University of Aizu

DDSF-UNet: dual-domain spatial–frequency learning for underwater image enhancement

Abstract Underwater image enhancement (UIE) is still difficult. This is mainly due to wavelength-dependent light absorption, scattering, and environmental noise, which lead to low visibility, color distortion, and loss of fine details. Most existing deep learning (DL) based model...

Exact Spectral Degeneracies in Kernel Discriminant Operators Under Small-Sample Designs

For a family of kernelized discriminant operators built from class-membership structure alone, this note proves two closed-form spectral theorems. Under an exactly balanced sampling design, the operator relevant to several fused objectives collapses to an exact scalar multiple of...

I Made the Choice, Did I? Exploring the Influence of Goal-Directed AI on Human Decision-Making

As AI become integrated into decision-making, some concerns emerge: Can AI shape our decisions without us noticing? To examine this, we adopt forcing techniques from performance magic, which guide apparently open choices toward predetermined outcomes. This provides a lens for exa...

Optimizing container loading and unloading through dual-cycling and dockyard rehandle reduction using a hybrid genetic algorithm

Abstract This paper addresses the NP-hard problem of optimizing container handling at ports by integrating Quay Crane Dual-Cycling (QCDC) and dockyard rehandle minimization. We identify critical inter-dependencies between the unloading sequence of QCDC and the dockyard container...

A certification-driven beam-energy projection algorithm for shape-controlled cubic Hermite interpolation

We develop a value-only cubic Hermite interpolation method that retains the bending-energy objective of the natural spline while controlling selected geometric features between data points. The method begins with the natural-spline slopes. Three interval tests detect escape from...