Orthogonal Transform based Generative Adversarial Network for Image Dehazing

no code implementations • 3 Jun 2022 • Ahlad Kumar, Mantra Sanathra, Manish Khare, Vijeta Khare

For this a customized Krawtchouk Convolution Layer (KCL) in the architecture is added.

Generative Adversarial Network Image Dehazing

Deep Learning Architecture Based Approach For 2D-Simulation of Microwave Plasma Interaction

no code implementations • 2 Jun 2022 • Mihir Desai, Pratik Ghosh, Ahlad Kumar, Bhaskar Chaudhury

The microwave propagation characteristics in complex plasma medium pertaining to transmission, absorption and reflection primarily depends on the ratio of electromagnetic (EM) wave frequency and electron plasma frequency, and the plasma density profile.

SSIM

Orthogonal Features Based EEG Signals Denoising Using Fractional and Compressed One-Dimensional CNN AutoEncoder

no code implementations • 16 Apr 2021 • Subham Nagar, Ahlad Kumar

The study shows that the proposed fractional and compressed architecture performs better than existing state-of-the-art signal denoising methods.

Denoising EEG +1

Tchebichef Transform Domain-based Deep Learning Architecture for Image Super-resolution

no code implementations • 21 Feb 2021 • Ahlad Kumar, Harsh Vardhan Singh

In this paper, we propose a deep learning based image super-resolution architecture in Tchebichef transform domain.

Image Super-Resolution Transfer Learning

Orthogonal Features-based EEG Signal Denoising using Fractionally Compressed AutoEncoder

no code implementations • 16 Feb 2021 • Subham Nagar, Ahlad Kumar, M. N. S. Swamy

The architecture makes use of fractional calculus to calculate the gradients during the backpropagation process, as a result of which a new hyper-parameter in the form of fractional order ($\alpha$) has been introduced which can be tuned to get the best denoising performance.

Denoising EEG