IEEE

Polynomial Phase Signal Denoising via Sparse Representations Over a SMAF-Based Dictionary Learning Algorithm

Abstract: In this paper, we address the problem of denoising polynomial phase signals (PPS) by removing additive white Gaussian noise. Our approach is based on sparse representation using a trained ...
IEEE

Frequency-Domain Super-Resolution With Reconstruction Using Compressed Representation (FDSR-RCR) Algorithm for Remote Sensing Satellite Images

Abstract: In remote sensing image processing for Earth and environmental applications, super-resolution (SR) is a crucial technique for enhancing the resolution of low-resolution (LR) images. In this ...
BBC

What are algorithms?

When you create an algorithm, you need to include precise, step-by-step instructions. This means you will need to break down the task or problem into smaller steps. We call this process decomposition.
Frontiers

Graph Learning and Deep Unfolding for Electromagnetic Field Modelling and Antenna Systems

Traditional computational electromagnetics (CEM) methods—such as MoM, FEM, or FDTD—offer high fidelity, but struggle to scale ...
GitHub

HybridGS: High-Efficiency Gaussian Splatting Data Compression using Dual-Channel Sparse Representation and Point Cloud Encoder (ICML2025)

This project is based on the official implementation associated with the paper "3D Gaussian Splatting for Real-Time Radiance Field Rendering", which can be found here. Abstract: *Most existing 3D ...
GitHub

MoEEG: A Sparse Mixture-of-Experts Transformer for Universal EEG Representation Learning

MoEEG has two variants, Base and Large, which share an identical model architecture but differ in hyperparameter configurations: the Base model features an embedding dimension of 128 with 4 attention ...