A holistic comparison between deep learning techniques to determine Covid-19 patients utilizing chest X-Ray images
EASL-Vol. 3 (2020), Issue 4, pp. 85 – 93 Open Access Full-Text PDF
Taki Hasan Rafi
Abstract: Novel coronavirus likewise called COVID-19 began in Wuhan, China in December 2019 and has now outspread over the world. Around 63 millions of people currently got influenced by novel coronavirus and it causes around 1,500,000 deaths. There are just about 600,000 individuals contaminated by COVID-19 in Bangladesh too. As it is an exceptionally new pandemic infection, its diagnosis is challenging for the medical community. In regular cases, it is hard for lower incoming countries to test cases easily. RT-PCR test is the most generally utilized analysis framework for COVID-19 patient detection. However, by utilizing X-ray image based programmed recognition can diminish the expense and testing time. So according to handling this test, it is important to program and effective recognition to forestall transmission to others. In this paper, author attempts to distinguish COVID-19 patients by chest X-ray images. Author executes various pre-trained deep learning models on the dataset such as Base-CNN, ResNet-50, DenseNet-121 and EfficientNet-B4. All the outcomes are compared to determine a suitable model for COVID-19 detection using chest X-ray images. Author also evaluates the results by AUC, where EfficientNet-B4 has 0.997 AUC, ResNet-50 has 0.967 AUC, DenseNet-121 has 0.874 AUC and the Base-CNN model has 0.762 AUC individually. The EfficientNet-B4 has achieved 98.86% accuracy.
On the entire Zagreb indices of the line graph and line cut-vertex graph of the subdivision graph
OMS-Vol. 4 (2020), Issue 1, pp. 470 – 475 Open Access Full-Text PDF
H. M. Nagesh, Girish V. R
Abstract: Let \(G=(V,E)\) be a graph. Then the first and second entire Zagreb indices of \(G\) are defined, respectively, as \(M_{1}^{\varepsilon}(G)=\displaystyle \sum_{x \in V(G) \cup E(G)} (d_{G}(x))^{2}\) and \(M_{2}^{\varepsilon}(G)=\displaystyle \sum_{\{x,y\}\in B(G)} d_{G}(x)d_{G}(y)\), where \(B(G)\) denotes the set of all 2-element subsets \(\{x,y\}\) such that \(\{x,y\} \subseteq V(G) \cup E(G)\) and members of \(\{x,y\}\) are adjacent or incident to each other. In this paper, we obtain the entire Zagreb indices of the line graph and line cut-vertex graph of the subdivision graph of the friendship graph.
Reverse Hermite-Hadamard’s inequalities using \(\psi\)-fractional integral
EASL-Vol. 3 (2020), Issue 4, pp. 75 – 84 Open Access Full-Text PDF
Tariq A. Aljaaidi, Deepak B. Pachpatte
Abstract: Our purpose in this paper is to use \(\psi-\)Riemann-Liouville fractional integral operator which is the fractional integral of any function with respect to another increasing function to establish some new fractional integral inequalities of Hermite-Hadamard, involving concave functions. Using the concave functions, we establish some new fractional integral
inequalities related to the Hermite-Hadamard type inequalities via \(\psi-\)Riemann-Liouville fractional integral operator.
inequalities related to the Hermite-Hadamard type inequalities via \(\psi-\)Riemann-Liouville fractional integral operator.
Boundary value problems for a class of stochastic nonlinear fractional order differential equations
OMA-Vol. 4 (2020), Issue 2, pp. 152 – 159 Open Access Full-Text PDF
McSylvester Ejighikeme Omaba, Louis O. Omenyi
Abstract: Consider a class of two-point Boundary Value Problems (BVP) for a stochastic nonlinear fractional order differential equation \(D^\alpha u(t)=\lambda\sqrt{I^\beta[\sigma^2(t,u(t))]}\dot{w}(t),\,\,00\) is a level of the noise term, \(\sigma:[0,1]\times\mathbb{R}\rightarrow\mathbb{R}\) is continuous, \(\dot{w}(t)\) is a generalized derivative of Wiener process (Gaussian white noise), \(D^\alpha\) is the Riemann-Liouville fractional differential operator of order \(\alpha\in (3,4)\) and \(I^\beta,\,\,\beta>0\) is a fractional integral operator. We formulate the solution of the equation via a stochastic Volterra-type equation and investigate its existence and uniqueness under some precise linearity conditions using contraction fixed point theorem. A case of the above BVP for a stochastic nonlinear second order differential equation for \(\alpha=2\) and \(\beta=0\) with \(u(0)=u(1)=0\) is also studied.
Towards understanding the mathematics of the \(2^{nd}\) law of thermodynamics
OMS-Vol. 4 (2020), Issue 1, pp. 466 – 469 Open Access Full-Text PDF
Md. Shafiqul Islam
Abstract: In this paper, the mathematical formulation of \(2^{nd}\) law of thermodynamics has been explained, and the mathematical formulation of \(1^{st}\) law has been revisited from this noble perspective. It is not claimed that the \(2^{nd}\) law of thermodynamics is a redundant of the \(1^{st}\) law, rather I shown here how we can extract the mathematical formulation of the \(2^{nd}\) law from the mathematical formulation of the \(1^{st}\) law of thermodynamics. The Clausius statement of the \(2^{nd}\) law of thermodynamics is, it is impossible to construct a device whose sole effect is the transfer of heat from a cool reservoir to a hot reservoir. An alternative statement of the law is, “All spontaneous processes are irreversible” or, “the entropy of an isolated system always increases”. Having strong experimental evidences, this empirical law is obvious, which tells us the arrow of time and the direction of spontaneous changes.
Measure of noncompactness for nonlinear Hilfer fractional differential equation with nonlocal Riemann–Liouville integral boundary conditions in Banach spaces
OMS-Vol. 4 (2020), Issue 1, pp. 456 – 465 Open Access Full-Text PDF
Abdelatif Boutiara, Maamar Benbachir, Kaddour Guerbati
Abstract: This paper investigates the existence results and uniqueness of solutions for a class of boundary value problems for fractional differential equations with the Hilfer fractional derivative. The reasoning is mainly based upon Mönch’s fixed point theorem associated with the technique of measure of noncompactness. We illustrate our main findings, with a particular case example, included to show the applicability of our outcomes. The boundary conditions introduced in this work are of quite general nature and reduce to many special cases by fixing the parameters involved in the conditions.
