Data augmentation methods of dynamic model identification for harbor maneuvers using feedforward neural network

Wakita, Kouki; Miyauchi, Yoshiki; Akimoto, Youhei et al.

Journal of Marine Science and Technology, 2024

Number of Access:324（2025-08-14 01:30 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/100126

Link to primary information 

File Format Terms of use Size Views Date.Available Description information
JMarineSciTechnol_s00773-024-01036-w pdf None 30.8 MB 23 2025.01.28  
Creative Commons : Attribution

Item Information

Output File Export EndNote Basic Export Mendeley

Title
Data augmentation methods of dynamic model identification for harbor maneuvers using feedforward neural network
Creator
ORCID
0000-0003-0363-1396 0000-0003-0363-1396
CreatorName
Wakita, Kouki
CreatorName
Miyauchi, Yoshiki
NRID
1000020709654 1000020709654
CreatorName
Akimoto, Youhei
NRID
1000050556496 1000050556496
ORCID
0000-0002-2819-1297 0000-0002-2819-1297
researchmap permalink
atsuo_maki atsuo_maki
Scopus Author ID
24503751100 24503751100
CreatorName
Maki, Atsuo
Subject
Jittering
Maneuvering model
Neural network
Slicing
Description
The version of record of this article, first published in Journal of Marine Science and Technology, is available online at Publisher’s website: https://doi.org/10.1007/s00773-024-01036-w.
Abstract
A dynamic model for an automatic berthing and unberthing controller has to estimate harbor maneuvers, which include berthing, unberthing, approaching maneuvers to berths, and entering and leaving the port. When the dynamic model is estimated by the system identification using feedforward neural networks, a large number of tests or trials are required to measure the various motions of harbor maneuvers. However, the amount of data that can be obtained is limited due to the high costs and time-consuming nature of full-scale ship trials. Therefore, this paper introduces data augmentation to improve the generalization performance of dynamic models identified from a limited dataset. This study used slicing and jittering as data augmentation methods and confirmed their effectiveness by numerical experiments using the free-running model tests. Results of numerical experiments demonstrated that slicing and jittering are effective data augmentation methods but could not improve generalization performance for extrapolation states of the original dataset.
Publisher
Springer
Source Title
Journal of Marine Science and Technology
Date of Issued
2024-11-20
Language
English
Handle URL
https://hdl.handle.net/11094/100126
PISSN
09484280
Relation.isIdenticalTo
DOI (Publisher Version)
https://doi.org/10.1007/s00773-024-01036-w
Access Rights
open access
CopyRight
This article is licensed under a Creative Commons Attribution 4.0 International License.
oaire:version
Version of Record
Category
学術雑誌論文 Journal Article