Conference

Conference	3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023
Country/Territory	China
City	Hybrid, Changchun
Period	22/09/23 → 24/09/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 14 Life Below Water

Keywords

intention recognition
long short-term
marinship formation
temporal features

Access to Document

10.1109/EIECS59936.2023.10435465

Cite this

Xi, Y., Zhang, J., Liu, J., Wang, L., Xu, H., Chen, L., & Jiang, J. (2023). A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention. In 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023 (pp. 252-255). (2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EIECS59936.2023.10435465

Xi, Yunqiao ; Zhang, Junping ; Liu, Jian et al. / A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention. 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 252-255 (2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023).

@inproceedings{cba2a338d9b14d51be4979a3eff07bab,

title = "A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention",

abstract = "To solve the problem that current dynamic intention recognition methods fail to make full use of time domain variation information between multi-temporal group targets, which leads to low accuracy of intention recognition. This paper proposes a bidirectional convolutional long short term memory-attention network for marine formation target intention recognition. The network takes the multi-source trajectory data of the marine ship formation target as the input, extracts and uses the target change rule and time domain characteristics of the Marine formation data, and trains the model to have the ability to independently learn the weight of information in different time periods. The simulation results show that the method has good performance and can meet the needs of practical application.",

keywords = "intention recognition, long short-term, marinship formation, temporal features",

author = "Yunqiao Xi and Junping Zhang and Jian Liu and Linlin Wang and Hongfeng Xu and Linxiu Chen and Jixiang Jiang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023 ; Conference date: 22-09-2023 Through 24-09-2023",

year = "2023",

doi = "10.1109/EIECS59936.2023.10435465",

language = "英语",

series = "2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023",

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

pages = "252--255",

booktitle = "2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023",

address = "美国",

}

Xi, Y, Zhang, J, Liu, J, Wang, L, Xu, H, Chen, L & Jiang, J 2023, A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention. in 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023. 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023, Institute of Electrical and Electronics Engineers Inc., pp. 252-255, 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023, Hybrid, Changchun, China, 22/09/23. https://doi.org/10.1109/EIECS59936.2023.10435465

A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention. / Xi, Yunqiao; Zhang, Junping; Liu, Jian et al.
2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 252-255 (2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023).

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

TY - GEN

T1 - A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention

AU - Xi, Yunqiao

AU - Zhang, Junping

AU - Liu, Jian

AU - Wang, Linlin

AU - Xu, Hongfeng

AU - Chen, Linxiu

AU - Jiang, Jixiang

PY - 2023

Y1 - 2023

N2 - To solve the problem that current dynamic intention recognition methods fail to make full use of time domain variation information between multi-temporal group targets, which leads to low accuracy of intention recognition. This paper proposes a bidirectional convolutional long short term memory-attention network for marine formation target intention recognition. The network takes the multi-source trajectory data of the marine ship formation target as the input, extracts and uses the target change rule and time domain characteristics of the Marine formation data, and trains the model to have the ability to independently learn the weight of information in different time periods. The simulation results show that the method has good performance and can meet the needs of practical application.

AB - To solve the problem that current dynamic intention recognition methods fail to make full use of time domain variation information between multi-temporal group targets, which leads to low accuracy of intention recognition. This paper proposes a bidirectional convolutional long short term memory-attention network for marine formation target intention recognition. The network takes the multi-source trajectory data of the marine ship formation target as the input, extracts and uses the target change rule and time domain characteristics of the Marine formation data, and trains the model to have the ability to independently learn the weight of information in different time periods. The simulation results show that the method has good performance and can meet the needs of practical application.

KW - intention recognition

KW - long short-term

KW - marinship formation

KW - temporal features

UR - https://www.scopus.com/pages/publications/85187022665

U2 - 10.1109/EIECS59936.2023.10435465

DO - 10.1109/EIECS59936.2023.10435465

M3 - 会议稿件

AN - SCOPUS:85187022665

T3 - 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023

SP - 252

EP - 255

BT - 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023

Y2 - 22 September 2023 through 24 September 2023

ER -

Xi Y, Zhang J, Liu J, Wang L, Xu H, Chen L et al. A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention. In 2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 252-255. (2023 3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023). doi: 10.1109/EIECS59936.2023.10435465

A Method for Marine Ship Formation Intention Recognition based on BiConvLSTM-Attention

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this