Jae-Hyuk Choi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jae-Hyuk Choi has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Jun-Soo Kim
Department of Power System Engineering, Chonnam National University, 50, Daehak-ro, Yeosu-si 59626, Republic of Korea
2 shared publications - Byung Chul Choi
R&D Center, Korean Register of Shipping, Busan 46762, Republic of Korea
1 shared publication - Cheol-Ho Baek
Department of marine environment, Korea Maritime Transportation Safety Authority, Sejong, South Korea
1 shared publication Dae Geun Park
1 shared publication- Ha-Seek Jang
Department of marine environment, Korea Maritime Transportation Safety Authority, Sejong, South Korea
1 shared publication - Jang-Won Seo
Pohang center, Korea Institute of Geoscience and Mineral Resources, Heunghae-eup, Buk-gu, Pohang, South Korea
1 shared publication
Latest Publications
- 21 October 2026
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 42
Dual-ignition concept for flashback reversal and hydrodynamic scaling in H2–CH4 premixed flames
- 21 October 2026
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 42
Dual-ignition concept for flashback reversal and hydrodynamic scaling in H2–CH4 premixed flames
- Open Access
- 14 September 2026
- Published by Elsevier in SSRN Electronic Journal
Oracle-Free Active Learning: A Confidence-Gated Generative Augmentation Framework for Imbalanced Classification
Every acquisition function in common use rests on an assumption class-conditional generation violates: that a selected sample's label is unknown and must be bought from an oracle. That assumption is what makes uncertainty the quantity to maximise. When candidates are drawn from a generator that was told which class to synthesise, the label is free, and the criterion inverts --- an uncertain candidate is no longer information awaiting purchase but a sample whose assigned class is probably wrong, that is, label noise. This paper takes that inversion as its premise and develops oracle-free acquisition for generative augmentation under severe class imbalance: the candidates worth keeping are those a classifier confidently assigns to the class they were conditioned on, and are mutually diverse. The rule puts the classifier inside the generative loop rather than after it, realised in four coupled stages --- an autoencoder that initialises the generator and supplies a class-conditional latent prior, a gradient-penalised adversarial backbone, interpolation-seeded candidates filtered by the oracle-free rule, and co-training of critic, generator and classifier anchored to a frozen reference that stops the generator chasing an imperfect classifier. An ablation attributes performance to each stage. Against five established generative augmenters on three public image datasets under a shared protocol, the method ranks first on all four metrics on two datasets and leads six of the nine cells of an imbalance-ratio sweep. The results further show that realism and utility are separate objectives: the augmenter with the best Fr\'echet Inception Distance returns the worst macro-$F2$.
- 14 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessOracle-Free Active Learning: A Confidence-Gated Generative Augmentation Framework for Imbalanced Classification
Every acquisition function in common use rests on an assumption class-conditional generation violates: that a selected sample's label is unknown and must be bought from an oracle. That assumption is what makes uncertainty the quantity to maximise. When candidates are drawn from a generator that was told which class to synthesise, the label is free, and the criterion inverts --- an uncertain candidate is no longer information awaiting purchase but a sample whose assigned class is probably wrong, that is, label noise. This paper takes that inversion as its premise and develops oracle-free acquisition for generative augmentation under severe class imbalance: the candidates worth keeping are those a classifier confidently assigns to the class they were conditioned on, and are mutually diverse. The rule puts the classifier inside the generative loop rather than after it, realised in four coupled stages --- an autoencoder that initialises the generator and supplies a class-conditional latent prior, a gradient-penalised adversarial backbone, interpolation-seeded candidates filtered by the oracle-free rule, and co-training of critic, generator and classifier anchored to a frozen reference that stops the generator chasing an imperfect classifier. An ablation attributes performance to each stage. Against five established generative augmenters on three public image datasets under a shared protocol, the method ranks first on all four metrics on two datasets and leads six of the nine cells of an imbalance-ratio sweep. The results further show that realism and utility are separate objectives: the augmenter with the best Fr\'echet Inception Distance returns the worst macro-$F2$.
- Open Access
- 19 March 2025
- Published by Taylor & Francis in Journal of International Maritime Safety, Environmental Affairs, and Shipping
- Vol. 9 (2)
Cutting carbon emissions by using H 2 gas on a heavy-duty 2-stroke marine engine
- 19 March 2025
- Published by Taylor & Francis in Journal of International Maritime Safety, Environmental Affairs, and Shipping
- Vol. 9 (2)
Open AccessCutting carbon emissions by using H 2 gas on a heavy-duty 2-stroke marine engine
- 20 April 2024
- Published by The Society of Naval Architects of Korea in Journal of the Society of Naval Architects of Korea
- Vol. 61 (2) , 88-97
A Study on Impact and Countermeasures of Marine Fuels in the FuelEU Maritime Regulation
This study performed the analysis on an economic feasibility of each marine fuel, potential fuel pathways and the relevance of compliance measures to ensure compliance with the FuelEU Maritime regulation. Additionally, it identified certain regulatory gaps to encourage the use of alternative marine fuels. Regarding GHG emissions calculations, the existing GHG regulations for ships applies the Tank-to-Wake (TtW) method, whereas FuelEU Maritime applies the Well-to-Wake (WtW) method. The main results present that important information to establish response strategy for FuelEU Maritime including the costs and benefits of each marine fuel, the minimum blending ratio of alternative fules, and compliance impacts of measures. For the regulatory costs and benefits of marine fuels following the implementation of the FuelEU Maritime from 2025, our findings indicate that while most fossil fuels incur regulatory costs from 2025, most of biofuels and RFNBO fuels do not incur costs until 2050. This will play a role to narrow the price gap between fossil fuels and alternative fuels.
- 20 April 2024
- Published by The Society of Naval Architects of Korea in Journal of the Society of Naval Architects of Korea
- Vol. 61 (2) , 88-97
A Study on Impact and Countermeasures of Marine Fuels in the FuelEU Maritime Regulation
This study performed the analysis on an economic feasibility of each marine fuel, potential fuel pathways and the relevance of compliance measures to ensure compliance with the FuelEU Maritime regulation. Additionally, it identified certain regulatory gaps to encourage the use of alternative marine fuels. Regarding GHG emissions calculations, the existing GHG regulations for ships applies the Tank-to-Wake (TtW) method, whereas FuelEU Maritime applies the Well-to-Wake (WtW) method. The main results present that important information to establish response strategy for FuelEU Maritime including the costs and benefits of each marine fuel, the minimum blending ratio of alternative fules, and compliance impacts of measures. For the regulatory costs and benefits of marine fuels following the implementation of the FuelEU Maritime from 2025, our findings indicate that while most fossil fuels incur regulatory costs from 2025, most of biofuels and RFNBO fuels do not incur costs until 2050. This will play a role to narrow the price gap between fossil fuels and alternative fuels.
- Open Access
- 2 October 2023
- Published by Taylor & Francis in Journal of International Maritime Safety, Environmental Affairs, and Shipping
- Vol. 7 (4)
A field-study of the feasibility of the use of biodiesel in the marine industry
- 2 October 2023
- Published by Taylor & Francis in Journal of International Maritime Safety, Environmental Affairs, and Shipping
- Vol. 7 (4)
Open AccessA field-study of the feasibility of the use of biodiesel in the marine industry
- Open Access
- 3 July 2023
- Published by Taylor & Francis in Journal of International Maritime Safety, Environmental Affairs, and Shipping
- Vol. 7 (2-3)
A study on analysis of green house gaseous emitted from ships through operation information
- 3 July 2023
- Published by Taylor & Francis in Journal of International Maritime Safety, Environmental Affairs, and Shipping
- Vol. 7 (2-3)
Open AccessA study on analysis of green house gaseous emitted from ships through operation information
- 1 January 2019
- Published by Elsevier in Experimental Thermal and Fluid Science
- Vol. 101, 276-282
Experimental study on the flame propagation behaviors of R245fa(C3H3F5)/CH4/O2/N2 mixtures in a constant volume combustion chamber
- 1 January 2019
- Published by Elsevier in Experimental Thermal and Fluid Science
- Vol. 101, 276-282
Experimental study on the flame propagation behaviors of R245fa(C3H3F5)/CH4/O2/N2 mixtures in a constant volume combustion chamber