Search Results for author: Farokh Marvasti

Found 26 papers, 2 papers with code

Ensemble Neural Representation Networks

1 code implementation7 Oct 2021 Milad Soltany Kadarvish, Hesam Mojtahedi, Hossein Entezari Zarch, Amirhossein Kazerouni, Alireza Morsali, Azra Abtahi, Farokh Marvasti

Hence, it is vital to suggest an optimization algorithm to find the sub-optimal structure of the ensemble network, which is done in this paper.

OBTAIN: Real-Time Beat Tracking in Audio Signals

1 code implementation7 Apr 2017 Ali Mottaghi, Kayhan Behdin, Ashkan Esmaeili, Mohammadreza Heydari, Farokh Marvasti

In this paper, we design a system in order to perform the real-time beat tracking for an audio signal.

Online Beat Tracking

Transduction with Matrix Completion Using Smoothed Rank Function

no code implementations19 May 2018 Ashkan Esmaeili, Kayhan Behdin, Mohammad Amin Fakharian, Farokh Marvasti

In this paper, we propose two new algorithms for transduction with Matrix Completion (MC) problem.

Matrix Completion

Measurement-Adaptive Sparse Image Sampling and Recovery

no code implementations9 Jun 2017 Ali Taimori, Farokh Marvasti

In the proposed sampler, we adaptively determine the number of required samples for retrieving image based on space-frequency-gradient information content of image patches.

Compressive Sensing

A Convex Similarity Index for Sparse Recovery of Missing Image Samples

no code implementations25 Jan 2017 Amirhossein Javaheri, Hadi Zayyani, Farokh Marvasti

The proposed criterion called Convex SIMilarity (CSIM) index is a modified version of the Structural SIMilarity (SSIM) index, which despite its predecessor, is convex and uni-modal.

SSIM

Recovery of Missing Samples Using Sparse Approximation via a Convex Similarity Measure

no code implementations28 Jun 2017 Amirhossein Javaheri, Hadi Zayyani, Farokh Marvasti

In this paper, we study the missing sample recovery problem using methods based on sparse approximation.

SSIM

Recovery of Sparse and Low Rank Components of Matrices Using Iterative Method with Adaptive Thresholding

no code implementations9 Mar 2017 Nematollah Zarmehi, Farokh Marvasti

In this letter, we propose an algorithm for recovery of sparse and low rank components of matrices using an iterative method with adaptive thresholding.

Fast Methods for Recovering Sparse Parameters in Linear Low Rank Models

no code implementations26 Jun 2016 Ashkan Esmaeili, Arash Amini, Farokh Marvasti

In this paper, we investigate the recovery of a sparse weight vector (parameters vector) from a set of noisy linear combinations.

Matrix Completion

Image Block Loss Restoration Using Sparsity Pattern as Side Information

no code implementations23 Jan 2014 Hossein Hosseini, Ali Goli, Neda Barzegar Marvasti, Masoume Azghani, Farokh Marvasti

In this paper, we propose a method for image block loss restoration based on the notion of sparse representation.

Comparison of Several Sparse Recovery Methods for Low Rank Matrices with Random Samples

no code implementations12 Jun 2016 Ashkan Esmaeili, Farokh Marvasti

This paper will focus on comparing the power of IMAT in reconstruction of the desired sparse signal with LASSO.

BIG-bench Machine Learning

Real-Time Impulse Noise Suppression from Images Using an Efficient Weighted-Average Filtering

no code implementations10 Jul 2014 Hossein Hosseini, Farzad Hessar, Farokh Marvasti

In this paper, we propose a method for real-time high density impulse noise suppression from images.

A Novel Approach to Quantized Matrix Completion Using Huber Loss Measure

no code implementations29 Oct 2018 Ashkan Esmaeili, Farokh Marvasti

Next, we form an unconstrained optimization problem by regularizing the rank function with Huber loss.

Matrix Completion Quantization

A Nonlinear Acceleration Method for Iterative Algorithms

no code implementations4 Jun 2019 Mahdi Shamsi, Mahmoud Ghandi, Farokh Marvasti

Iterative methods have led to better understanding and solving problems such as missing sampling, deconvolution, inverse systems, impulsive and Salt and Pepper noise removal problems.

Salt-And-Pepper Noise Removal

Distributed interference cancellation in multi-agent scenarios

no code implementations22 Oct 2019 Mahdi Shamsi, Alireza Moslemi Haghighi, Farokh Marvasti

This paper considers the problem of detecting impaired and noisy nodes over network.

Efficient Sparse Artificial Neural Networks

no code implementations13 Mar 2021 Seyed Majid Naji, Azra Abtahi, Farokh Marvasti

In the proposed methods, the sparse structure of a network as well as the values of its parameters are trained and updated during the learning process.

Image Classification

Robust Adaptive Generalized Correntropy-based Smoothed Graph Signal Recovery with a Kernel Width Learning

no code implementations19 Sep 2022 Razieh Torkamani, Hadi Zayyani, Farokh Marvasti

In addition, some synthetic and real-world experiments show the advantage of the proposed algorithm in comparison to some other adaptive algorithms in the literature of adaptive graph signal recovery.

Algorithmic Trading Using Continuous Action Space Deep Reinforcement Learning

no code implementations7 Oct 2022 Naseh Majidi, Mahdi Shamsi, Farokh Marvasti

This paper aims to offer an approach using Twin-Delayed DDPG (TD3) and the daily close price in order to achieve a trading strategy in the stock and cryptocurrency markets.

Algorithmic Trading Position +2

Augmenting SEFDM Performance in High-Doppler Channels

no code implementations21 Sep 2023 Mahdi Shamsi, Farokh Marvasti

This paper presents an innovative approach leveraging Spectrally Efficient Frequency Division Multiplexing (SEFDM) with enhancements, including Frequency Domain Cyclic Prefix (FDCP) and Modified Non-Linear (MNL) acceleration, to address challenges arising from delay and Doppler shift in mobile communication channels.

Distributed Estimation with Partially Accessible Information: An IMAT Approach to LMS Diffusion

no code implementations15 Oct 2023 Mahdi Shamsi, Farokh Marvasti

Distributed algorithms, particularly Diffusion Least Mean Square, are widely favored for their reliability, robustness, and fast convergence in various industries.

Cannot find the paper you are looking for? You can Submit a new open access paper.