Deep convolutional neural network (CNN) model optimization techniques—Review for medical imaging

Ghazanfar Latif; Jaafar Alghazo; Majid Ali Khan; Ghassen Ben Brahim; Khaled Fawagreh; Nazeeruddin Mohammad; Ghazanfar Latif; Jaafar Alghazo; Majid Ali Khan; Ghassen Ben Brahim; Khaled Fawagreh; Nazeeruddin Mohammad

doi:10.3934/math.2024998

AIMS Mathematics

2024, Volume 9, Issue 8: 20539-20571. doi: 10.3934/math.2024998

Previous Article Next Article

Review Special Issues

Deep convolutional neural network (CNN) model optimization techniques—Review for medical imaging

1.
Department of Computer Science, Prince Mohammad Bin Fahd University, Khobar, Saudi Arabia
2.
Department of Software Engineering and Information Technology Management, University of Minnesota Crookston, Crookston, MN 56716, USA

Received: 22 February 2024 Revised: 02 May 2024 Accepted: 20 May 2024 Published: 25 June 2024
MSC : 62M45, 68T45

The field of artificial intelligence (AI) and machine learning (ML) has been expanding and is explored by researchers in various fields. In medical diagnosis, for instance, the field of AI/ML is being explored because if medical diagnostic devices are built and designed with a backend of AI/ML, then the benefits would be unprecedented. Automated diagnostic tools would result in reduced health care costs, diagnosis without human intervention, overcoming human errors, and providing adequate and affordable medical care to a wider portion of the population with portions of the actual cost. One domain where AI/ML can make an immediate impact is medical imaging diagnosis (MID), namely the classification of medical images, where researchers have applied optimization techniques aiming to improve image classification accuracy. In this paper, we provide the research community with a comprehensive review of the most relevant studies to date on the use of deep CNN architecture optimization techniques for MID. As a case study, the application of these techniques to COVID-19 medical images were made. The impacts of the related variables, including datasets and AI/ML techniques, were investigated in detail. Additionally, the significant shortcomings and challenges of the techniques were touched upon. We concluded our work by affirming that the application of AI/ML techniques for MID will continue for many years to come, and the performance of the AI/ML classification techniques will continue to increase.

Keywords:

Citation: Ghazanfar Latif, Jaafar Alghazo, Majid Ali Khan, Ghassen Ben Brahim, Khaled Fawagreh, Nazeeruddin Mohammad. Deep convolutional neural network (CNN) model optimization techniques—Review for medical imaging[J]. AIMS Mathematics, 2024, 9(8): 20539-20571. doi: 10.3934/math.2024998

Related Papers:

[1]	Osama Ala'yed, Rania Saadeh, Ahmad Qazza . Numerical solution for the system of Lane-Emden type equations using cubic B-spline method arising in engineering. AIMS Mathematics, 2023, 8(6): 14747-14766. doi: 10.3934/math.2023754
[2]	Emre Kırlı . A novel B-spline collocation method for Hyperbolic Telegraph equation. AIMS Mathematics, 2023, 8(5): 11015-11036. doi: 10.3934/math.2023558
[3]	Shafeeq Rahman Thottoli, Mohammad Tamsir, Mutum Zico Meetei, Ahmed H. Msmali . Numerical investigation of nonlinear extended Fisher-Kolmogorov equation via quintic trigonometric B-spline collocation technique. AIMS Mathematics, 2024, 9(7): 17339-17358. doi: 10.3934/math.2024843
[4]	M. S. Hashmi, Rabia Shikrani, Farwa Nawaz, Ghulam Mustafa, Kottakkaran Sooppy Nisar, Velusamy Vijayakumar . An effective approach based on Hybrid B-spline to solve Riesz space fractional partial differential equations. AIMS Mathematics, 2022, 7(6): 10344-10363. doi: 10.3934/math.2022576
[5]	Yan Wu, Chun-Gang Zhu . Generating bicubic B-spline surfaces by a sixth order PDE. AIMS Mathematics, 2021, 6(2): 1677-1694. doi: 10.3934/math.2021099
[6]	Shanshan Wang . Split-step quintic B-spline collocation methods for nonlinear Schrödinger equations. AIMS Mathematics, 2023, 8(8): 19794-19815. doi: 10.3934/math.20231009
[7]	Osama Ala'yed, Belal Batiha, Diala Alghazo, Firas Ghanim . Cubic B-Spline method for the solution of the quadratic Riccati differential equation. AIMS Mathematics, 2023, 8(4): 9576-9584. doi: 10.3934/math.2023483
[8]	Abdul Majeed, Muhammad Abbas, Amna Abdul Sittar, Md Yushalify Misro, Mohsin Kamran . Airplane designing using Quadratic Trigonometric B-spline with shape parameters. AIMS Mathematics, 2021, 6(7): 7669-7683. doi: 10.3934/math.2021445
[9]	Mei Li, Wanqiang Shen . Integral method from even to odd order for trigonometric B-spline basis. AIMS Mathematics, 2024, 9(12): 36470-36492. doi: 10.3934/math.20241729
[10]	Ram Kishun Lodhi, Saud Fahad Aldosary, Kottakkaran Sooppy Nisar, Ateq Alsaadi . Numerical solution of non-linear Bratu-type boundary value problems via quintic B-spline collocation method. AIMS Mathematics, 2022, 7(4): 7257-7273. doi: 10.3934/math.2022405

Abstract

1. Introduction

The Lane-Emden equation represents a dimensionless form of Poisson's equation that arises in astrophysics for the spherically symmetric, polytrophic fluids, and the gravitational potential of Newtonian self-gravitating ^[1,2,3]. Modeling diverse phenomena in astrophysics, physical, and mathematical physics, such as the stellar structure theory, isothermal gas spheres, the thermal dynamic of a spherical gas cloud, the thermionic current theory, chemical reactions, population evolution, and pattern formation, results in scalar and systems of Lane-Emden equations, see ^[4,5] and the references therein. While there has been little research on Lane-Emden equation systems, recent attention to studying this type of systems has increased considerably ^[5].

In this study, we consider the following Lane-Emden system of the form

$\frac{{d}^{2}{\omega }_{i}\left(\tau \right)}{d{\tau }^{2}}+\frac{{\delta }_{i}}{\tau }\frac{d{\omega }_{i}\left(\tau \right)}{d\tau }+{\hslash }_{i}\left(\tau , {\omega }_{1}\left(\tau \right), {\omega }_{2}\left(\tau \right)\right) = {\aleph }_{i}\left(\tau \right), i = 1, 2,$

(1)

subject to

${\omega }_{i}\left(0\right) = {\varepsilon }_{i}, {\omega }_{i}^{\text{'}}\left(0\right) = 0,$

(2)

where ${\delta }_{1}, {\delta }_{2}, {\varepsilon }_{1}, \;\mathrm{a}\mathrm{n}\mathrm{d}\;{\varepsilon }_{2}$ are real constants, and ${\hslash }_{i}$ and ${\aleph }_{i}\left(\tau \right), i = 1, 2$ are given continuous functions.

Numerous approaches have been established for solving scalar and systems of Lane-Emden equations, including the Haar wavelet collocation method ^[6], Laplace transform and residual error function ^[7], Bernoulli wavelets functional matrix technique ^[5], B-spline methods ^[8,9,10], Adomian decomposition method ^[9], Chebyshev operational matrix method ^[4], variational iteration method ^[11,12], discontinuous finite element method ^[13], Bernstein collocation method ^[14], Bessel-collocation procedure ^[15], and Legendre Polynomials ^[16,17,18].

The literature survey reveals that collocation methods are an important tool in obtaining approximate solutions for different types of differential equations, including different classes of initial and boundary value problems, Singular differential equations, partial and fractional partial differential equations, system of partial differential equations, fractional Volterra integro-differential equations, and Abel's integral equations, ^{[19,20,21,22,23,24,25,26,27,28,29,30,31,32]}, among others. One well-known established method among collocation methods is the so-called B-spline method, where the letter "B" represents "basis". This method was originally introduced by Schoenberg in 1946. The primary motivation for introducing the B-splines is the creation of a stable interpolating function across finite number of points, which maintain the smoothness and the shape of the data ^[33,34]. Recently, B-spline methods have been demonstrated to be useful in approximation theory, image processing, and numerical computation due to their valuable properties such as numerical computation stability, local effects of coefficient changes, and built-in smoothness between adjacent polynomial pieces.

The spline methods, as is known, provide inaccurate solutions with the presence of singularity. To defeat the drawback of these methods, we, in this work, develop an effective method based on quintic B-spline functions, known as the quintic B-spline method (QBSM), to approximate the solution of (1). To construct the QBSM, the approximate solution is forced to fulfill the considered system at the grid points, converting it into a set of algebraic equations with unknown coefficients. Solving the set of algebraic equations determines the values of these coefficients. Note that the considered problem has a singularity at $\tau = 0.$ When addressing the singularity of (1) numerically, it is important to efficiently deal with the singularity via certain means. In our case, we employ the L'Hôpital rule to its second term. To the best of our knowledge, the results presented in this work are new and have not been previously presented in the literature. The method is illustrated with several test problems. It is demonstrated that the accuracy of the method is of fourth-order convergence, superior to the convergence of the cubic B-spline method, which is proven to be of second-order convergence, derived in our prior work ^[8]. Outcomes are compared with some other numerical solutions to demonstrate the advantage of the method.

The structure of this paper is as follows: Section 2 provides the preliminaries of the quintic B-spine functions and their properties. Section 3 is dedicated to the construction of QBSM for obtaining the solution of the considered system. Section 4 discusses the convergence of the method. Section 5 provides the numerical illustration, and, finally, Section 6 summarizes and concludes our work.

2. Preliminaries

In this section, we define quintic B-spline functions and their main properties to be utilized in constructing QBSM. We construct this method upon a uniform mesh. To do this, we partition the solution domain $\mathrm{\Gamma } = [\alpha, \beta]$ into $k$ subintervals ${\mathrm{\Gamma }}_{i} = [{\tau }_{i}, {\tau }_{i+1}$ ] by the grid points ${\tau }_{i} = \alpha +i\mathrm{\Lambda }$ $(i = 0, 1, ..., k)$ , where $\mathrm{\Lambda } = (\beta -\alpha)/k.$ Let $\mathrm{\Omega }$ be the set of these grid points of the solution domain $\mathrm{\Gamma }$ , referred to as the partition of $\mathrm{\Gamma }$ , and is defined as $\mathrm{\Omega } = \left\{{\tau }_{0}, {\tau }_{1}, \dots, {\tau }_{k}\right\}.$ To provide proper support for the quintic B-spline functions, it is essential to introduce an additional five grid points on each side of the solution domain $\mathrm{\Gamma }$ . Consequently, the solution domain $\mathrm{\Gamma }$ is extended to $\stackrel{-}{\mathrm{\Gamma }} = [\alpha -5\mathrm{\Lambda }, \beta +5\mathrm{\Lambda }]$ with ${\tau }_{i} = \alpha +i\mathrm{\Lambda }$ $\left(i = -5, ..., k+5\right).$ The linear space of quintic splines over this defined partition is expressed as

${\mathrm{{\rm M}}}_{5}\left(\mathrm{\Gamma }\right) = \{\mu \left(\tau \right)\in {C}^{4}\left(\mathrm{\Gamma }\right):{\mu \left(\tau \right)|}_{{\mathrm{\Gamma }}_{i}}\in {P}_{5}, i = 0, . . . , k-1\},$

where ${\mu \left(\tau \right)|}_{{\mathrm{\Gamma }}_{i}}$ indicates the restriction of $\mu \left(\tau \right)$ over ${\mathrm{\Gamma }}_{i}$ and ${P}_{5}$ designates the set of one-variable quintic polynomials. The dimension of the linear space ${\mathrm{{\rm M}}}_{5}\left(\mathrm{\Gamma }\right)$ is $(k+5).$ According to ^[30], the quintic B-spline ${\mathrm{{\rm K}}}_{r}\left(\tau \right)(r = -2, ..., k+2)$ is defined as

${\mathrm{{\rm K}}}_{r}\left(\tau \right) = \frac{1}{{120\mathrm{\Lambda }}^{5}}\left\{\begin{array}{l}{\left(\tau -{\tau }_{r-3}\right)}^{5}, \\ {\left(\tau -{\tau }_{r-3}\right)}^{5}-6{\left(\tau -{\tau }_{r-2}\right)}^{5}, \\ {\left(\tau -{\tau }_{r-3}\right)}^{5}-6{\left(\tau -{\tau }_{r-2}\right)}^{5}+15{\left(\tau -{\tau }_{r-1}\right)}^{5}, \\ {\left(-\tau +{\tau }_{r+3}\right)}^{5}-6{\left(-\tau +{\tau }_{r-2}\right)}^{5}+15{\left(-\tau +{\tau }_{r+1}\right)}^{5}, \\ {\left(-\tau +{\tau }_{r+3}\right)}^{5}-6{\left(\tau +{\tau }_{r+2}\right)}^{5}, \\ {\left(\tau -{\tau }_{r-3}\right)}^{5}, \\ 0, \end{array}\right. \begin{array}{c}\tau \in [{\tau }_{r-3}, {\tau }_{r-2}]\\ \tau \in [{\tau }_{r-2}, {\tau }_{r-1}]\\ \tau \in \left[{\tau }_{r-1}, {\tau }_{r}\right]\\ \tau \in \left[{\tau }_{r}, {\tau }_{r+1}\right]\\ \tau \in \left[{\tau }_{r+1}, {\tau }_{r+2}\right]\\ \tau \in [{\tau }_{r+2}, {\tau }_{r+3}]\\ \text{e}\text{l}\text{s}\text{e}\text{.}\end{array}$

The basis functions ${\mathrm{{\rm K}}}_{r}$ , $r = -2, ..., k+2$ , are nonnegative and linearly independent on the domain $\left[\alpha, \beta \right].$ The values of ${\mathrm{{\rm K}}}_{r}\left(\tau \right)$ and their derivatives up to the third order at the grid points are recorded in Table 1.

Table 1. The values of

${\mathrm{{\rm K}}}_{r}^{\left(\nu \right)}\left(\tau \right)(\nu = 0, 1, 2, 3)$ at the grid points.

	${\tau }_{r-2}$	${\tau }_{r-1}$	${\tau }_{r}$	${\tau }_{r+1}$	${\tau }_{r+2}$	else
${\mathrm{{\rm K}}}_{r}\left(\tau \right)$	$\frac{1}{120}$	$\frac{26}{120}$	$\frac{66}{120}$	$\frac{26}{120}$	$\frac{1}{120}$	0
${\mathrm{{\rm K}}}_{r}^{\text{'}}\left(\tau \right)$	$\frac{1}{24\mathrm{\Lambda }}$	$\frac{10}{24\mathrm{\Lambda }}$	0	$-\frac{10}{24\mathrm{\Lambda }}$	$-\frac{1}{24\mathrm{\Lambda }}$	0
${\mathrm{{\rm K}}}_{r}^{\text{'}\text{'}}\left(\tau \right)$	$\frac{1}{{6\mathrm{ }\mathrm{\Lambda }}^{2}}$	$\frac{2}{{6\mathrm{ }\mathrm{\Lambda }}^{2}}$	$\frac{-6}{6{\mathrm{\Lambda }}^{2}}$	$\frac{2}{{6\mathrm{ }\mathrm{\Lambda }}^{2}}$	$\frac{1}{{6\mathrm{ }\mathrm{\Lambda }}^{2}}$	0
${\mathrm{{\rm K}}}_{r}^{\text{'}\text{'}\text{'}}\left(\tau \right)$	$\frac{1}{{2\mathrm{ }\mathrm{\Lambda }}^{3}}$	$-\frac{2}{{2\mathrm{ }\mathrm{\Lambda }}^{3}}$	0	$\frac{2}{{2\mathrm{ }\mathrm{\Lambda }}^{3}}$	$-\frac{1}{{2\mathrm{ }\mathrm{\Lambda }}^{3}}$	0

| Show Table

DownLoad: CSV

For an appropriately smooth function $\omega \left(\tau \right)$ , one can uniquely define a quintic spline

$\mu \left(\tau \right) = \sum\limits_{r = -2}^{k+2}{{\mathrm{\lambda }}_{r}\mathrm{{\rm K}}}_{r}\left(\tau \right)\in {\mathrm{{\rm M}}}_{5}\left(I\right)$

that fulfill the interpolation conditions $\mu \left({\tau }_{i}\right) = \omega \left({\tau }_{i}\right), i = 0, ..., k,$ and ${\mu }^{\text{'}}\left(\alpha \right) = {\omega }^{\text{'}}\left(\alpha \right).$ From , for the discretization knots ${\tau }_{j}(j = 0, ..., k)$ , we get

$\mu \left({\tau }_{j}\right) = \sum\limits_{r = -2}^{k+2}{\mathrm{\lambda }}_{r}{\mathrm{K}}_{r}\left({\tau }_{j}\right) = \frac{{\mathrm{\lambda }}_{j-2}+26{\mathrm{\lambda }}_{j-1}+66{\mathrm{\lambda }}_{j}+26{\mathrm{\lambda }}_{j+1}+{\mathrm{\lambda }}_{j+2}}{120},$

(3)

${\mu }^{\text{'}}\left({\tau }_{j}\right) = \sum\limits_{r = -2}^{k+2}{\mathrm{\lambda }}_{r}{\mathrm{K}}_{r}^{\text{'}}\left({\tau }_{j}\right) = \frac{-{\mathrm{\lambda }}_{j-2}-10{\mathrm{\lambda }}_{j-1}+10{\mathrm{\lambda }}_{j+1}+{\mathrm{\lambda }}_{j+2}}{24\mathrm{\Lambda }},$

(4)

${\mu }^{\text{'}\text{'}}\left({\tau }_{j}\right) = \sum\limits_{r = -2}^{k+2}{\mathrm{\lambda }}_{r}{\mathrm{K}}_{r}^{\text{'}\text{'}}\left({\tau }_{j}\right) = \frac{{\mathrm{\lambda }}_{j-2}+2{\mathrm{\lambda }}_{j-1}-6{\mathrm{\lambda }}_{j}+2{\mathrm{\lambda }}_{j+1}+{\mathrm{\lambda }}_{j+2}}{6{\mathrm{\Lambda }}^{2}},$

(5)

${\mu }^{\text{'}\text{'}\text{'}}\left({\tau }_{j}\right) = \sum\limits_{r = -2}^{k+2}{\mathrm{\lambda }}_{r}{\mathrm{K}}_{r}^{\text{'}\text{'}\text{'}}\left({\tau }_{j}\right) = \frac{-{\mathrm{\lambda }}_{j-2}+2{\mathrm{\lambda }}_{j-1}-2{\mathrm{\lambda }}_{j+1}+{\mathrm{\lambda }}_{j+2}}{2{\mathrm{\Lambda }}^{3}}.$

(6)

Equations (3)–(6) serve as the fundamental relations in the construction of the QBSM.

3. Construction and convergence analysis of the method

This part of the study discusses the method and the convergence analysis.

3.1. Construction of QPSM

In this section, we present the development of a collocation method based on quintic B-spline functions for (1) and (2). Let ${\mu }_{i}\left(\tau \right) = \sum _{r = -2}^{k+2}{{\mathrm{\lambda }}_{i, r}\mathrm{{\rm K}}}_{r}\left(\tau \right), i = 1, 2,$ represents the quintic B-spline approximate solution of the exact solution ${\omega }_{i}\left(\tau \right)$ to (1). To overcome the singularity behavior of (1), we employ the L'Hôpital rule on the second term at $\tau = 0,$ to obtain

$\left(1+{\delta }_{i}\right)\frac{{d}^{2}{\omega }_{i}\left(\tau \right)}{d{\tau }^{2}}+{\hslash }_{i}\left(\tau , {\omega }_{1}\left(\tau \right), {\omega }_{2}\left(\tau \right)\right) = {\aleph }_{i}\left(\tau \right), \mathrm{f}\mathrm{o}\mathrm{r}\;\tau = 0,$

(7)

Discretizing (7), we get

$(1+{\delta }_{i})\frac{{d}^{2}{\omega }_{i}\left({\tau }_{0}\right)}{d{\tau }^{2}}+{\hslash }_{i}({\tau }_{0}, {\omega }_{1}({\tau }_{0}), {\omega }_{2}({\tau }_{0}\left)\right) = {\aleph }_{i}\left({\tau }_{0}\right),$

$\frac{{d}^{2}{\omega }_{i}\left({\tau }_{j}\right)}{d{\tau }^{2}}+\frac{{\delta }_{i}}{{\tau }_{j}}\frac{d{\omega }_{i}\left({\tau }_{j}\right)}{d\tau }+{\hslash }_{i}\left({\tau }_{j}, {\omega }_{1}\left({\tau }_{j}\right), {\omega }_{2}\left({\tau }_{j}\right)\right) = {\aleph }_{i}\left({\tau }_{j}\right),$

(8)

where $j = 1, \cdots, k.$ Using (3)–(5), we have

$\begin{array}{c}\left(1+{\delta }_{i}\right)\left(\frac{{\mathrm{\lambda }}_{i, -2}+2{\mathrm{\lambda }}_{i, -1}-6{\mathrm{\lambda }}_{i, 0}+2{\mathrm{\lambda }}_{i, 1}+{\mathrm{\lambda }}_{i, 2}}{6{\mathrm{\Lambda }}^{2}}\right)+{\hslash }_{i}\left({\tau }_{0}, {\varepsilon }_{1}, {\vartheta }_{1}\right) = {\aleph }_{i}\left({\tau }_{0}\right), \\\left(\frac{{\mathrm{\lambda }}_{i, j-2}+2{\mathrm{\lambda }}_{i, j-1}-6{\mathrm{\lambda }}_{i, j}+2{\mathrm{\lambda }}_{i, j+1}+{\mathrm{\lambda }}_{i, j+2}}{6{\mathrm{\Lambda }}^{2}}\right)+\frac{{\delta }_{i}}{{\tau }_{j}}\left(\frac{-{\mathrm{\lambda }}_{i, j-2}-10{\mathrm{\lambda }}_{i, j-1}+10{\mathrm{\lambda }}_{i, j+1}+{\mathrm{\lambda }}_{i, j+2}}{24\mathrm{\Lambda }}\right)\\+{\varrho }_{i}\left({\mathrm{\lambda }}_{1, j-2}, {\mathrm{\lambda }}_{1, j-1}, {\mathrm{\lambda }}_{1, j}, {\mathrm{\lambda }}_{1, j+1}, {\mathrm{\lambda }}_{1, j+2}, {\mathrm{\lambda }}_{2, j-2}, {\mathrm{\lambda }}_{2, j-1}, {\mathrm{\lambda }}_{2, j}, {\mathrm{\lambda }}_{2, j+1}, {\mathrm{\lambda }}_{2, j+2}\right) = {\aleph }_{i}\left({\tau }_{j}\right), \end{array}$

(9)

where $i = 1, 2$ and $j = 1, \cdots, k.$ Additionally, from (2), we derive the following four equations

${\omega }_{i}\left(0\right) = {\varepsilon }_{i} = \frac{{\mathrm{\lambda }}_{i, -2}+26{\mathrm{\lambda }}_{i, -1}+66{\mathrm{\lambda }}_{i, 0}+26{\mathrm{\lambda }}_{i, 1}+{\mathrm{\lambda }}_{i, 2}}{120},$

(10)

${\omega }_{i}^{\text{'}}\left(0\right) = 0 = \frac{-{\mathrm{\lambda }}_{i, -2}-10{\mathrm{\lambda }}_{i, -1}+10{\mathrm{\lambda }}_{i, 1}+{\mathrm{\lambda }}_{i, 2}}{24\mathrm{\Lambda }},$

(11)

where $i = 1, 2.$ Four equations are still needed. Therefore, by differentiating (1), we obtain:

$\begin{array}{c}\frac{{d}^{3}{\omega }_{i}\left(\tau \right)}{d{\tau }^{2}}+{\delta }_{i}\frac{\tau {\omega }_{i}^{\text{'}\text{'}}\left(\tau \right)-{\omega }_{i}^{\text{'}}\left(\tau \right)}{{\tau }^{2}}+\frac{d}{d\tau }{\hslash }_{i}\left(\tau , {\omega }_{1}\left(\tau \right), {\omega }_{2}\left(\tau \right)\right)\\+\frac{d{\hslash }_{i}\left(\tau , {\omega }_{1}\left(\tau \right), {\omega }_{2}\left(\tau \right)\right)}{d{\omega }_{1}\left(\tau \right)}{\omega }_{1}^{\text{'}}\left(\tau \right)+\frac{d{\hslash }_{i}\left(\tau , {\omega }_{1}\left(\tau \right), {\omega }_{2}\left(\tau \right)\right)}{d{\omega }_{2}\left(\tau \right)}{\omega }_{2}^{\text{'}}\left(\tau \right) = {\aleph }_{i}^{\text{'}}\left(\tau \right). \end{array}$

(12)

Applying the L'Hôpital rule and using (2)–(4), (6) and (12) becomes

$\left(1+\frac{{\delta }_{i}}{2}\right)\left(\frac{-{\mathrm{\lambda }}_{i, -2}+2{\mathrm{\lambda }}_{i, -1}-2{\mathrm{\lambda }}_{i, 1}+{\mathrm{\lambda }}_{i, 2}}{2{\mathrm{\Lambda }}^{3}}\right)+\frac{d}{d\tau }{\hslash }_{i}\left({\tau }_{0}, {\varepsilon }_{1}, {\varepsilon }_{2}\right) = {\aleph }_{i}^{\text{'}}\left(0\right).$

(13)

Similarly, at $\tau = 1$ , we obtain

$\begin{array}{c} \frac{-{\mathrm{\lambda }}_{i, k-2}+2{\mathrm{\lambda }}_{i, k-1}-2{\mathrm{\lambda }}_{i, k+1}+{\mathrm{\lambda }}_{i, k+2}}{2{\mathrm{\Lambda }}^{3}}\\+{\varpi }_{i}\left({\mathrm{\lambda }}_{1, k-2}, {\mathrm{\lambda }}_{1, k-1}, {\mathrm{\lambda }}_{1, k}, {\mathrm{\lambda }}_{1, k+1}, {\mathrm{\lambda }}_{1, k+2}, {\mathrm{\lambda }}_{2, k-2}, {\mathrm{\lambda }}_{2, k-1}, {\mathrm{\lambda }}_{2, k}, {\mathrm{\lambda }}_{2, k+1}, {\mathrm{\lambda }}_{2, k+2}\right) = {\aleph }_{i}^{\text{'}}\left(1\right),\end{array}$

(14)

where $i = 1, 2$ .

Expressing (9)–(11), (13), and (14) in matrix form as

$\mathrm{A}\mathrm{\Phi } = \mathrm{\Psi },$

(15)

where A represents a coefficient matrix of dimension $2(k+5)\times 2(k+5)$ , $\mathrm{\Phi }$ is a column vector defined as

$\mathrm{\Phi } = [{\mathrm{\lambda }}_{1, -2}, \cdots , {\mathrm{\lambda }}_{1, k+2}, {\mathrm{\lambda }}_{2, -2}, \cdots , {\mathrm{\lambda }}_{2, k+2}{]}^{T} ,$

and $\mathrm{\Psi }$ is a column vector with $2(k+5)$ entries. Solving this system yields the coefficients of the approximate solution ${\mu }_{i}\left(\tau \right)$ for (1).

3.2. Convergence analysis

In this section, we demonstrate the convergence analysis of QBSM. To facilitate this analysis, we assume that ${\omega }_{i}\left(\tau \right)\in {C}^{5}\left[\mathrm{0, 1}\right], i = \mathrm{1, 2}.$ From (3)–(6), we have ^[35,36]

$\begin{array}{c}{\mu }_{i}^{\text{'}}\left({\tau }_{j-2}\right)+26{\mu }_{i}^{\text{'}}\left({\tau }_{j-1}\right)+66{\mu }_{i}^{\text{'}}\left({\tau }_{j}\right)+26{\mu }_{i}^{\text{'}}\left({\tau }_{j+1}\right)+{\mu }_{i}^{\text{'}}\left({\tau }_{j+2}\right) \\ = \frac{-5{\omega }_{i}\left({\tau }_{j-2}\right)-50{\omega }_{i}\left({\tau }_{j-1}\right)+50{\omega }_{i}\left({\tau }_{j+1}\right)+5{\omega }_{i}\left({\tau }_{j+2}\right)}{\mathrm{\Lambda }}, \\{\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j-2}\right)+26{\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j-1}\right)+66{\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j}\right)+26{\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j+1}\right)+{\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j+2}\right)\\ = \frac{20{\omega }_{i}\left({\tau }_{j-2}\right)+40{\omega }_{i}\left({\tau }_{j-1}\right)-120{\omega }_{i}\left({\tau }_{j}\right)+40{\omega }_{i}\left({\tau }_{j+1}\right)+20{\omega }_{i}\left({\tau }_{j+2}\right)}{{\mathrm{\Lambda }}^{2}}, \\ {\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j-2}\right)+26{\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j-1}\right)+66{\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j}\right)+26{\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j+1}\right)+{\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j+2}\right) \\ = \frac{-60{\omega }_{i}\left({\tau }_{j-2}\right)+120{\omega }_{i}\left({\tau }_{j-1}\right)-120{\omega }_{i}\left({\tau }_{j+1}\right)+60{\omega }_{i}\left({\tau }_{j+2}\right)}{{\mathrm{\Lambda }}^{3}}. \end{array}$

(16)

With the operator notations, $\mathrm{\Xi }{\omega }_{i}\left({\tau }_{j}\right) = {\omega }_{i}\left({\tau }_{j+1}\right), D{\omega }_{i}\left({\tau }_{j}\right) = {\omega }_{i}^{\text{'}}\left({\tau }_{j}\right)$ , and $I{\omega }_{i}\left({\tau }_{j}\right) = {\omega }_{i}\left({\tau }_{j}\right)$ , Eq (16) can be expressed as

${\mu }_{i}^{\text{'}}\left({\tau }_{j}\right) = \frac{1}{\mathrm{\Lambda }}\left(\frac{-5{\mathrm{\Xi }}^{-2}-50{\mathrm{\Xi }}^{-1}+50\mathrm{\Xi }+5{\mathrm{\Xi }}^{2}}{{\mathrm{\Xi }}^{-2}+26{\mathrm{\Xi }}^{-1}+66I+26\mathrm{\Xi }+{\mathrm{\Xi }}^{2}}\right){\omega }_{i}\left({\tau }_{j}\right),$

${\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j}\right) = \frac{1}{{\mathrm{\Lambda }}^{2}}\left(\frac{20{\mathrm{\Xi }}^{-2}+40{\mathrm{\Xi }}^{-1}-120I+40\mathrm{\Xi }+20{\mathrm{\Xi }}^{2}}{{\mathrm{\Xi }}^{-2}+26{\mathrm{\Xi }}^{-1}+66I+26\mathrm{\Xi }+{\mathrm{\Xi }}^{2}}\right){\omega }_{i}\left({\tau }_{j}\right),$

${\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j}\right) = \frac{1}{{\mathrm{\Lambda }}^{3}}\left(\frac{-60{\mathrm{\Xi }}^{-2}+120{\mathrm{\Xi }}^{-1}-120\mathrm{\Xi }+60{\mathrm{\Xi }}^{2}}{{\mathrm{\Xi }}^{-2}+26{\mathrm{\Xi }}^{-1}+66I+26\mathrm{\Xi }+{\mathrm{\Xi }}^{2}}\right){\omega }_{i}\left({\tau }_{j}\right),$

(17)

$i = \mathrm{1, 2}.$ Setting $\mathrm{\Xi } = {e}^{\mathrm{\Lambda }D}$ in (17) gives

${\mu }_{i}^{\text{'}}\left({\tau }_{j}\right) = \frac{1}{\mathrm{\Lambda }}\left(\frac{-5{e}^{-2\mathrm{\Lambda }D}-50{e}^{-\mathrm{\Lambda }D}+50{e}^{\mathrm{\Lambda }D}+5{e}^{2\mathrm{\Lambda }D}}{{e}^{-2\mathrm{\Lambda }D}+26{e}^{-\mathrm{\Lambda }D}+66+26{e}^{\mathrm{\Lambda }D}+{e}^{2\mathrm{\Lambda }D}}\right){\omega }_{i}\left({\tau }_{j}\right),$

${\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j}\right) = \frac{1}{{\mathrm{\Lambda }}^{2}}\left(\frac{20{e}^{-2\mathrm{\Lambda }D}+40{e}^{-\mathrm{\Lambda }D}-120+40{e}^{\mathrm{\Lambda }D}+20{e}^{2\mathrm{\Lambda }D}}{{e}^{-2\mathrm{\Lambda }D}+26{e}^{-\mathrm{\Lambda }D}+66+26{e}^{\mathrm{\Lambda }D}+{e}^{2\mathrm{\Lambda }D}}\right){\omega }_{i}\left({\tau }_{j}\right),$

${\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j}\right) = \frac{1}{{\mathrm{\Lambda }}^{3}}\left(\frac{-60{e}^{-2\mathrm{\Lambda }D}+120{e}^{-\mathrm{\Lambda }D}-120{e}^{\mathrm{\Lambda }D}+60{e}^{2\mathrm{\Lambda }D}}{{e}^{-2\mathrm{\Lambda }D}+26{e}^{-\mathrm{\Lambda }D}+66+26{e}^{\mathrm{\Lambda }D}+{e}^{2\mathrm{\Lambda }D}}\right){\omega }_{i}\left({\tau }_{j}\right),$

(18)

Expanding the exponential functions in (18) in powers of $\mathrm{\Lambda }D$ , we obtain

${\mu }_{i}^{\text{'}}\left({\tau }_{j}\right) = {\omega }_{i}^{\text{'}}\left({\tau }_{j}\right)+\frac{1}{5040}{\mathrm{\Lambda }}^{6}{\omega }_{i}^{\left(7\right)}\left({\tau }_{j}\right)+O\left({\mathrm{\Lambda }}^{8}\right),$

${\mu }_{i}^{\text{'}\text{'}}\left({\tau }_{j}\right) = {\omega }_{i}^{\text{'}\text{'}}\left({\tau }_{j}\right)+\frac{1}{720}{\mathrm{\Lambda }}^{4}{\omega }_{i}^{\left(6\right)}\left({\tau }_{j}\right)+O\left({\mathrm{\Lambda }}^{6}\right),$

${\mu }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j}\right) = {\omega }_{i}^{\text{'}\text{'}\text{'}}\left({\tau }_{j}\right)-\frac{1}{240}{\mathrm{\Lambda }}^{4}{\omega }_{i}^{\left(7\right)}\left({\tau }_{j}\right)+O\left({\mathrm{\Lambda }}^{6}\right),$

(19)

$i = \mathrm{1, 2}.$ Next, let's define truncation error as follows

${e}_{i}\left({\tau }_{j}\right) = {\aleph }_{i}\left({\tau }_{j}\right)-\frac{{d}^{2}{\omega }_{i}\left({\tau }_{j}\right)}{d{\tau }^{2}}-\frac{{\delta }_{i}}{{\tau }_{j}}\frac{d{\omega }_{1}\left({\tau }_{j}\right)}{d\tau }-{\hslash }_{i}\left({\omega }_{1}\left({\tau }_{j}\right), {\omega }_{2}\left({\tau }_{j}\right)\right)\\ \;\;\;\;\;\;\;\; = \left[\frac{{d}^{2}{\mu }_{i}\left({\tau }_{j}\right)}{d{\tau }^{2}}+\frac{{\delta }_{i}}{{\tau }_{j}}\frac{d{\mu }_{1}\left({\tau }_{j}\right)}{d\tau }+{\hslash }_{i}\left({\mu }_{1}\left({\tau }_{j}\right), {\mu }_{2}\left({\tau }_{j}\right)\right)\right]\\\;\;\;\;\;\;\;\;\;\;-\frac{{d}^{2}{\omega }_{i}\left({\tau }_{j}\right)}{d{\tau }^{2}}-\frac{{\delta }_{i}}{{\tau }_{j}}\frac{d{\omega }_{1}\left({\tau }_{j}\right)}{d\tau }-{\hslash }_{i}\left({\omega }_{1}\left({\tau }_{j}\right), {\omega }_{2}\left({\tau }_{j}\right)\right).$

(20)

As ${\mu }_{i}\left({\tau }_{j}\right) = {\omega }_{i}\left({\tau }_{j}\right), i = 1, 2$ and $j = 1, ..., k,$ Eq (20) can be simplified as

${e}_{i}\left({\tau }_{j}\right) = \left[\frac{{d}^{2}{\mu }_{i}\left({\tau }_{j}\right)}{d{\tau }^{2}}-\frac{{d}^{2}{\omega }_{i}\left({\tau }_{j}\right)}{d{\tau }^{2}}\right]+\frac{{\delta }_{i}}{{\tau }_{j}}\left[\frac{d{\mu }_{i}\left({\tau }_{j}\right)}{d\tau }-\frac{d{\omega }_{i}\left({\tau }_{j}\right)}{d\tau }\right],$

(21)

Hence, by using (19) in (21), we can conclude that

${‖{e}_{i}\left({\tau }_{j}\right)‖}_{\infty } = O\left({\Lambda }^{4}\right),$

(22)

and for j = 0, we have

${e}_{i}\left({\tau }_{0}\right) = {\aleph }_{i}\left({\tau }_{0}\right)-\left(1+{\delta }_{i}\right)\frac{{d}^{2}{\omega }_{i}\left({\tau }_{0}\right)}{d{\tau }^{2}}-{\hslash }_{i}\left({\omega }_{1}\left({\tau }_{0}\right), {\omega }_{2}\left({\tau }_{0}\right)\right) \\ \;\;\;\;\;\;\;\; = \left(1+{\delta }_{i}\right)\frac{{d}^{2}{\mu }_{i}\left({\tau }_{0}\right)}{d{\tau }^{2}}+{\hslash }_{i}\left({\mu }_{1}\left({\tau }_{0}\right), {\mu }_{2}\left({\tau }_{0}\right)\right) \\\;\;\;\;\;\;\;\;-\left(1+{\delta }_{i}\right)\frac{{d}^{2}{\omega }_{i}\left({\tau }_{0}\right)}{d{\tau }^{2}}-{\hslash }_{i}({\omega }_{1}\left({\tau }_{0}\right), {\omega }_{2}\left({\tau }_{0}\right).$

(23)

As ${\mu }_{i}\left({\tau }_{0}\right) = {\omega }_{i}\left({\tau }_{0}\right), i = 1, 2,$ Eq (23) can be simplified as

${e}_{i}\left({\tau }_{j}\right) = \left(1+{\delta }_{i}\right)\left[\frac{{d}^{2}{\mu }_{i}\left({\tau }_{0}\right)}{d{\tau }^{2}}-\frac{{d}^{2}{\omega }_{i}\left({\tau }_{0}\right)}{d{\tau }^{2}}\right].$

(24)

Hence, by using (19) in (24), we find

${‖{e}_{i}\left({\tau }_{0}\right)‖}_{\infty } = O\left({\mathrm{\Lambda }}^{4}\right).$

(25)

In light of (22) and (25), it can be deduced that the truncation error for the Lane-Emden system is of the order $O\left({\mathrm{\Lambda }}^{4}\right).$

4. Numerical results

In this section, five test problems are considered to demonstrate the accuracy and applicability of QBSM. Additionally, the obtained numerical results corresponding to the considered system have been compared with those achieved previously ^[4,8,37]. Note that, in our calculations, " $\mathrm{E}-n$ " means ${10}^{-n}.$

The absolute error ( ${Abs}_{i}$ ) and ${L}_{\infty }$ error are defined by

${Abs}_{i} = \left|{\omega }_{i}\left({\tau }_{j}\right)-{\mu }_{i}\left({\tau }_{j}\right)\right|, i = \mathrm{1, 2},$

${L}_{\infty }^{i}\left(k\right) = \underset{0\le j\le k}{\mathrm{max}}\left|{\omega }_{i}\left({\tau }_{j}\right)-{\mu }_{i}\left({\tau }_{j}\right)\right|, i = \mathrm{1, 2},$

where ${\omega }_{i}\left(\tau \right)$ and ${\mu }_{i}\left(\tau \right)$ represent the exact and QBSM solutions at the grid point ${\tau }_{j}$ , respectively. Moreover, the order of convergence (OC) of the method is computed by applying the following formula:

${OC}^{i} = {\mathrm{log}}_{2}\left(\frac{{L}_{\infty }^{i}\left(k\right)}{{L}_{\infty }^{i}\left(2k\right)}\right), i = \mathrm{1, 2}.$

Problem 1. Consider the following system

$\frac{{d}^{2}{\omega }_{1}\left(\tau \right)}{d{\tau }^{2}}+\frac{3}{\tau }\frac{d{\omega }_{1}\left(\tau \right)}{d\tau }-4({\omega }_{1}\left(\tau \right)+{\omega }_{2}\left(\tau \right)) = 0,$

(26)

subject to

${\omega }_{1}\left(0\right) = 1, {{\omega }^{\text{'}}}_{1}\left(0\right) = 0,$

${\omega }_{2}\left(0\right) = 1, {{\omega }^{\text{'}}}_{2}\left(0\right) = 0.$

(27)

The exact solution for this system is ${\omega }_{1}\left(\tau \right) = 1+{\tau }^{2}, {\omega }_{2}\left(\tau \right) = 1-{\tau }^{2}.$

We apply the proposed QBSM to solve this problem for $\mathrm{\Lambda } = 0.1$ . Table 2 presents the exact and approximate solutions at the grid points. It is worth mentioning that, for this problem, the outcomes are exact and the errors are only incurred caused by round-off errors in computational processes.

Table 2. Absolute errors of Problem 1.

$\boldsymbol{\tau }$	${\boldsymbol{\omega }}_\bf{1}\left(\boldsymbol{\tau }\right)$	${\boldsymbol{\mu }}_\bf{1}\left(\boldsymbol{\tau }\right)$ ( $\mathbf{\Lambda=0.1 }$ )	${\boldsymbol{A}\boldsymbol{b}\boldsymbol{s}}_\bf{1}$	${\boldsymbol{\omega }}_\bf{2}\left(\boldsymbol{\tau }\right)$	${\boldsymbol{\mu }}_\bf{2}\left(\boldsymbol{\tau }\right)$ ( $\mathbf{\Lambda=0.1 }$ )	${\boldsymbol{A}\boldsymbol{b}\boldsymbol{s}}_\bf{2}$
$0.0$	1	$1$	$1.11\mathrm{E}-16$	1	1	$0$
$0.1$	1.01	$1.01$	$2.22\mathrm{E}-16$	0.99	0.99	$0$
$0.2$	1.04	$1.04$	$2.22\mathrm{E}-16$	0.96	0.96	$1.11\mathrm{E}-16$
$0.3$	1.09	$1.09$	$2.22\mathrm{E}-16$	0.91	0.91	$1.11\mathrm{E}-16$
$0.4$	1.16	1.16	$2.22\mathrm{E}-16$	0.84	0.84	$1.11\mathrm{E}-16$
$0.5$	1.25	1.25	$0$	0.75	0.75	$0$
$0.6$	1.36	1.36	$2.22\mathrm{E}-16$	0.64	0.64	$1.11\mathrm{E}-16$
$0.7$	1.49	1.49	$0$	0.51	0.51	$2.22\mathrm{E}-16$
$0.8$	1.61	1.61	$2.22\mathrm{E}-16$	0.36	0.36	$2.77\mathrm{E}-16$
$0.9$	1.81	1.81	$2.22\mathrm{E}-16$	0.19	0.19	$3.33\mathrm{E}-16$
$1.0$	2	2	$0$	0	5.64 $\mathrm{E}-16$	$3.84\mathrm{E}-16$

| Show Table

DownLoad: CSV

Problem 2. Consider the following system

${\omega }_{1}^{\text{'}\text{'}}\left(\tau \right)+\frac{2}{\tau }{\omega }_{1}^{\text{'}}\left(\tau \right)-\left(4{\tau }^{2}+6\right){\omega }_{1}\left(\tau \right)+{\omega }_{2}\left(\tau \right) = {\tau }^{4}-{\tau }^{3},$

${\omega }_{2}^{\text{'}\text{'}}\left(\tau \right)+\frac{8}{\tau }{\omega }_{2}^{\text{'}}\left(\tau \right)+{\omega }_{1}\left(\tau \right)+\tau {\omega }_{2}\left(\tau \right) = {e}^{{\tau }^{2}}+{\tau }^{5}-{\tau }^{4}+44{\tau }^{2}-30\tau ,$

(28)

subject to

${\omega }_{1}\left(0\right) = 1, {{\omega }^{\text{'}}}_{1}\left(0\right) = 0,$

${\omega }_{2}\left(0\right) = 0, {{\omega }^{\text{'}}}_{2}\left(0\right) = 0.$

(29)

The exact solution of this system is

${\omega }_{1}\left(\tau \right) = {e}^{{\tau }^{2}}, {\omega }_{2}\left(\tau \right) = {\tau }^{4}-{\tau }^{3}.$

We apply the proposed QBSM to solve this problem for $\mathrm{\Lambda } = 0.1, 0.01$ . The logarithmic plots of absolute errors for various values of $k$ are depicted in , which exhibits that if the value of $k$ is increased, the error decreases. The absolute errors obtained by QBSM are given in Tables 3 and 4 along with those obtained by CBSM ^[8] and Chebyshev operational matrix method (COMM) ^[4]. Comparison reveals that QBSM yields more accurate solutions than the methods in ^[4,8]. The outcomes of ${L}_{\infty }^{i}\left(k\right)$ errors are listed using $k = 16, 32, 64,$ and $128$ . In addition, the ${OC}^{i}, i = \mathrm{1, 2},$ are computed and the results are tabulated in . It can be observed that the achieved ${OC}^{i}, i = \mathrm{1, 2},$ is four. The method's computational time (CPU time) is reported in the same Table, which confirms that the QBSM is computationally effective.

Figure 1. Logarithmic plots of absolute errors for Problem 2.

DownLoad: Full-Size Img PowerPoint

Table 3. Absolute errors for approximate solution of

${\omega }_{1}\left(\tau \right)$ in Problem 2.

$\boldsymbol{\tau }$	CBSM ^[8]		COMM ^[4]			QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda=0.1 }$	$\mathbf{\Lambda =0.01}$	$\boldsymbol{n}\mathbf{=5}$	$\boldsymbol{n}\mathbf{=6}$	$\boldsymbol{n}\mathbf{=8}$	$\mathbf{\Lambda =0.1}$	$\mathbf{\Lambda=0.01 }$
$0.0$	$0$	0	$8.00\mathrm{E}-9$	$5.00E-10$	0	$0$	0
$0.1$	$3.39\mathrm{E}-5$	$1.72\mathrm{E}-7$	----	----	----	$5.98\mathrm{E}-8$	$2.88\mathrm{E}-12$
$0.2$	$9.52\mathrm{E}-5$	$7.17\mathrm{E}-7$	$2.38\mathrm{E}-5$	$1.35\mathrm{E}-7$	$1.02\mathrm{E}-7$	$1.58\mathrm{E}-7$	$1.23\mathrm{E}-11$
$0.3$	$2.02\mathrm{E}-4$	$1.76\mathrm{E}-6$	----	----	----	$3.45\mathrm{E}-7$	$3.09\mathrm{E}-11$
$0.4$	$3.81\mathrm{E}-4$	$3.51\mathrm{E}-6$	$1.26\mathrm{E}-4$	$6.90\mathrm{E}-6$	$2.61\mathrm{E}-7$	$6.78\mathrm{E}-7$	$6.39\mathrm{E}-11$
$0.5$	$6.72\mathrm{E}-4$	$6.35\mathrm{E}-6$	----	----	----	$1.24\mathrm{E}-6$	$1.21\mathrm{E}-10$
$0.6$	$1.14\mathrm{E}-3$	$1.09\mathrm{E}-5$	$2.09\mathrm{E}-4$	$3.05\mathrm{E}-5$	$4.71\mathrm{E}-7$	$2.20\mathrm{E}-6$	$2.17\mathrm{E}-10$
$0.7$	$1.87\mathrm{E}-3$	$1.81\mathrm{E}-5$	----	----	----	$3.78\mathrm{E}-6$	$3.77\mathrm{E}-10$
$0.8$	$3.04\mathrm{E}-3$	$2.96\mathrm{E}-5$	$6.88\mathrm{E}-3$	$1.02\mathrm{E}-4$	$9.09\mathrm{E}-7$	$6.44\mathrm{E}-6$	$6.47\mathrm{E}-10$
$0.9$	$4.90\mathrm{E}-3$	$4.78\mathrm{E}-5$	----	----	----	$1.08\mathrm{E}-5$	$1.10\mathrm{E}-9$
$1.0$	$7.89\mathrm{E}-3$	$7.71\mathrm{E}-5$	$3.14\mathrm{E}-2$	$6.11\mathrm{E}-4$	$1.97\mathrm{E}-4$	$1.84\mathrm{E}-5$	$1.86\mathrm{E}-9$

| Show Table

DownLoad: CSV

Table 4. Absolute errors for approximate solution of

${\omega }_{2}\left(\tau \right)$ in Problem 2.

$\boldsymbol{\tau }$	CBSM ^[8]		COMM ^[4]			QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda =0.1 }$	$\mathbf{\Lambda =0.01}$	$\mathbf{n=5}$	$\mathbf{n=6}$	$\mathbf{n=8}$	$\mathbf{\Lambda =0.1 }$	$\mathbf{\Lambda =0.01}$
$0.0$	$6.00\mathrm{E}-31$	0	$0$	$0$	0	$7.23\mathrm{E}-21$	$2.82\mathrm{E}-23$
$0.1$	$4.67\mathrm{E}-5$	$1.13\mathrm{E}-7$	----	----	----	$1.53\mathrm{E}-11$	$6.59\mathrm{E}-16$
$0.2$	$6.21\mathrm{E}-5$	$4.46\mathrm{E}-7$	$4.36\mathrm{E}-8$	$1.89\mathrm{E}-10$	$1.22\mathrm{E}-10$	$1.76\mathrm{E}-10$	$1.07\mathrm{E}-14$
$0.3$	$1.20\mathrm{E}-4$	$9.98\mathrm{E}-7$	----	----	----	$7.45\mathrm{E}-10$	$5.78\mathrm{E}-14$
$0.4$	$1.99\mathrm{E}-4$	$1.77\mathrm{E}-6$	$3.43\mathrm{E}-7$	$3.58\mathrm{E}-8$	$3.99\mathrm{E}-10$	$2.31\mathrm{E}-9$	$2.00\mathrm{E}-13$
$0.5$	$2.95\mathrm{E}-4$	$2.74\mathrm{E}-6$	----	----	----	$5.97\mathrm{E}-9$	$5.47\mathrm{E}-13$
$0.6$	$4.12\mathrm{E}-4$	$3.92\mathrm{E}-6$	$7.70\mathrm{E}-6$	$1.02\mathrm{E}-7$	$1.38\mathrm{E}-9$	$1.37\mathrm{E}-8$	$1.30\mathrm{E}-12$
$0.7$	$5.47\mathrm{E}-4$	$5.27\mathrm{E}-6$	----	----	----	$2.91\mathrm{E}-8$	$2.82\mathrm{E}-12$
$0.8$	$6.96\mathrm{E}-4$	$6.77\mathrm{E}-6$	$6.20\mathrm{E}-6$	$2.59\mathrm{E}-7$	$4.55\mathrm{E}-9$	$5.85\mathrm{E}-8$	$5.75\mathrm{E}-12$
$0.9$	$8.53\mathrm{E}-4$	$8.36\mathrm{E}-6$	----	----	----	$1.13\mathrm{E}-7$	$1.12\mathrm{E}-11$
$1.0$	$1.01\mathrm{E}-3$	$9.96\mathrm{E}-6$	$4.19\mathrm{E}-5$	$7.22\mathrm{E}-6$	$1.68\mathrm{E}-7$	$2.12\mathrm{E}-7$	$2.12\mathrm{E}-11$

| Show Table

DownLoad: CSV

Table 5. The outcomes of

${L}_{\infty }^{i}\left(k\right)$ errors, the

${OC}^{i}$ , and CPU times, in Problem 2 using various

$k$ .

$k$	${L}_{\infty }^{1}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{1}$	${L}_{\infty }^{2}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{2}$	CPU (s)
$8$	$4.493\times {10}^{-5}$	$-$	$5.149\times {10}^{-7}$	$-$	$0.0156$
$16$	$2.825\times {10}^{-6}$	$3.991$	$3.234\times {10}^{-8}$	$3.993$	$0.0312$
$32$	$1.771\times {10}^{-7}$	$3.996$	$2.022\times {10}^{-9}$	$3.999$	$0.0312$
$64$	$1.108\times {10}^{-8}$	$3.999$	$1.263\times {10}^{-10}$	$3.999$	$0.0625$
$128$	$6.927\times {10}^{-10}$	$3.999$	$7.899\times {10}^{-12}$	$3.999$	$0.1406$

| Show Table

DownLoad: CSV

Problem 3. Consider the following system

$\begin{array}{c} {\omega }_{1}^{\text{'}\text{'}}\left(\tau \right)+\frac{5}{\tau }{\omega }_{1}^{\text{'}}\left(\tau \right)+8\left({e}^{{\omega }_{1}\left(\tau \right)}+2{e}^{-\frac{{\omega }_{2}\left(\tau \right)}{2}}\right) = 0, \\{\omega }_{2}^{\text{'}\text{'}}\left(\tau \right)+\frac{3}{\tau }{\omega }_{2}^{\text{'}}\left(\tau \right)-8({e}^{\frac{{\omega }_{1}\left(\tau \right)}{2}}+{e}^{-{\omega }_{2}\left(\tau \right)}) = 0, \end{array}$

(30)

subject to

${\omega }_{1}\left(0\right) = 1-2\mathrm{ln}\left(2\right), {{\omega }^{\text{'}}}_{1}\left(0\right) = 0, \\ {\omega }_{2}\left(0\right) = 1+2\mathrm{ln}\left(2\right), {{\omega }^{\text{'}}}_{2}\left(0\right) = 0,$

(31)

where the exact solution is

${\omega }_{1}\left(\tau \right) = 1-2\mathrm{ln}\left({\tau }^{2}+2\right), {\omega }_{2}\left(\tau \right) = 1+2\mathrm{ln}({\tau }^{2}+2).$

We apply the proposed QBSM to obtain the approximate solutions to this problem for $\mathrm{\Lambda } = 0.1, 0.01$ . Absolute errors of QBSM for $\mathrm{\Lambda } = 0.1, 0.01$ are listed in and , respectively, along with those obtained by the CBSM ^[8]. From these tables, it can be observed that QBSM provides lesser error than CBSM. The logarithmic plots of absolute errors for various values of $k$ are depicted in . The outcomes of ${L}_{\infty }^{i}\left(k\right)$ errors are listed using $k = 16, 32, 64,$ and $128$ . In addition, the ${OC}^{i}, i = \mathrm{1, 2},$ are computed and the results are tabulated in and . The table show that the achieved ${OC}^{i}, i = \mathrm{1, 2},$ is four. The method's CPU time is reported in the same table, which confirms that the QBSM is computationally effective.

Table 6. Absolute errors for approximate solution of

${\omega }_{1}\left(\tau \right)$ in Problem 3.

$\boldsymbol{\tau }$	CBSM ^[8]		QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda=0.1 }$	$\mathbf{\Lambda=0.01}$	$\mathbf{\Lambda=0.1 }$	$\mathbf{\Lambda=0.01}$
$0.0$	$2.22E-16$	$2.22E-16$	$2.22E-16$	$2.22E-16$
$0.1$	$1.29\mathrm{E}-5$	$4.14\mathrm{E}-8$	$2.47\mathrm{E}-8$	$6.75\mathrm{E}-13$
$0.2$	$2.12\mathrm{E}-5$	$1.53\mathrm{E}-7$	$2.99\mathrm{E}-8$	$2.34\mathrm{E}-12$
$0.3$	$3.50\mathrm{E}-5$	$3.08\mathrm{E}-7$	$4.56\mathrm{E}-8$	$4.19\mathrm{E}-12$
$0.4$	$5.03\mathrm{E}-5$	$4.67\mathrm{E}-7$	$5.18\mathrm{E}-8$	$5.24\mathrm{E}-12$
$0.5$	$6.18\mathrm{E}-5$	$5.92\mathrm{E}-7$	$4.21\mathrm{E}-8$	$4.80\mathrm{E}-12$
$0.6$	$6.68\mathrm{E}-5$	$6.51\mathrm{E}-7$	$1.58\mathrm{E}-8$	$2.59\mathrm{E}-12$
$0.7$	$6.36\mathrm{E}-5$	$6.26\mathrm{E}-7$	$2.47\mathrm{E}-8$	$1.13\mathrm{E}-12$
$0.8$	$5.16\mathrm{E}-5$	$5.13\mathrm{E}-7$	$7.33\mathrm{E}-8$	$5.82\mathrm{E}-12$
$0.9$	$3.16\mathrm{E}-5$	$3.18\mathrm{E}-7$	$1.24\mathrm{E}-7$	$1.08\mathrm{E}-11$
$1.0$	$5.10\mathrm{E}-6$	$5.70\mathrm{E}-8$	$1.68\mathrm{E}-7$	$1.54\mathrm{E}-11$

| Show Table

DownLoad: CSV

Figure 2. Logarithmic plots of absolute errors for Problem 3.

DownLoad: Full-Size Img PowerPoint

Table 7. Absolute errors for approximate solution of

${\omega }_{2}\left(\tau \right)$ in Problem 3.

$\boldsymbol{\tau }$	CBSM ^[8]		QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda=0.1 }$	$\mathbf{\Lambda=0.01}$	$\mathbf{\Lambda=0.1 }$	$\mathbf{\Lambda=0.01}$
$0.0$	$2.22\mathrm{E}-16$	$2.22\mathrm{E}-16$	$2.22\mathrm{E}-16$	$2.22\mathrm{E}-16$
$0.1$	$1.48\mathrm{E}-5$	$6.21\mathrm{E}-8$	$2.79\mathrm{E}-8$	$1.02\mathrm{E}-12$
$0.2$	$3.18\mathrm{E}-5$	$2.33\mathrm{E}-7$	$4.86\mathrm{E}-8$	$3.60\mathrm{E}-12$
$0.3$	$5.42\mathrm{E}-5$	$4.75\mathrm{E}-7$	$7.42\mathrm{E}-8$	$6.64\mathrm{E}-12$
$0.4$	$7.94\mathrm{E}-5$	$7.39\mathrm{E}-7$	$9.19\mathrm{E}-8$	$8.83\mathrm{E}-12$
$0.5$	$1.02\mathrm{E}-4$	$9.71\mathrm{E}-7$	$8.89\mathrm{E}-8$	$9.10\mathrm{E}-12$
$0.6$	$1.16\mathrm{E}-4$	$1.12\mathrm{E}-6$	$6.21\mathrm{E}-8$	$6.95\mathrm{E}-12$
$0.7$	$1.20\mathrm{E}-4$	$1.17\mathrm{E}-6$	$1.28\mathrm{E}-8$	$2.51\mathrm{E}-12$
$0.8$	$1.12\mathrm{E}-4$	$1.10\mathrm{E}-6$	$5.23\mathrm{E}-8$	$3.64\mathrm{E}-12$
$0.9$	$9.26\mathrm{E}-5$	$9.13\mathrm{E}-7$	$1.26\mathrm{E}-7$	$1.07\mathrm{E}-11$
$1.0$	$6.27\mathrm{E}-5$	$6.21\mathrm{E}-7$	$1.97\mathrm{E}-7$	$1.79\mathrm{E}-11$

| Show Table

DownLoad: CSV

Table 8. The outcomes of

${L}_{\infty }^{i}$ errors, the

${OC}^{i}$ , and CPU times, in Problem 3 using various

$k$ .

$k$	${L}_{\infty }^{1}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{1}$	${L}_{\infty }^{2}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{2}$	CPU (s)
$8$	$4.299\times {10}^{-7}$	$-$	$5.072\times {10}^{-7}$	$-$	$0.0156$
$16$	$2.439\times {10}^{-8}$	$4.139$	$2.842\times {10}^{-8}$	$4.157$	$0.0312$
$32$	$1.484\times {10}^{-9}$	$4.038$	$1.724\times {10}^{-9}$	$4.042$	$0.0312$
$64$	$9.215\times {10}^{-11}$	$4.009$	$1.069\times {10}^{-10}$	$4.011$	$0.0625$
$128$	$5.746\times {10}^{-12}$	$4.003$	$6.643\times {10}^{-12}$	$4.009$	$0.1406$

| Show Table

DownLoad: CSV

Problem 4. Consider the following system of LEE

${\omega }_{1}^{\text{'}\text{'}}\left(\tau \right)+\frac{1}{\tau }{\omega }_{1}^{\text{'}}\left(\tau \right)-{\omega }_{2}^{3}\left(\tau \right)\left({\omega }_{1}^{2}+1\right) = 0, \\ {\omega }_{2}^{\text{'}\text{'}}\left(\tau \right)+\frac{3}{\tau }{\omega }_{2}^{\text{'}}\left(\tau \right)+{\omega }_{2}^{5}\left(\tau \right)({\omega }_{1}^{2}+3) = 0,$

(32)

subject to

${\omega }_{1}\left(0\right) = 1, {{\omega }^{\text{'}}}_{1}\left(0\right) = 0,$

${\omega }_{2}\left(0\right) = 1, {{\omega }^{\text{'}}}_{2}\left(0\right) = 0,$

(33)

where the exact solution is given by ${\omega }_{1}\left(\tau \right) = \sqrt{{1+\tau }^{2}}, {\omega }_{2}\left(\tau \right) = \frac{1}{\sqrt{{1+\tau }^{2}}}.$ We solve this system using the proposed QBSM for $\mathrm{\Lambda } = 0.1, 0.01$ . Absolute errors obtained by QBSM for $\mathrm{\Lambda } = 0.1, 0.01$ are given in Tables 9 and 10, along with the errors obtained by the CBSM ^[8] and COMM ^[4]. From these tables, it seems that the errors of QBSM are less than the errors of CBSM and COMM. The logarithmic graphs of absolute errors for different values of n are presented in . The outcomes of ${L}_{\infty }^{i}\left(k\right)$ errors are listed using $k = 16, 32, 64,$ and $128$ . In addition, the ${OC}^{i}, i = \mathrm{1, 2},$ are computed and the results are tabulated in . The table show that the achieved ${OC}^{i}, i = \mathrm{1, 2},$ is four. The method's CPU time is reported in the same table, which confirms that the QBSM is computationally effective.

Table 9. Absolute errors for approximate solution of

${\omega }_{1}\left(\tau \right)$ in Problem 4.

$\boldsymbol{\tau }$	CBSM ^[8]		COMM ^[4]			QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda =0.1 =0.01}$	$\mathbf{\Lambda =0.1 =0.01}$	$\mathbf{n=4}$	$\mathbf{n=5}$	$\mathbf{n=6}$	$\mathbf{\Lambda =0.1 }$	$\mathbf{\Lambda =0.01}$
$0.0$	$0$	0	$0$	$0$	0	$0$	0
$0.1$	$3.39\mathrm{E}-5$	$1.72\mathrm{E}-7$	----	----	----	$2.61\mathrm{E}-8$	$1.51\mathrm{E}-12$
$0.2$	$9.52\mathrm{E}-5$	$7.17\mathrm{E}-7$	$5.09\mathrm{E}-4$	$5.65\mathrm{E}-5$	$7.56\mathrm{E}-6$	$6.61\mathrm{E}-8$	$5.11\mathrm{E}-12$
$0.3$	$2.02\mathrm{E}-4$	$1.76\mathrm{E}-6$	----	----	----	$1.02\mathrm{E}-7$	$8.86\mathrm{E}-12$
$0.4$	$3.81\mathrm{E}-4$	$3.51\mathrm{E}-6$	$6.28\mathrm{E}-4$	$2.16\mathrm{E}-5$	$8.65\mathrm{E}-6$	$1.20\mathrm{E}-7$	$1.09\mathrm{E}-11$
$0.5$	$6.72\mathrm{E}-4$	$6.35\mathrm{E}-6$	----	----	----	$1.13\mathrm{E}-7$	$1.06\mathrm{E}-11$
$0.6$	$1.14\mathrm{E}-3$	$1.09\mathrm{E}-5$	$2.77\mathrm{E}-4$	$5.57\mathrm{E}-6$	$4.56\mathrm{E}-6$	$8.93\mathrm{E}-8$	$8.35\mathrm{E}-12$
$0.7$	$1.87\mathrm{E}-3$	$1.81\mathrm{E}-5$	----	----	----	$6.00\mathrm{E}-8$	$5.27\mathrm{E}-12$
$0.8$	$3.04\mathrm{E}-3$	$2.96\mathrm{E}-5$	$2.72\mathrm{E}-4$	$7.38\mathrm{E}-5$	$7.71\mathrm{E}-6$	$3.81\mathrm{E}-8$	$2.61\mathrm{E}-12$
$0.9$	$4.90\mathrm{E}-3$	$4.78\mathrm{E}-5$	----	----	----	$3.24\mathrm{E}-8$	$1.32\mathrm{E}-12$
$1.0$	$7.89\mathrm{E}-3$	$7.71\mathrm{E}-5$	$6.44\mathrm{E}-4$	$7.46\mathrm{E}-5$	$6.56\mathrm{E}-6$	$4.80\mathrm{E}-8$	$1.96\mathrm{E}-12$

| Show Table

DownLoad: CSV

Table 10. Absolute errors for approximate solution of

${\omega }_{2}\left(\tau \right)$ in Problem 4.

$\boldsymbol{\tau }$	CBSM ^[8]		COMM ^[4]			QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda=0.1 }$	$\mathbf{\Lambda=0.01}$	$\mathbf{n=4}$	$\mathbf{n=5}$	$\mathbf{n=6}$	$\mathbf{\Lambda =0.1 }$	$\mathbf{\Lambda =0.01}$
$0.0$	$6.00\mathrm{E}-31$	0	$0$	$0$	0	0	$2.22\mathrm{E}-16$
$0.1$	$4.67\mathrm{E}-5$	$1.13\mathrm{E}-7$	----	----	----	$1.06\mathrm{E}-7$	$3.61\mathrm{E}-12$
$0.2$	$6.21\mathrm{E}-5$	$4.46\mathrm{E}-7$	$1.03\mathrm{E}-4$	$1.65\mathrm{E}-5$	$6.59\mathrm{E}-6$	$1.42\mathrm{E}-7$	$1.08\mathrm{E}-11$
$0.3$	$1.20\mathrm{E}-4$	$9.98\mathrm{E}-7$	----	----	----	$1.39\mathrm{E}-7$	$1.42\mathrm{E}-11$
$0.4$	$1.99\mathrm{E}-4$	$1.77\mathrm{E}-6$	$2.27\mathrm{E}-4$	$1.51\mathrm{E}-5$	$7.65\mathrm{E}-6$	$5.25\mathrm{E}-8$	$8.72\mathrm{E}-12$
$0.5$	$2.95\mathrm{E}-4$	$2.74\mathrm{E}-6$	----	----	----	$1.13\mathrm{E}-7$	$5.17\mathrm{E}-12$
$0.6$	$4.12\mathrm{E}-4$	$3.92\mathrm{E}-6$	$1.00\mathrm{E}-4$	$1.66\mathrm{E}-5$	$9.63\mathrm{E}-6$	$3.03\mathrm{E}-7$	$2.31\mathrm{E}-11$
$0.7$	$5.47\mathrm{E}-4$	$5.27\mathrm{E}-6$	----	----	----	$4.70\mathrm{E}-7$	$4.00\mathrm{E}-11$
$0.8$	$6.96\mathrm{E}-4$	$6.77\mathrm{E}-6$	$6.92\mathrm{E}-4$	$1.67\mathrm{E}-5$	$8.65\mathrm{E}-6$	$5.81\mathrm{E}-7$	$5.22\mathrm{E}-11$
$0.9$	$8.53\mathrm{E}-4$	$8.36\mathrm{E}-6$	----	----	----	$6.27\mathrm{E}-7$	$5.85\mathrm{E}-11$
$1.0$	$1.01\mathrm{E}-3$	$9.96\mathrm{E}-6$	$2.62\mathrm{E}-4$	$6.08\mathrm{E}-5$	$6.53\mathrm{E}-7$	$6.16\mathrm{E}-7$	$5.91\mathrm{E}-11$

| Show Table

DownLoad: CSV

Figure 3. Logarithmic plots of absolute errors for Problem 4.

DownLoad: Full-Size Img PowerPoint

Table 11. The outcomes of

${L}_{\infty }^{i}$ errors, the

${OC}^{i}$ , and CPU times, in Problem 4 using various

$k$ .

$k$	${L}_{\infty }^{1}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{1}$	${L}_{\infty }^{2}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{2}$	CPU (s)
$8$	$2.961\times {10}^{-7}$	$-$	$1.583\times {10}^{-6}$	$-$	$0.0156$
$16$	$1.766\times {10}^{-8}$	$4.067$	$9.263\times {10}^{-8}$	$4.095$	$0.0312$
$32$	$1.073\times {10}^{-9}$	$4.040$	$5.697\times {10}^{-9}$	$4.023$	$0.0312$
$64$	$6.638\times {10}^{-11}$	$4.015$	$3.547\times {10}^{-10}$	$4.005$	$0.0468$
$128$	$4.132\times {10}^{-12}$	$4.005$	$2.216\times {10}^{-11}$	$4.000$	$0.1250$

| Show Table

DownLoad: CSV

Problem 5. Consider the following system of LEE

${\omega }_{1}^{\text{'}\text{'}}\left(\tau \right)+\frac{8}{\tau }{\omega }_{1}^{\text{'}}\left(\tau \right)+\left(18{\omega }_{1}\left(\tau \right)-4{\omega }_{1}\left(\tau \right)\mathrm{ln}{\omega }_{2}\left(\tau \right)\right) = 0, \\{\omega }_{2}^{\text{'}\text{'}}\left(\tau \right)+\frac{4}{\tau }{\omega }_{2}^{\text{'}}\left(\tau \right)+(4{\omega }_{2}\left(\tau \right)\mathrm{ln}{\omega }_{1}\left(\tau \right)-10{\omega }_{2}\left(\tau \right)) = 0$

(34)

subject to

${\omega }_{1}\left(0\right) = 1, {{\omega }^{\text{'}}}_{1}\left(0\right) = 0, \\{\omega }_{2}\left(0\right) = 1, {{\omega }^{\text{'}}}_{2}\left(0\right) = 0.$

(35)

The exact solution for this system is

${\omega }_{1}\left(\tau \right) = {e}^{-{\tau }^{2}}, {\omega }_{2}\left(\tau \right) = {e}^{{\tau }^{2}}.$

We solve this system using the proposed QBSM for $\mathrm{\Lambda } = 0.1, 0.01$ . Absolute errors obtained by QBSM for $\mathrm{\Lambda } = 0.1, 0.01$ are tabulated in Tables 12 and 13, along with the errors reported in CBSM ^[8] and Dickson operational matrix (DOM) ^[37]. We note that QBSM yields results more accurate than those obtained in ^[8,37]. The logarithmic graphs of absolute errors for different values of $k$ are displayed in . The outcomes of ${L}_{\infty }^{i}\left(k\right)$ errors are listed using $k = 16, 32, 64,$ and $128$ . In addition, the ${OC}^{i}, i = \mathrm{1, 2},$ are computed and the results are tabulated in . The table show that the achieved ${OC}^{i}, i = \mathrm{1, 2},$ is four. The method's CPU time is reported in the same Table, which confirms that the QBSM is computationally effective.

Table 12. Absolute errors for approximate solution of

${\omega }_{1}\left(\tau \right)$ in Problem 5.

$\boldsymbol{\tau }$	CBSM ^[8]		DOM ^[37]		QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda =0.1 }$	$\mathbf{\Lambda =0.01}$	$\mathbf{n=8 }$	$\mathbf{n=10}$	$\mathbf{\Lambda =0.1 }$	$\mathbf{\Lambda =0.01}$
$0.0$	$0$	0	----	----	$1.11\mathrm{E}-16$	0
$0.1$	$3.39\mathrm{E}-5$	$1.72\mathrm{E}-7$	$5.84E-8$	$1.17\mathrm{E}-9$	$4.43\mathrm{E}-8$	$9.12\mathrm{E}-13$
$0.2$	$9.52\mathrm{E}-5$	$7.17\mathrm{E}-7$	1.04 $\mathrm{E}-7$	$1.67\mathrm{E}-9$	$3.81\mathrm{E}-8$	$3.23\mathrm{E}-12$
$0.3$	$2.02\mathrm{E}-4$	$1.76\mathrm{E}-6$	$2.21\mathrm{E}-7$	$2.17\mathrm{E}-10$	$7.01\mathrm{E}-8$	$5.97\mathrm{E}-12$
$0.4$	$3.81\mathrm{E}-4$	$3.51\mathrm{E}-6$	1.37 $\mathrm{E}-7$	$2.91\mathrm{E}-9$	$7.71\mathrm{E}-8$	$7.78\mathrm{E}-12$
$0.5$	$6.72\mathrm{E}-4$	$6.35\mathrm{E}-6$	$3.18\mathrm{E}-7$	$2.17\mathrm{E}-9$	$6.38\mathrm{E}-8$	$7.30\mathrm{E}-12$
$0.6$	$1.14\mathrm{E}-3$	$1.09\mathrm{E}-5$	$2.59\mathrm{E}-7$	$1.59\mathrm{E}-9$	$1.82\mathrm{E}-8$	$3.54\mathrm{E}-12$
$0.7$	$1.87\mathrm{E}-3$	$1.81\mathrm{E}-5$	$3.00\mathrm{E}-7$	$3.33\mathrm{E}-9$	$6.32\mathrm{E}-8$	$3.91\mathrm{E}-12$
$0.8$	$3.04\mathrm{E}-3$	$2.96\mathrm{E}-5$	$2.41\mathrm{E}-7$	$1.16\mathrm{E}-9$	$1.75\mathrm{E}-7$	$1.47\mathrm{E}-11$
$0.9$	$4.90\mathrm{E}-3$	$4.78\mathrm{E}-5$	$2.77\mathrm{E}-7$	$3.21\mathrm{E}-11$	$3.10\mathrm{E}-7$	$2.79\mathrm{E}-11$
$1.0$	$7.89\mathrm{E}-3$	$7.71\mathrm{E}-5$	$5.95\mathrm{E}-7$	$2.19\mathrm{E}-10$	$4.47\mathrm{E}-7$	$4.22\mathrm{E}-11$

| Show Table

DownLoad: CSV

Table 13. Absolute errors for approximate solution of

${\omega }_{2}\left(\tau \right)$ in Problem 5.

$\boldsymbol{\tau }$	CBSM ^[8]		DOM ^[37]		QBSM
$\boldsymbol{\tau }$	$\mathbf{\Lambda=0.1 }$	$\mathbf{\Lambda=0.01}$	$\mathbf{n=8 }$	$\mathbf{n=10}$	$\mathbf{\Lambda =0.1 }$	$\mathbf{\Lambda =0.01}$
$0.0$	$6.00\mathrm{E}-31$	0	----	----	0	0
$0.1$	$4.67\mathrm{E}-5$	$1.13\mathrm{E}-7$	$3.30\mathrm{E}-7$	$1.27\mathrm{E}-8$	$5.14\mathrm{E}-8$	$1.74\mathrm{E}-12$
$0.2$	$6.21\mathrm{E}-5$	$4.46\mathrm{E}-7$	$1.18\mathrm{E}-6$	$1.28\mathrm{E}-8$	$1.01\mathrm{E}-7$	$7.50\mathrm{E}-12$
$0.3$	$1.20\mathrm{E}-4$	$9.98\mathrm{E}-7$	$1.14\mathrm{E}-6$	$6.24\mathrm{E}-9$	$2.24\mathrm{E}-7$	$1.93\mathrm{E}-11$
$0.4$	$1.99\mathrm{E}-4$	$1.77\mathrm{E}-6$	1.69 $\mathrm{E}-6$	$3.15\mathrm{E}-8$	$4.50\mathrm{E}-7$	$4.11\mathrm{E}-11$
$0.5$	$2.95\mathrm{E}-4$	$2.74\mathrm{E}-6$	$1.44\mathrm{E}-6$	$1.35\mathrm{E}-8$	$8.44\mathrm{E}-7$	$7.97\mathrm{E}-11$
$0.6$	$4.12\mathrm{E}-4$	$3.92\mathrm{E}-6$	$2.46\mathrm{E}-6$	$2.31\mathrm{E}-8$	$1.53\mathrm{E}-6$	$1.47\mathrm{E}-10$
$0.7$	$5.47\mathrm{E}-4$	$5.27\mathrm{E}-6$	$1.17\mathrm{E}-6$	$3.51\mathrm{E}-8$	$2.69\mathrm{E}-6$	$2.63\mathrm{E}-10$
$0.8$	$6.96\mathrm{E}-4$	$6.77\mathrm{E}-6$	$1.87\mathrm{E}-6$	$9.14\mathrm{E}-9$	$4.68\mathrm{E}-6$	$4.61\mathrm{E}-10$
$0.9$	$8.53\mathrm{E}-4$	$8.36\mathrm{E}-6$	$2.20\mathrm{E}-6$	$7.33\mathrm{E}-10$	$7.99\mathrm{E}-6$	$7.99\mathrm{E}-10$
$1.0$	$1.01\mathrm{E}-3$	$9.96\mathrm{E}-6$	$3.36\mathrm{E}-7$	$2.57\mathrm{E}-9$	$1.39\mathrm{E}-5$	$1.38\mathrm{E}-9$

| Show Table

DownLoad: CSV

Figure 4. Logarithmic plots of absolute errors for Problem 5.

DownLoad: Full-Size Img PowerPoint

Table 14. The outcomes of

${L}_{\infty }^{i}$ errors, the

${OC}^{i}$ , and CPU times, in Problem 5 using various

$k$ .

$k$	${L}_{\infty }^{1}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{1}$	${L}_{\infty }^{2}\left(k\right)$	${\mathrm{O}\mathrm{C}}^{2}$	CPU (s)
$8$	$1.120\times {10}^{-6}$	$-$	$3.416\times {10}^{-5}$	$-$	$0.0156$
$16$	$6.588\times {10}^{-8}$	$4.088$	$2.106\times {10}^{-6}$	$4.019$	$0.0312$
$32$	$4.044\times {10}^{-9}$	$4.025$	$1.314\times {10}^{-7}$	$4.002$	$0.0312$
$64$	$2.515\times {10}^{-10}$	$4.006$	$8.213\times {10}^{-9}$	$4.000$	$0.0468$
$128$	$1.570\times {10}^{-11}$	$4.001$	$5.133\times {10}^{-10}$	$4.000$	$0.1250$

| Show Table

DownLoad: CSV

As can be observed from the above tables, the proposed QBSM is fourth-order accurate and the practical convergence order aligns consistently with the theoretical convergence order obtained in the previous section.

5. Conclusions

In this study, we have established a numerical method for solving systems of Lane-Emden equations. The QBSM has been constructed using quintic B-spline functions on the uniform mesh. We investigate the convergence analysis of the QBSM and found it exhibited fourth-order convergence. To strengthen the significance of the QBSM method and validate theoretical results, we examined five test problems. We have presented tabular and graphical exhibitions to confirm the effectiveness of QBSM. Notably, the numerical solutions of QBSM are in good agreement with the exact ones, and their accuracy improves as the step sizes decrease. Moreover, we compared the QBSM with other numerical methods such as CBSM, DOM, and COMM, and the comparison exposed that the QBSM produces more accurate numerical results than the other methods. In conclusion, the method is computationally efficient, accurate, robust, easy to address the singularity, and, therefore, it can be employed to solve different classes of nonlinear singular differential equations.

Use of AI tools declaration

The authors declare that they have not used Artificial Intelligence (AI) tools in the creation of this article.

Conflict of interest

The authors declare no conflicts of interest.

References

[1]	V. Sharma, M. G. Dastidar, S. Sutradhar, V. Raj, K. De Silva, S. Roy, A step toward better sample management of COVID-19: On-spot detection by biometric technology and artificial intelligence, COVID-19 Sustain, Develop. Goals, 2022 (2022), 349–380. https://doi.org/10.1016/B978-0-323-91307-2.00017-1 doi: 10.1016/B978-0-323-91307-2.00017-1
[2]	G. Latif, H. Morsy, A. Hassan, J. Alghazo, Novel coronavirus and common pneumonia detection from CT scans using deep learning-based extracted features, Viruses, 14 (2022), 1667. https://doi.org/10.3390/v14081667 doi: 10.3390/v14081667
[3]	A. Islam, T. Rahim, M. Masuduzzaman, S. Y. Shin, A blockchain-based artificial intelligence-empowered contagious pandemic situation supervision scheme using internet of drone things, IEEE Wirel. Commun., 28 (2021), 166–173. https://doi.org/10.1109/MWC.001.2000429 doi: 10.1109/MWC.001.2000429
[4]	T. Rahim, M. A. Usman, S. Y. Shin, A survey on contemporary computer-aided tumor, polyp, and ulcer detection methods in wireless capsule endoscopy imaging, Comput. Med. Imag. Grap., 85 (2020), 101767. https://doi.org/10.1016/j.compmedimag.2020.101767 doi: 10.1016/j.compmedimag.2020.101767
[5]	G. Latif, DeepTumor: Framework for brain MR image classification, segmentation and tumor detection, Diagnostics, 12 (2022), 2888. https://doi.org/10.3390/diagnostics12112888 doi: 10.3390/diagnostics12112888
[6]	T. Rahim, S. A. Hassan, S. Y. Shin, A deep convolutional neural network for the detection of polyps in colonoscopy images, Biomed. Signal Proces., 68 (2021), 102654. https://doi.org/10.1016/j.bspc.2021.102654 doi: 10.1016/j.bspc.2021.102654
[7]	A. Bashar, G. Latif, G. Ben Brahim, N. Mohammad, J. Alghazo, COVID-19 pneumonia detection using optimized deep learning techniques, Diagnostics, 11 (2021), 1972. https://doi.org/10.3390/diagnostics11111972 doi: 10.3390/diagnostics11111972
[8]	E. Hussain, M. Hasan, M. A. Rahman, I. Lee, T. Tamanna, M. Z. Parvez, CoroDet: A deep learning based classification for COVID-19 detection using chest X-ray images, Chaos Soliton. Fract., 142 (2021), 110495. https://doi.org/10.1016/j.chaos.2020.110495 doi: 10.1016/j.chaos.2020.110495
[9]	G. Latif, G. Ben Brahim, D. N. F. A. Iskandar, A. Bashar, J. Alghazo, Glioma tumors' classification using deep-neural-network-based features with SVM classifier, Diagnostics, 12 (2022), 1018. https://doi.org/10.3390/diagnostics12041018 doi: 10.3390/diagnostics12041018
[10]	I. Iqbal, M. Younus, K. Walayat, M. U. Kakar, J. Ma, Automated multi-class classification of skin lesions through deep convolutional neural network with dermoscopic images, Comput. Med. Imag. grap, 88 (2021), 101843. https://doi.org/10.1016/j.compmedimag.2020.101843 doi: 10.1016/j.compmedimag.2020.101843
[11]	I. Iqbal, K. Walayat, M. U. Kakar, J. Ma, Automated identification of human gastrointestinal tract abnormalities based on deep convolutional neural network with endoscopic images, Intell. Syst. Appl., 16 (2022), 200149. https://doi.org/10.1016/j.iswa.2022.200149 doi: 10.1016/j.iswa.2022.200149
[12]	V. Shah, R. Keniya, A. Shridharani, M. Punjabi, J. Shah, N. Mehendale, Diagnosis of COVID-19 using CT scan images and deep learning techniques, Emerg. Radiol., 28 (2021), 497–505. https://doi.org/10.1007/s10140-020-01886-y doi: 10.1007/s10140-020-01886-y
[13]	M. M. Rahaman, C. Li, Y. Yao, K. Frank, M. A. Rahman, Q. Wang, et al., Identification of COVID-19 samples from chest X-Ray images using deep learning: A comparison of transfer learning approaches, J. X-Ray Sci. Technol., 28 (2020), 821–839. https://doi.org/10.3233/XST-200715 doi: 10.3233/XST-200715
[14]	A. S. Al-Waisy, S. Al-Fahdawi, M. A. Mohammed, K. H. Abdulkareem, S. A. Mostafa, M. S. Maashi, et al., COVID-CheXNet: Hybrid deep learning framework for identifying COVID-19 virus in chest X-rays images, Soft Comput., 27 (2020), 2657–2672. https://doi.org/10.1007/s00500-020-05424-3 doi: 10.1007/s00500-020-05424-3
[15]	Y. Chang, X. Jing, Z. Ren, B. Schuller, CovNet: A transfer learning framework for automatic COVID-19 detection from crowd-sourced cough sounds, Front. Digit. Health, 3 (2022), 799067. https://doi.org/10.3389/fdgth.2021.799067 doi: 10.3389/fdgth.2021.799067
[16]	M. Elpeltagy, H. Sallam, Automatic prediction of COVID-19 from chest images using modified ResNet50, Multimed. Tools Appl., 80 (2021), 26451–26463. https://doi.org/10.1007/s11042-021-10783-6 doi: 10.1007/s11042-021-10783-6
[17]	R. K. Patel, M. Kashyap, Automated diagnosis of COVID stages from lung CT images using statistical features in 2-dimensional flexible analytic wavelet transform, Biocybern. Biomed. Eng., 42 (2022), 829–841. https://doi.org/10.1016/j.bbe.2022.06.005 doi: 10.1016/j.bbe.2022.06.005
[18]	D. K. Redie, A. E. Sirko, T. M. Demissie, S. S. Teferi, V. K. Shrivastava, O. P. Verma, et al., Diagnosis of COVID-19 using chest X-ray images based on modified DarkCovidNet model, Evol Intell., 16 (2022), 729–738. https://doi.org/10.1007/s12065-021-00679-7 doi: 10.1007/s12065-021-00679-7
[19]	F. Özyurt, Efficient deep feature selection for remote sensing image recognition with fused deep learning architectures, J. Supercomput, 76 (2020), 8413–8431. https://doi.org/10.1007/s11227-019-03106-y doi: 10.1007/s11227-019-03106-y
[20]	D. H. Hubel, T. N. Wiesel, Receptive fields, binocular interaction and functional architecture in the cat's visual cortex, J. Physiol., 160 (1962), 106–154. https://doi.org/10.1113/jphysiol.1962.sp006837 doi: 10.1113/jphysiol.1962.sp006837
[21]	Y. LeCun, Y. Bengio, Convolutional networks for images, speech, and time series, In: The handbook of brain theory and neural networks, 1995.
[22]	G. Latif, J. Alghazo, L. Alzubaidi, M. N. Nasser, Y. Alghazo, Deep convolutional neural network for recognition of unified multi-language handwritten numerals, In: 2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), 2018. https://doi.org/10.1109/ASAR.2018.8480289
[23]	A. Krizhevsky, I. Sutskever, G. E. Hinton, ImageNet classification with deep convolutional neural networks. Commun. ACM, 60 (2017), 84–90. https://doi.org/10.1145/3065386 doi: 10.1145/3065386
[24]	C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, et al., Going deeper with convolutions, 2014, arXiv: 1409.4842.
[25]	S. Alghamdi, M. Alabkari, F. Aljishi, G. Latif, A. Bashar, Lung cancer detection from LDCT images using deep convolutional neural networks, In: International Conference on Communication, Computing and Electronics Systems, Singapore: Springer, 733 (2021), 363–374. https://doi.org/10.1007/978-981-33-4909-4_27
[26]	D. A. Alghmgham, G. Latif, J. Alghazo, L. Alzubaidi, Autonomous traffic sign (ATSR) detection and recognition using deep CNN, Procedia Comput. Sci., 163 (2019), 266–274. https://doi.org/10.1016/j.procs.2019.12.108 doi: 10.1016/j.procs.2019.12.108
[27]	G. Latif, N. Mohammad, R. AlKhalaf, R. AlKhalaf, J. Alghazo, M. Khan, An automatic arabic sign language recognition system based on deep CNN: An assistive system for the deaf and hard of hearing, Int. J. Comput. Digital Syst., 9 (2020), 715–724. http://doi.org/10.12785/ijcds/090418 doi: 10.12785/ijcds/090418
[28]	B. Zhou, A. Lapedriza, J. Xiao, A. Torralba, A. Oliva, Learning deep features for scene recognition using places database, In: NIPS'14: Proceedings of the 27th International Conference on Neural Information Processing Systems, 1 (2014), 487–495.
[29]	M. M. Butt, G. Latif, D. N. F. A. Iskandar, J. Alghazo, A. H. Khan, Multi-channel convolutions neural network based diabetic retinopathy detection from fundus images, Procedia Comput. Sci., 163 (2019), 283–291. https://doi.org/10.1016/j.procs.2019.12.110 doi: 10.1016/j.procs.2019.12.110
[30]	D. C. Cireşan, U. Meier, J. Masci, L. Gambardella, J. Schmidhuber, Flexible, high performance convolutional neural networks for image classification, In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, 2011, 1237–1242. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-210
[31]	G. Lokku, G. H. Reddy, M. N. G. Prasad, OPFaceNet: Optimized face recognition network for noise and occlusion affected face images using hyperparameters tuned convolutional neural network, Appl. Soft Comput., 117 (2022), 108365. https://doi.org/10.1016/j.asoc.2021.108365 doi: 10.1016/j.asoc.2021.108365
[32]	S. Y. Kim, Z. W. Geem, G. Han, Hyperparameter optimization method based on harmony search algorithm to improve performance of 1D CNN human respiration pattern recognition system, Sensors, 20 (2020), 3697. https://doi.org/10.3390/s20133697 doi: 10.3390/s20133697
[33]	G. Latif, K. Bouchard, J. Maitre, A. Back, L. P. Bedard, Deep-learning-based automatic mineral grain segmentation and recognition, Minerals, 12 (2022), 455. https://doi.org/10.3390/min12040455 doi: 10.3390/min12040455
[34]	J. Bruna, S. Mallat, Invariant scattering convolution networks, IEEE T. Pattern Anal., 35 (2013), 1872–1886. https://doi.org/10.1109/TPAMI.2012.230 doi: 10.1109/TPAMI.2012.230
[35]	S. Lawrence, C. L. Giles, A. C. Tsoi, What size neural network gives optimal generalization? Convergence properties of backpropagation, In: Digital Repository at the University of Maryland, 1998.
[36]	L. Wan, M. Zeiler, S. Zhang, Y. Cun, R. Fergus, Regularization of neural networks using dropconnect, In: ICML'13: Proceedings of the 30th International Conference on International Conference on Machine Learning, 28 (2013), 1058–1066.
[37]	Q. Xu, M. Zhang, Z. Gu, G. Pan, Overfitting remedy by sparsifying regularization on fully-connected layers of CNNs, Neurocomputing, 328 (2019), 69–74. https://doi.org/10.1016/j.neucom.2018.03.080 doi: 10.1016/j.neucom.2018.03.080
[38]	S. R. Dubey, S. K. Singh, B. B. Chaudhuri, Activation functions in deep learning: A comprehensive survey and benchmark, Neurocomputing, 503 (2022), 92–108. https://doi.org/10.1016/j.neucom.2022.06.111 doi: 10.1016/j.neucom.2022.06.111
[39]	S. Akbar, M. Peikari, S. Salama, S. Nofech-Mozes, A. Martel, The transition module: A method for preventing overfitting in convolutional neural networks, Comput. Methods Biomech. Biomed. Eng.: Imaging Vis., 7 (2019), 260–265. https://doi.org/10.1080/21681163.2018.1427148 doi: 10.1080/21681163.2018.1427148
[40]	H. Wu, X. Gu, Towards dropout training for convolutional neural networks, Neural Networks, 71 (2015), 1–10. https://doi.org/10.1016/j.neunet.2015.07.007 doi: 10.1016/j.neunet.2015.07.007
[41]	M. Anthimopoulos, S. Christodoulidis, L. Ebner, A. Christe, S. Mougiakakou, Lung pattern classification for interstitial lung diseases using a deep convolutional neural network, IEEE T. Med. Imaging, 35 (2016), 1207–1216. https://doi.org/10.1109/TMI.2016.2535865 doi: 10.1109/TMI.2016.2535865
[42]	J. Chen, Y. Shen, The effect of kernel size of CNNs for lung nodule classification, In: 2017 9th International Conference on Advanced Infocomm Technology (ICAIT), 2017,340–344. https://doi.org/10.1109/ICAIT.2017.8388942
[43]	B. Chen, W. Deng, J. Du, Noisy softmax: Improving the generalization ability of DCNN via postponing the early softmax saturation, In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, 4021–4030. https://doi.org/10.1109/CVPR.2017.428
[44]	Y. Bengio, P. Lamblin, D. Popovici, H. Larochelle, Greedy layer-wise training of deep networks, In: Advances in Neural Information Processing Systems 19 (NIPS 2006), 2006.
[45]	K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016,770–778. https://doi.org/10.1109/CVPR.2016.90
[46]	S. Han, J. Pool, J. Tran, W. J. Dally, Learning both weights and connections for efficient neural network, In: NIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems, 1 (2015), 1135–1143.
[47]	P. Ochs, A. Dosovitskiy, T. Brox, T. Pock, On iteratively reweighted algorithms for nonsmooth nonconvex optimization in computer vision, SIAM J. Imaging Sci., 8 (2015), 331–372. https://doi.org/10.1137/140971518 doi: 10.1137/140971518
[48]	P. Murugan, S. Durairaj, Regularization and optimization strategies in deep convolutional neural network, 2017, arXiv: 1712.04711.
[49]	J. Snoek, O. Rippel, K. Swersky, R. Kiros, N. Satish, N. Sundaram, et al., Scalable Bayesian optimization using deep neural networks, In: ICML'15: Proceedings of the 32nd International Conference on International Conference on Machine Learning, 37 (2015), 2171–2180.
[50]	D. Cheng, Y. Gong, S. Zhou, J. Wang, N. Zheng, Person re-identification by multi-channel parts-based CNN with improved triplet loss function, In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, 1335–1344. https://doi.org/10.1109/CVPR.2016.149
[51]	Y. S. Aurelio, G. M. de Almeida, C. L. de Castro, A. P. Braga, Learning from imbalanced data sets with weighted cross-entropy function, Neural Process Lett., 50 (2019), 1937–1949. https://doi.org/10.1007/s11063-018-09977-1 doi: 10.1007/s11063-018-09977-1
[52]	M. Bouten, J. Schietse, C. Van. den Broeck, Gradient descent learning in perceptrons: A review of its possibilities, Phys. Rev. E, 52 (1995), 1958–1967. https://doi.org/10.1103/PhysRevE.52.1958 doi: 10.1103/PhysRevE.52.1958
[53]	A. El-Sawy, M. Loey, H. El-Bakry, Arabic handwritten characters recognition using convolutional neural network, WSEAS Trans. Comput. Res., 5 (2017), 11–19.
[54]	Y. Sun, W. Zhang, H. Gu, C. Liu, S. Hong, W. Xu, et al., Convolutional neural network based models for improving super-resolution imaging, IEEE Access, 7 (2019), 43042–43051. https://doi.org/10.1109/ACCESS.2019.2908501 doi: 10.1109/ACCESS.2019.2908501
[55]	G. D. Rubin, C. J. Ryerson, L. B. Haramati, N. Sverzellati, J. P. Kanne, S. Raoof, et al., The role of chest imaging in patient management during the COVID-19 pandemic: A multinational consensus statement from the Fleischner society, Radiology, 296 (2020), 172–180. https://doi.org/10.1148/radiol.2020201365 doi: 10.1148/radiol.2020201365
[56]	B. Xu, Y. Xing, J. Peng, Z. Zheng, W. Tang, Y. Sun, et al., Chest CT for detecting COVID-19: A systematic review and meta-analysis of diagnostic accuracy, Eur Radiol, 30 (2020), 5720–5727. https://doi.org/10.1007/s00330-020-06934-2 doi: 10.1007/s00330-020-06934-2
[57]	A. M. Rahmani, E. Azhir, M. Naserbakht, M. Mohammadi, A. H. M. Aldalwie, M. K. Majeed, et al., Automatic COVID-19 detection mechanisms and approaches from medical images: A systematic review, Multimed. Tools Appl., 81 (2022), 28779–28798. https://doi.org/10.1007/s11042-022-12952-7 doi: 10.1007/s11042-022-12952-7
[58]	E. E. Hemdan, M. A. Shouman, M. E. Karar, COVIDX-Net: A framework of deep learning classifiers to diagnose COVID-19 in X-ray images, 2020, arXiv: 2003.11055.
[59]	M. Polsinelli, L. Cinque, G. Placidi, A light CNN for detecting COVID-19 from CT scans of the chest, Pattern Recogn. Lett., 140 (2020), 95–100. https://doi.org/10.1016/j.patrec.2020.10.001 doi: 10.1016/j.patrec.2020.10.001
[60]	A. Narin, C. Kaya, Z. Pamuk, Automatic detection of coronavirus disease (COVID-19) using X-ray images and deep convolutional neural networks, Pattern Anal, Appl., 24 (2021), 1207–1220. https://doi.org/10.1007/s10044-021-00984-y doi: 10.1007/s10044-021-00984-y
[61]	P. Mooney, Chest X-ray images (Pneumonia), 2018. Available from: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia.
[62]	T. Rahman, COVID-19 radiography database, 2020. Available from: https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database.
[63]	I. D. Apostolopoulos, T. A. Mpesiana, Covid-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks, Phys. Eng. Sci. Med., 43 (2020), 635–640. https://doi.org/10.1007/s13246-020-00865-4 doi: 10.1007/s13246-020-00865-4
[64]	P. K. Sethy, S. K. Behera, P. K. Ratha, P. Biswas, Detection of coronavirus disease (COVID-19) based on deep features and support vector machine, Int. J. Math. Eng. Manage. Sci., 5 (2020), 643–651. https://doi.org/10.33889/IJMEMS.2020.5.4.052 doi: 10.33889/IJMEMS.2020.5.4.052
[65]	Y. Wang, M. Hu, Q. Li, X. Zhang, G. Zhai, N. Yao, Abnormal respiratory patterns classifier may contribute to large-scale screening of people infected with COVID-19 in an accurate and unobtrusive manner, 2020, arXiv: 2002.05534.
[66]	J. Zhang, Y. Xie, G. Pang, Z. Liao, J. Verjans, W. Li, et al., Viral pneumonia screening on chest X-rays using confidence-aware anomaly detection, IEEE T. Med. Imaging, 40 (2021), 879–890. https://doi.org/10.1109/TMI.2020.3040950 doi: 10.1109/TMI.2020.3040950
[67]	P. Afshar, S. Heidarian, F. Naderkhani, A. Oikonomou, K. N. Plataniotis, A. Mohammadi, COVID-CAPS: A capsule network-based framework for identification of COVID-19 cases from X-ray images, Pattern Recogn. Lett., 138 (2020), 638–643. https://doi.org/10.1016/j.patrec.2020.09.010 doi: 10.1016/j.patrec.2020.09.010
[68]	M. E. H. Chowdhury, T. Rahman, A. Khandakar, R. Mazhar, M. A. Kadir, Z. B. Mahbub, et al., Can AI help in screening viral and COVID-19 pneumonia? IEEE Access, 8 (2020), 132665–132676. https://doi.org/10.1109/ACCESS.2020.3010287 doi: 10.1109/ACCESS.2020.3010287
[69]	L. O. Hall, R. Paul, D. B. Goldgof, G. M. Goldgof, Finding Covid-19 from chest X-rays using deep learning on a small dataset, 2020, arXiv: 2004.02060.
[70]	T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, O. Yildirim, U. R. Acharya, Automated detection of COVID-19 cases using deep neural networks with X-ray images, Comput. Biol. Med., 121 (2020), 103792. https://doi.org/10.1016/j.compbiomed.2020.103792 doi: 10.1016/j.compbiomed.2020.103792
[71]	R. M. Pereira, D. Bertolini, L. O. Teixeira, C. N. Silla, Y. M. G. Costa, COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios, Comput. Meth. Prog. Bio., 194 (2020), 105532. https://doi.org/10.1016/j.cmpb.2020.105532 doi: 10.1016/j.cmpb.2020.105532
[72]	L. Mahdy, K. Ezzat, H. Elmousalami, H. Ella, A. Hassanien, Automatic X-ray COVID-19 lung image classification system based on multi-level thresholding and support vector machine, 2020, medRxiv preprint. https://doi.org/10.1101/2020.03.30.20047787
[73]	K. El Asnaoui, Y. Chawki, A. Idri, Automated methods for detection and classification pneumonia based on X-ray images using deep learning, In: Artificial intelligence and blockchain for future cybersecurity applications, Springer, Cham, 2021,257–284. https://doi.org/10.1007/978-3-030-74575-2_14
[74]	D. Singh, V. Kumar, V. Kaur, M. Kaur, Classification of COVID-19 patients from chest CT images using multi-objective differential evolution–based convolutional neural networks, Eur. J. Clin. Microbiol. Infect. Dis., 39 (2020), 1379–1389. https://doi.org/10.1007/s10096-020-03901-z doi: 10.1007/s10096-020-03901-z
[75]	M. Yamac, M. Ahishali, A. Degerli, S. Kiranyaz, M. E. H. Chowdhury, M. Gabbouj, Convolutional sparse support estimator-based COVID-19 recognition from X-ray images, IEEE T. Neur. Net. Lear. Syst., 32 (2021), 1810–1820. https://doi.org/10.1109/TNNLS.2021.3070467 doi: 10.1109/TNNLS.2021.3070467
[76]	U. Özkaya, Ş. Öztürk, M. Barstugan, Coronavirus (COVID-19) classification using deep features fusion and ranking technique, In: Big Data Analytics and Artificial Intelligence Against COVID-19: Innovation Vision and Approach, Springer, Cham, 2020,281–295. https://doi.org/10.1007/978-3-030-55258-9_17
[77]	C. Salvatore, M. Interlenghi, C. Monti, D. Ippolito, D. Capra, A. Cozzi, et al., Artificial intelligence applied to chest X-ray for differential diagnosis of COVID-19 pneumonia, Diagnostics, 11 (2021), 530. https://doi.org/10.3390/diagnostics11030530 doi: 10.3390/diagnostics11030530
[78]	T. T. Nguyen, Q. V. H. Nguyen, D. T. Nguyen, S. Yang, P. W. Eklund, T. Huynh-The, et al., Artificial intelligence in the battle against coronavirus (COVID-19): A survey and future research directions, 2020, arXiv: 2008.07343.
[79]	E. Neri, V. Miele, F. Coppola, R. Grassi, Use of CT and artificial intelligence in suspected or COVID-19 positive patients: Statement of the Italian society of medical and interventional radiology, La radiologia medica, 125 (2020), 505–508. https://doi.org/10.1007/s11547-020-01197-9 doi: 10.1007/s11547-020-01197-9
[80]	L. Li, L. Qin, Z. Xu, Y. Yin, X. Wang, B. Kong, et al., Using artificial intelligence to detect COVID-19 and community-acquired pneumonia based on pulmonary CT: Evaluation of the diagnostic accuracy, Radiology, 296 (2020), E65–E71. https://doi.org/10.1148/radiol.2020200905 doi: 10.1148/radiol.2020200905
[81]	M. A. Amou, K. Xia, S. Kamhi, M. Mouhafid, A novel MRI diagnosis method for brain tumor classification based on CNN and Bayesian optimization, Healthcare, 10 (2022), 494. https://doi.org/10.3390/healthcare10030494 doi: 10.3390/healthcare10030494
[82]	S. Z. Kurdi, M. H. Ali, M. M. Jaber, T. Saba, A. Rehman, R. Damaševičius, Brain tumor classification using meta-heuristic optimized convolutional neural networks, J. Pers. Med, 13 (2023), 181. https://doi.org/10.3390/jpm13020181 doi: 10.3390/jpm13020181
[83]	E. Irmak, Multi-classification of brain tumor MRI images using deep convolutional neural network with fully optimized framework, Iran. J. Sci. Technol. Trans. Electr. Eng., 45 (2021), 1015–1036. https://doi.org/10.1007/s40998-021-00426-9 doi: 10.1007/s40998-021-00426-9
[84]	C. Venkatesh, K. Ramana, S. Y. Lakkisetty, S. S. Band, S. Agarwal, A. Mosavi, A neural network and optimization based lung cancer detection system in CT images, Front. Public Health, 10 (2022), 769692. https://doi.org/10.3389/fpubh.2022.769692 doi: 10.3389/fpubh.2022.769692
[85]	D. Paikaray, A. K. Mehta, D. A. Khan, Optimized convolutional neural network for the classification of lung cancer, J. Supercomput., 80 (2024), 1973–1989. https://doi.org/10.1007/s11227-023-05550-3 doi: 10.1007/s11227-023-05550-3
[86]	C. Lin, S. Jeng, M. Chen, Using 2D CNN with Taguchi parametric optimization for lung cancer recognition from CT images, Appl. Sci., 10 (2020), 2591. https://doi.org/10.3390/app10072591 doi: 10.3390/app10072591

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)