20 April 2024 in Journal of the Society of Naval Architects of Korea
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.
1 January 2019 in Experimental Thermal and Fluid Science
3 July 2023 in Journal of International Maritime Safety, Environmental Affairs, and Shipping
2 October 2023 in Journal of International Maritime Safety, Environmental Affairs, and Shipping
19 March 2025 in Journal of International Maritime Safety, Environmental Affairs, and Shipping
14 September 2026 in SSRN Electronic Journal
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-$F2$.