ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines

Leonardo Espinosa-Leal; Amin Majd

doi:10.1007/978-3-031-21678-7_13

ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines

Leonardo Espinosa-Leal^*
, Amin Majd

^*Corresponding author for this work

Not published at VTT

Arcada University of Applied Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

A new algorithm for ship classification named ELMShip is presented. The proposed methodology uses an extreme learning machine algorithm trained via features extracted via a pre-trained deep neural network. Here, we used an open available labelled dataset of 6252 images and five different classes. The original data was augmented via the extraction of subimages using squared sliding windows of different sizes and overlapped ratios to improve our calculations. Upon fine-tuning, we found that our best model outperforms the previously published results for all classes in all evaluated metrics.

Original language	English
Title of host publication	Proceedings of ELM 2021
Subtitle of host publication	Theory, Algorithms and Applications
Editors	Kaj-Mikael Björk
Place of Publication	Cham
Publisher	Springer
Pages	135-143
ISBN (Electronic)	978-3-031-21678-7
ISBN (Print)	978-3-031-21677-0, 978-3-031-21680-0
DOIs	https://doi.org/10.1007/978-3-031-21678-7_13
Publication status	Published - 2023
MoE publication type	A4 Article in a conference publication
Event	11th International Conference on Extreme Learning Machines (ELM2021) - On-line, Helsinki, Finland Duration: 15 Dec 2021 → 16 Dec 2021 Conference number: 11 https://risklab.fi/events/

Publication series

Series	Proceedings in Adaptation, Learning and Optimization
Volume	16
ISSN	2363-6084

Conference

Conference	11th International Conference on Extreme Learning Machines (ELM2021)
Abbreviated title	ELM2021
Country/Territory	Finland
City	Helsinki
Period	15/12/21 → 16/12/21
Internet address	https://risklab.fi/events/

Access to Document

10.1007/978-3-031-21678-7_13

Cite this

@inproceedings{1652850f80a04fa3a1071c3338d278ce,

title = "ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines",

abstract = "A new algorithm for ship classification named ELMShip is presented. The proposed methodology uses an extreme learning machine algorithm trained via features extracted via a pre-trained deep neural network. Here, we used an open available labelled dataset of 6252 images and five different classes. The original data was augmented via the extraction of subimages using squared sliding windows of different sizes and overlapped ratios to improve our calculations. Upon fine-tuning, we found that our best model outperforms the previously published results for all classes in all evaluated metrics.",

author = "Leonardo Espinosa-Leal and Amin Majd",

year = "2023",

doi = "10.1007/978-3-031-21678-7\_13",

language = "English",

isbn = "978-3-031-21677-0",

series = "Proceedings in Adaptation, Learning and Optimization",

publisher = "Springer",

pages = "135--143",

editor = "Kaj-Mikael Bj{\"o}rk",

booktitle = "Proceedings of ELM 2021",

address = "Germany",

note = "11th International Conference on Extreme Learning Machines (ELM2021), ELM2021 ; Conference date: 15-12-2021 Through 16-12-2021",

url = "https://risklab.fi/events/",

}

Espinosa-Leal, L & Majd, A 2023, ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines. in K-M Björk (ed.), Proceedings of ELM 2021: Theory, Algorithms and Applications. Springer, Cham, Proceedings in Adaptation, Learning and Optimization, vol. 16, pp. 135-143, 11th International Conference on Extreme Learning Machines (ELM2021), Helsinki, Finland, 15/12/21. https://doi.org/10.1007/978-3-031-21678-7_13

ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines. / Espinosa-Leal, Leonardo; Majd, Amin.
Proceedings of ELM 2021: Theory, Algorithms and Applications. ed. / Kaj-Mikael Björk. Cham: Springer, 2023. p. 135-143 (Proceedings in Adaptation, Learning and Optimization, Vol. 16).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines

AU - Espinosa-Leal, Leonardo

AU - Majd, Amin

N1 - Conference code: 11

PY - 2023

Y1 - 2023

N2 - A new algorithm for ship classification named ELMShip is presented. The proposed methodology uses an extreme learning machine algorithm trained via features extracted via a pre-trained deep neural network. Here, we used an open available labelled dataset of 6252 images and five different classes. The original data was augmented via the extraction of subimages using squared sliding windows of different sizes and overlapped ratios to improve our calculations. Upon fine-tuning, we found that our best model outperforms the previously published results for all classes in all evaluated metrics.

AB - A new algorithm for ship classification named ELMShip is presented. The proposed methodology uses an extreme learning machine algorithm trained via features extracted via a pre-trained deep neural network. Here, we used an open available labelled dataset of 6252 images and five different classes. The original data was augmented via the extraction of subimages using squared sliding windows of different sizes and overlapped ratios to improve our calculations. Upon fine-tuning, we found that our best model outperforms the previously published results for all classes in all evaluated metrics.

U2 - 10.1007/978-3-031-21678-7_13

DO - 10.1007/978-3-031-21678-7_13

M3 - Conference article in proceedings

SN - 978-3-031-21677-0

SN - 978-3-031-21680-0

T3 - Proceedings in Adaptation, Learning and Optimization

SP - 135

EP - 143

BT - Proceedings of ELM 2021

A2 - Björk, Kaj-Mikael

PB - Springer

CY - Cham

T2 - 11th International Conference on Extreme Learning Machines (ELM2021)

Y2 - 15 December 2021 through 16 December 2021

ER -

ELMShip: An Efficient Ship Classifier Using Extreme Learning Machines

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this