75 citations · 342 across the 18 of their papers we have counts for
7 papers · 1 filter
TopoFormer: Integrating Transformers and ConvLSTMs for Coastal Topography Prediction
Santosh Munian, Oktay Karakuş, William Russell +1
This paper presents \textit{TopoFormer}, a novel hybrid deep learning architecture that integrates transformer-based encoders with convolutional long short-term memory (ConvLSTM) l…
Robust Kalman Filters Based on the Sub-Gaussian -stable Distribution
Pengcheng Hao, Oktay Karakuş, Alin Achim
Motivated by filtering tasks under a linear system with non-Gaussian heavy-tailed noise, various robust Kalman filters (RKFs) based on different heavy-tailed distributions have bee…
On Solving SAR Imaging Inverse Problems Using Non-Convex Regularization with a Cauchy-based Penalty
Oktay Karakuş, Alin Achim
Synthetic aperture radar (SAR) imagery can provide useful information in a multitude of applications, including climate change, environmental monitoring, meteorology, high dimensio…
Convergence Guarantees for Non-Convex Optimisation with Cauchy-Based Penalties
Oktay Karakus, Perla Mayo, Alin Achim
In this paper, we propose a proximal splitting methodology with a non-convex penalty function based on the heavy-tailed Cauchy distribution. We first suggest a closed-form expressi…
Detection of Ship Wakes in SAR Imagery Using Cauchy Regularisation
Tianqi Yang, Oktay Karakuş, Alin Achim
Ship wake detection is of great importance in the characterisation of synthetic aperture radar (SAR) images of the ocean surface since wakes usually carry essential information abo…
Ship Wake Detection in SAR Images via Sparse Regularization
Oktay Karakuş, Igor Rizaev, Alin Achim
In order to analyse synthetic aperture radar (SAR) images of the sea surface, ship wake detection is essential for extracting information on the wake generating vessels. One possib…
Beyond trans-dimensional RJMCMC with a case study in impulsive data modeling
Oktay Karakuş, Ercan E. Kuruoğlu, Mustafa A. Altınkaya
Reversible jump Markov chain Monte Carlo (RJMCMC) is a Bayesian model estimation method which has been used for trans-dimensional sampling. In this study, we propose utilization of…