Search Results for author: Fakhri Karray

Found 60 papers, 27 papers with code

GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis

no code implementations20 Sep 2023 Youssef Abdelkareem, Shady Shehata, Fakhri Karray

Generalizable human view synthesis methods combine the pre-fitted 3D human meshes with image features to reach generalization, yet they are mainly designed to operate on single-human scenes.

Novel View Synthesis

Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based Augmentation

1 code implementation7 Jun 2023 Massa Baali, Ibrahim Almakky, Shady Shehata, Fakhri Karray

We perform further validation on real English dysarthric speech showing a WER improvement of 124% compared to the baseline trained only on healthy English LJSpeech dataset.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Clip21: Error Feedback for Gradient Clipping

no code implementations30 May 2023 Sarit Khirirat, Eduard Gorbunov, Samuel Horváth, Rustem Islamov, Fakhri Karray, Peter Richtárik

Motivated by the increasing popularity and importance of large-scale training under differential privacy (DP) constraints, we study distributed gradient methods with gradient clipping, i. e., clipping applied to the gradients computed from local information at the nodes.

Multi-Plane Neural Radiance Fields for Novel View Synthesis

no code implementations3 Mar 2023 Youssef Abdelkareem, Shady Shehata, Fakhri Karray

Multi-plane Neural Radiance Fields (MINE) open the door for combining implicit and explicit scene representations.

Novel View Synthesis

Harris Hawks Feature Selection in Distributed Machine Learning for Secure IoT Environments

no code implementations20 Feb 2023 Neveen Hijazi, Moayad Aloqaily, Bassem Ouni, Fakhri Karray, Merouane Debbah

Although IoT applications are helpful in smart building applications, they present a real risk as the large number of interconnected devices in those buildings, using heterogeneous networks, increases the number of potential IoT attacks.

feature selection

Integrating Digital Twin and Advanced Intelligent Technologies to Realize the Metaverse

no code implementations3 Oct 2022 Moayad Aloqaily, Ouns Bouachir, Fakhri Karray, Ismaeel Al Ridhawi, Abdulmotaleb El Saddik

In this article, we discuss some of the key issues required in order to attain realization of metaverse services.

Internet of Things Device Capabilities, Architectures, Protocols, and Smart Applications in Healthcare Domain: A Review

no code implementations12 Apr 2022 Md. Milon Islam, Sheikh Nooruddin, Fakhri Karray, Ghulam Muhammad

In this paper, the most common and popular IoT device capabilities, architectures, and protocols are demonstrated in brief to provide a clear overview of the IoT technology to the researchers in this area.

On Manifold Hypothesis: Hypersurface Submanifold Embedding Using Osculating Hyperspheres

no code implementations3 Feb 2022 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Using an induction in a pyramid structure, we also extend the embedding dimensionality to lower embedding dimensionalities to show the validity of manifold hypothesis for embedding dimensionalities $\{1, 2, \dots, d-1\}$.

Dimensionality Reduction

Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospects

no code implementations2 Feb 2022 Md. Milon Islam, Sheikh Nooruddin, Fakhri Karray, Ghulam Muhammad

Human Activity Recognition (HAR) plays a significant role in the everyday life of people because of its ability to learn extensive high-level information about human activity from wearable or stationary devices.

Human Activity Recognition

Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey

no code implementations23 Jan 2022 Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

In deep learning methods, we first introduce reconstruction autoencoders and supervised loss functions for metric learning.

Dimensionality Reduction Metric Learning

Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey

no code implementations26 Nov 2021 Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

Finally, we explain the autoencoders based on adversarial learning including adversarial autoencoder, PixelGAN, and implicit autoencoder.

Dimensionality Reduction Face Generation +4

Internet of Behavior (IoB) and Explainable AI Systems for Influencing IoT Behavior

no code implementations15 Sep 2021 Haya Elayan, Moayad Aloqaily, Fakhri Karray, Mohsen Guizani

The scenario results showed a decrease of 522. 2 kW of active power when compared to original consumption over a 200-hours period.

Cloud Computing Explainable Artificial Intelligence (XAI)

Uniform Manifold Approximation and Projection (UMAP) and its Variants: Tutorial and Survey

no code implementations25 Aug 2021 Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

We start with UMAP algorithm where we explain probabilities of neighborhood in the input and embedding spaces, optimization of cost function, training algorithm, derivation of gradients, and supervised and semi-supervised embedding by UMAP.

Data Visualization Dimensionality Reduction

Unified Framework for Spectral Dimensionality Reduction, Maximum Variance Unfolding, and Kernel Learning By Semidefinite Programming: Tutorial and Survey

no code implementations29 Jun 2021 Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

This is a tutorial and survey paper on unification of spectral dimensionality reduction methods, kernel learning by Semidefinite Programming (SDP), Maximum Variance Unfolding (MVU) or Semidefinite Embedding (SDE), and its variants.

Dimensionality Reduction

Smart Healthcare in the Age of AI: Recent Advances, Challenges, and Future Prospects

no code implementations24 Jun 2021 Mahmoud Nasr, Md. Milon Islam, Shady Shehata, Fakhri Karray, Yuri Quintana

The significant increase in the number of individuals with chronic ailments (including the elderly and disabled) has dictated an urgent need for an innovative model for healthcare systems.

UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detection

1 code implementation18 May 2021 Moloud Abdar, Soorena Salari, Sina Qahremani, Hak-Keung Lam, Fakhri Karray, Sadiq Hussain, Abbas Khosravi, U. Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi

Differently from most of existing studies, which used either CT scan or X-ray images in COVID-19-case classification, we present a simple but efficient deep learning feature fusion model, called UncertaintyFuseNet, which is able to classify accurately large datasets of both of these types of images.

Computed Tomography (CT)

Generative Locally Linear Embedding

1 code implementation4 Apr 2021 Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

In this work, we propose two novel generative versions of LLE, named Generative LLE (GLLE), whose linear reconstruction steps are stochastic rather than deterministic.

Dimensionality Reduction Variational Inference

Deep Learning Approaches for Forecasting Strawberry Yields and Prices Using Satellite Images and Station-Based Soil Parameters

no code implementations17 Feb 2021 Mohita Chaudhary, Mohamed Sadok Gastli, Lobna Nassar, Fakhri Karray

Computational tools for forecasting yields and prices for fresh produce have been based on traditional machine learning approaches or time series modelling.

Time Series Analysis

On the Philosophical, Cognitive and Mathematical Foundations of Symbiotic Autonomous Systems (SAS)

no code implementations11 Feb 2021 Yingxu Wang, Fakhri Karray, Sam Kwong, Konstantinos N. Plataniotis, Henry Leung, Ming Hou, Edward Tunstel, Imre J. Rudas, Ljiljana Trajkovic, Okyay Kaynak, Janusz Kacprzyk, Mengchu Zhou, Michael H. Smith, Philip Chen, Shushma Patel

Symbiotic Autonomous Systems (SAS) are advanced intelligent and cognitive systems exhibiting autonomous collective intelligence enabled by coherent symbiosis of human-machine interactions in hybrid societies.

Locally Linear Embedding and its Variants: Tutorial and Survey

1 code implementation22 Nov 2020 Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

In this paper, we first cover LLE, kernel LLE, inverse LLE, and feature fusion with LLE.

Dimensionality Reduction

Acceleration of Large Margin Metric Learning for Nearest Neighbor Classification Using Triplet Mining and Stratified Sampling

1 code implementation29 Sep 2020 Parisa Abdolrahim Poorheravi, Benyamin Ghojogh, Vincent Gaudet, Fakhri Karray, Mark Crowley

Many triplet mining methods have been developed for Siamese networks; however, these techniques have not been applied on the triplets of large margin metric learning for nearest neighbor classification.

Metric Learning

Stochastic Neighbor Embedding with Gaussian and Student-t Distributions: Tutorial and Survey

1 code implementation22 Sep 2020 Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray, Mark Crowley

Stochastic Neighbor Embedding (SNE) is a manifold learning and dimensionality reduction method with a probabilistic approach.

Dimensionality Reduction

A Review on Deep Learning Techniques for the Diagnosis of Novel Coronavirus (COVID-19)

no code implementations9 Aug 2020 Md. Milon Islam, Fakhri Karray, Reda Alhajj, Jia Zeng

Novel coronavirus (COVID-19) outbreak, has raised a calamitous situation all over the world and has become one of the most acute and severe ailments in the past hundred years.

COVID-19 Diagnosis

Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem

1 code implementation10 Jul 2020 Milad Sikaroudi, Benyamin Ghojogh, Fakhri Karray, Mark Crowley, H. R. Tizhoosh

However, sampling from stochastic distributions of data rather than sampling merely from the existing embedding instances can provide more discriminative information.

Dimensionality Reduction Histopathological Image Classification +1

Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition

1 code implementation28 Jun 2020 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Although various methods have been proposed for 3D action recognition, some of which are basic and some use deep learning, the need of basic methods based on generalized eigenvalue problem is sensed for action recognition.

3D Action Recognition Face Recognition

Quantile-Quantile Embedding for Distribution Transformation and Manifold Embedding with Ability to Choose the Embedding Distribution

1 code implementation19 Jun 2020 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

We propose a new embedding method, named Quantile-Quantile Embedding (QQE), for distribution transformation and manifold embedding with the ability to choose the embedding distribution.

Dimensionality Reduction Metric Learning

Anomaly Detection and Prototype Selection Using Polyhedron Curvature

1 code implementation5 Apr 2020 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

We propose a novel approach to anomaly detection called Curvature Anomaly Detection (CAD) and Kernel CAD based on the idea of polyhedron curvature.

Anomaly Detection Image Denoising +2

Backprojection for Training Feedforward Neural Networks in the Input and Feature Spaces

1 code implementation5 Apr 2020 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

After the tremendous development of neural networks trained by backpropagation, it is a good time to develop other algorithms for training neural networks to gain more insights into networks.

Dimensionality Reduction

Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks

1 code implementation5 Apr 2020 Benyamin Ghojogh, Milad Sikaroudi, Sobhan Shafiei, H. R. Tizhoosh, Fakhri Karray, Mark Crowley

The FDT and FDC loss functions are designed based on the statistical formulation of the Fisher Discriminant Analysis (FDA), which is a linear subspace learning method.

Classification Of Breast Cancer Histology Images Dimensionality Reduction +3

Weighted Fisher Discriminant Analysis in the Input and Feature Spaces

1 code implementation4 Apr 2020 Benyamin Ghojogh, Milad Sikaroudi, H. R. Tizhoosh, Fakhri Karray, Mark Crowley

We also propose a weighted FDA in the feature space to establish a weighted kernel FDA for both existing and newly proposed weights.

Dimensionality Reduction Face Recognition

Roweis Discriminant Analysis: A Generalized Subspace Learning Method

1 code implementation11 Oct 2019 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

We also propose kernel RDA, generalizing kernel PCA, kernel SPCA, and kernel FDA, using both dual RDA and representation theory.

Dimensionality Reduction Face Recognition

Quantized Fisher Discriminant Analysis

1 code implementation6 Sep 2019 Benyamin Ghojogh, Ali Saheb Pasand, Fakhri Karray, Mark Crowley

This paper proposes a new subspace learning method, named Quantized Fisher Discriminant Analysis (QFDA), which makes use of both machine learning and information theory.

BIG-bench Machine Learning Dimensionality Reduction +1

Principal Component Analysis Using Structural Similarity Index for Images

1 code implementation25 Aug 2019 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Despite the advances of deep learning in specific tasks using images, the principled assessment of image fidelity and similarity is still a critical ability to develop.

Dimensionality Reduction Image Quality Assessment +1

Locally Linear Image Structural Embedding for Image Structure Manifold Learning

1 code implementation25 Aug 2019 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

We propose a new manifold learning method, Locally Linear Image Structural Embedding (LLISE), and kernel LLISE for learning this manifold.

Dimensionality Reduction Image Quality Assessment +1

Fisher and Kernel Fisher Discriminant Analysis: Tutorial

2 code implementations22 Jun 2019 Benyamin Ghojogh, Fakhri Karray, Mark Crowley

This is a detailed tutorial paper which explains the Fisher discriminant Analysis (FDA) and kernel FDA.

Dimensionality Reduction

Feature Selection and Feature Extraction in Pattern Analysis: A Literature Review

2 code implementations7 May 2019 Benyamin Ghojogh, Maria N. Samad, Sayema Asif Mashhadi, Tania Kapoor, Wahab Ali, Fakhri Karray, Mark Crowley

Pattern analysis often requires a pre-processing stage for extracting or selecting features in order to help the classification, prediction, or clustering stage discriminate or represent the data in a better way.

Clustering Dimensionality Reduction +4

Fitting A Mixture Distribution to Data: Tutorial

1 code implementation20 Jan 2019 Benyamin Ghojogh, Aydin Ghojogh, Mark Crowley, Fakhri Karray

In explaining the main algorithm, first, fitting a mixture of two distributions is detailed and examples of fitting two Gaussians and Poissons, respectively for continuous and discrete cases, are introduced.

Bayesian Inference Bayesian Optimisation +1

New Results on Multi-Step Traffic Flow Prediction

no code implementations4 Mar 2018 Arief Koesdwiady, Fakhri Karray

Multi-step traffic flow prediction extends this set-up to the case where predicting multiple time-steps into the future based on some finite history is of interest.

Data Augmentation Generative Adversarial Network

Semi-supervised Dictionary Learning Based on Hilbert-Schmidt Independence Criterion

no code implementations25 Apr 2016 Mehrdad J. Gangeh, Safaa M. A. Bedawi, Ali Ghodsi, Fakhri Karray

The proposed method benefits from the supervisory information by learning the dictionary in a space where the dependency between the data and class labels is maximized.

Dictionary Learning

Driver distraction detection and recognition using RGB-D sensor

no code implementations1 Feb 2015 Céline Craye, Fakhri Karray

Based on active sensor Kinect and computer vision tools, we have built an efficient module for detecting driver distraction and recognizing the type of distraction.

Embed and Conquer: Scalable Embeddings for Kernel k-Means on MapReduce

no code implementations11 Nov 2013 Ahmed Elgohary, Ahmed K. Farahat, Mohamed S. Kamel, Fakhri Karray

Exploiting the proposed parallelization strategy, we present two scalable MapReduce algorithms for kernel $k$-means.

Clustering Distributed Computing

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