Muhammad Ali

Muhammad Ali
Charles Sturt University · Centre for Research into Complex Systems (CRiCS)

PhD ☞ Computer Science + MPhil ☞ Industrial Mathematics + MSc ☞ Mathematics

About

23
Publications
144,793
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
43
Citations
Introduction
Muhammad Ali received a Master degree in Mathematics from the Gomal University D.I. Khan (Pakistan) in 2000 and a Master of Philosophy from Techno University of Kaiserslautern (Germany) with specialization in Mathematical Modelling and Scientific Computing in 2005. Thereafter, in 2018, he completed a PhD degree from Charles Sturt University (Australia) in Machine Learning with contribution to nonclassical/nonlinear statistical modelling on MANIFOLDS with its applications to computer vision.

Publications

Publications (23)
Preprint
Full-text available
This proposal highlights a strategic overview to optimal position of the state space system filtering (noise reduction) techniques. To do so there a re several choices in the existing literature, e.g., one of the related such technique is Butterworth filter which is good for understanding filtering analysis as first step, however., it has some limi...
Technical Report
Full-text available
Teaching mathematical sciences is one of the challenging task for teachers to effectively share or convey their already learned mathematical/computing concepts, ideas, and techniques to the newly learners. The ideal need of mathematics and computing arises every where in our surroundings in the presence of real physical objects of the world. From t...
Presentation
Full-text available
Problem:�In Non Linear Control Systems (NLCS) Linearization criterion is often unsatisfying.�� Goal: Develop a condition that works even if the linearization approach fails.�
Conference Paper
Full-text available
Matrix manifolds such as Stiefel manifolds have been widely been used in modern computer vision community. The goal of this short paper is an overview of the problem of clustering such manifold valued data, based on the maximum likelihood estimation for the parametric probability density functions defined on the manifolds. By using a new and most e...
Conference Paper
Full-text available
In this paper we focus on with making classification on generalised Scheiddegger-Watson distribution using standard Maximum Likelihood Estimation (MLE) via simple Bayesian approach. The main barrier in working with Scheiddegger-Watson or any other matrix variate distributions via standard MLE is the normalising constant naturally appearing with the...
Preprint
Full-text available
This paper demonstrates learning on Grassmann manifolds over the Bingham parametric model using a Bayesian approach of Maximum Likelihood Estimation (MLE). By using a Bayesian framework, the most practical challenge is the evaluation of the normalizing constant for recognition analysis. The normalizing constant that appears in the proposed model is...
Preprint
Full-text available
This paper proposes the standard Maximum Likelihood Estimation (MLE) over Grassmannian-variate Angular Central Gaussian (GACG) distribution with Bayesian parametric classification using Grassmann manifolds. The main focus is on practical applicability of antipodal symmetric GACG distribution for classification tasks. The GACG distributions is an al...
Article
In this paper, we present a novel Bayesian classification framework of matrix variate Bingham distributions, with the inclusion of its normalizing constant, and develop a consistent general parametric modeling framework based on Grassmann manifolds. To calculate the normalizing constants of the Bingham model, the paper extends the method of Saddle-...
Thesis
Full-text available
The aim of this thesis is to develop a consistent general parametric modeling framework based on analytic manifolds. In practice, the structures of most real-world data such as images and videos have a very complex nature, and that is why it is assumed that instead of linear vector space (Euclidean space), such data may actually lie in nonlinear di...
Article
Full-text available
In the existing literature, the numerical estimation of multivariate normalizing constant is considered highly non-trivial, intractable or a big barrier to Bayesian approach, and hence non-parametric and many other techniques are adopted as an alternative for inferential problems, i.e., without the use of normalizing constant. This problem is a sub...
Presentation
Full-text available
Statistical models on manifolds for parametric classification
Conference Paper
Learning on Grassmann manifold has become popular in many computer vision tasks, with the strong capability to extract discriminative information for imagesets and videos. However, such learning algorithms particularly on high-dimensional Grassmann manifold always involve with significantly high computational cost, which seriously limits the applic...
Article
Symmetric Positive semi-Definite (SPD) matrices, as a kind of effective feature descriptors, have been widely used in pattern recognition and computer vision tasks. Affine-invariant metric (AIM) is a popular way to measure the distance between SPD matrices, but it imposes a high computational burden in practice. Compared with AIM, the Log-Euclidean...
Thesis
Full-text available
In this thesis, we first thinking about matrix functions, uniqueness of matrix square roots, iterative methods for convergence and stability analysis of ma- trix square roots and its generalized version (matrix pth root). In order to acclerate convergence, we will introduce some scaling procedures, and Pade′ approximants for obtaining good accuracy...
Article
Full-text available
The most important role of the blood in the human body is to transport O2, CO2 and nutrients. The main goal of the body is to support the tis- sue with enough oxygen, where the amount depends on the level of exercise, and to maintain a certain level of blood pressure. Our goal was to set up a model which should be able to describe the effects of he...

Questions

Questions (20)

Network

Cited By

Projects

Projects (8)
Project
Corona COVID-19 function / weakness identified! Researchers at the University of Bristol in the UK have said they hope to stop the corona virus. Researchers at the University of Bristol in the United Kingdom, praising their research, said they hoped to stop the corona virus. The researchers found sinuses on the surface of the virus that could be blocked by antivirals before they could enter more cells. They found that the corona virus uses a small molecule called linoleic acid (LA) to bind to each other and spread to other cells; So the research team believes that there is now a way to disable these molecules and possibly make the Corona virus inoperable. Corona function: "There is a small molecule at the center of the Covid 19 function that is the main cause of the deterioration in patients," said Professor Emery Berger, a researcher at the university. The virus that causes all these problems is dependent on this molecule and uses it to disrupt the body's immune system. Therefore, our research identifies the first direct link between this molecule and the symptoms of the disease. The question now is how to use this new knowledge against the virus itself and defeat it? Researchers hope that scientists have discovered a similar sinusoid in rhinoviruses as in the past, and have been able to prevent it from becoming contagious.  
Project
Mathematical & Statistical Contributions to Psychology & Sociology