Hybrid arithmetic optimization algorithm with deep learning model for secure Unmanned Aerial Vehicle networks

Sultanah M. Alshammari; Nofe A. Alganmi; Mohammed H. Ba-Aoum; Sami Saeed Binyamin; Abdullah AL-Malaise AL-Ghamdi; Mahmoud Ragab; Sultanah M. Alshammari; Nofe A. Alganmi; Mohammed H. Ba-Aoum; Sami Saeed Binyamin; Abdullah AL-Malaise AL-Ghamdi; Mahmoud Ragab

doi:10.3934/math.2024348

AIMS Mathematics

2024, Volume 9, Issue 3: 7131-7151. doi: 10.3934/math.2024348

Previous Article Next Article

Research article Special Issues

Hybrid arithmetic optimization algorithm with deep learning model for secure Unmanned Aerial Vehicle networks

1.
Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia
2.
Center of Excellence in Smart Environment Research, King Abdulaziz University, Jeddah 21589, Saudi Arabia
3.
Industrial and Systems Engineering Department, Virginia Polytechnic Institute and State University, Blacksburg 24061, VA, USA
4.
Systems Engineering Department, King Fahd University of Petroleum and Minerals, Dhahran 31261, Saudi Arabia
5.
Computer and Information Technology Department, The Applied College, King Abdulaziz University, Jeddah 21589, Saudi Arabia
6.
Information Systems Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia
7.
Information Systems Department, School of Engineering, Computing and Design, Dar Al-Hekma University, Jeddah 22246, Saudi Arabia
8.
Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia

Received: 01 December 2023 Revised: 05 January 2024 Accepted: 18 January 2024 Published: 19 February 2024
MSC : 68M11, 68M25, 68T07, 68W1

Securing Unmanned Aerial Vehicle (UAV) systems is vital to safeguard the processes involved in operating the drones. This involves the execution of robust communication encryption processes to defend the data exchanged between the UAVs and ground control stations. Intrusion detection, powered by Deep Learning (DL) techniques such as Convolutional Neural Networks (CNN), allows the classification and identification of potential attacks or illegal objects in the operational region of the drone, thus distinguishing them from the routine basics. The current research work offers a new Hybrid Arithmetic Optimizer Algorithm with DL method for Secure Unmanned Aerial Vehicle Network (HAOADL-UAVN) model. The purpose of the proposed HAOADL-UAVN technique is to secure the communication that occurs in UAV networks via threat detection. At the primary level, the network data is normalized through min-max normalization approach in order to scale the input dataset into a useful format. The HAOA is used to select a set of optimal features. Next, the security is attained via Deep Belief Network Autoencoder (DBN-AE)-based threat detection. At last, the hyperparameter choice of the DBN-AE method is implemented using the Seagull Optimization Algorithm (SOA). A huge array of simulations was conducted using the benchmark datasets to demonstrate the improved performance of the proposed HAOADL-UAVN algorithm. The comprehensive results underline the supremacy of the HAOADL-UAVN methodology under distinct evaluation metrics.

Keywords:

Citation: Sultanah M. Alshammari, Nofe A. Alganmi, Mohammed H. Ba-Aoum, Sami Saeed Binyamin, Abdullah AL-Malaise AL-Ghamdi, Mahmoud Ragab. Hybrid arithmetic optimization algorithm with deep learning model for secure Unmanned Aerial Vehicle networks[J]. AIMS Mathematics, 2024, 9(3): 7131-7151. doi: 10.3934/math.2024348

Related Papers:

[1]	Xiujiao Chi, Pengtong Li . Characterization of frame vectors for $\mathcal{A}$ -group-like unitary systems on Hilbert $C^{\ast}$ -modules. AIMS Mathematics, 2023, 8(9): 22112-22126. doi: 10.3934/math.20231127
[2]	Adel Alahmadi, Tamador Alihia, Patrick Solé . The build up construction for codes over a non-commutative non-unitary ring of order $9$ . AIMS Mathematics, 2024, 9(7): 18278-18307. doi: 10.3934/math.2024892
[3]	Yan Ling Fu, Wei Zhang . Some results on frames by pre-frame operators in Q-Hilbert spaces. AIMS Mathematics, 2023, 8(12): 28878-28896. doi: 10.3934/math.20231480
[4]	Yunpeng Xue . On enhanced general linear groups: nilpotent orbits and support variety for Weyl module. AIMS Mathematics, 2023, 8(7): 14997-15007. doi: 10.3934/math.2023765
[5]	Bhabesh Das, Helen K. Saikia . On the Sum of Unitary Divisors Maximum Function. AIMS Mathematics, 2017, 2(1): 96-101. doi: 10.3934/Math.2017.1.96
[6]	Xiaogang Liu, Muhammad Ahsan, Zohaib Zahid, Shuili Ren . Fault-tolerant edge metric dimension of certain families of graphs. AIMS Mathematics, 2021, 6(2): 1140-1152. doi: 10.3934/math.2021069
[7]	Lyimo Sygbert Mhagama, Muhammad Faisal Nadeem, Mohamad Nazri Husin . On the edge metric dimension of some classes of cacti. AIMS Mathematics, 2024, 9(6): 16422-16435. doi: 10.3934/math.2024795
[8]	Ali N. A. Koam, Adnan Khalil, Ali Ahmad, Muhammad Azeem . Cardinality bounds on subsets in the partition resolving set for complex convex polytope-like graph. AIMS Mathematics, 2024, 9(4): 10078-10094. doi: 10.3934/math.2024493
[9]	Hui Chen . Characterizations of normal cancellative monoids. AIMS Mathematics, 2024, 9(1): 302-318. doi: 10.3934/math.2024018
[10]	Chenggang Huo, Humera Bashir, Zohaib Zahid, Yu Ming Chu . On the 2-metric resolvability of graphs. AIMS Mathematics, 2020, 5(6): 6609-6619. doi: 10.3934/math.2020425

Abstract

1. Introduction

Fractional differential equations have gotten attention and prominence due to their numerous applications in engineering and science. These equations, for instance, are increasingly being utilized to explain phenomena in many different physical processes, including fluid mechanics, biology, electromagnetic, signal processing, acoustics and many more. In these and other applications, the non-locality of fractional differential equations is their main benefit. The integer order differential operator is typically considered a local operator, whereas the fractional order differential operator is non-local. This shows that the next state of a system depends on both its present state and all of its previous states. This is more practical, which is one of the reasons fractional calculus is growing in popularity ^{[1,2,3,4,5,6,7,8,9]}.

Finding solutions to fractional differential equations has therefore received a lot of interest. A fractional differential equation is typically challenging to solve exactly. Researchers were interested in numerical approaches, the perturbation method among them. However, there are significant drawbacks to perturbation methods. For instance, the approximate solution necessitates a number of small parameters, which is problematic because most nonlinear problems do not have any small parameters. Even if an adequate selection of minor parameters occasionally results in the optimal solution, inappropriate selections frequently have negative consequences for the solutions. J. H. He, a Chinese researcher, invented the homotopy perturbation method (HPM) and presented it in 1998 ^[10,11].

The Adomian decomposition method ^[12,13] is a powerful approach for solving linear and nonlinear, homogeneous and nonhomogeneous partial and differential equations, and integro-differential equations of integer and non-integer order, which gives us convergent series from exact solutions. Several mathematicians used the homotopy perturbation method for handling nonlinear equations arising in engineering and science ^{[14,15,16,17]}. Many authors have focused their attention recently on examining the solutions to both linear and nonlinear partial differential equations using a variety of techniques such as Elzaki transform decomposition method ^[18,19], homotopy perturbation transform technique ^[20,21], homotopy analysis transform method ^[22,23], $q$ -homotopy analysis transform method ^[24], iterative Laplace transform method ^[25], variational iteration method ^[26,27] and many others among them.

The mathematical theory of shock waves describes the first-order quasi-linear hyperbolic system of partial differential equations (PDEs) surface of discontinuity's characteristics. In the latter half of the 19th century, concerns with the compressible fluids and motion of gases gave rise to the mathematical theory of shock waves. The research of Earnshaw ^[28], Riemann ^[29], Rankine ^[30] and Hugoniot ^[31] laid the groundwork for it. One imagines a medium devoid of dissipation, viscosity and thermal conductivity as an idealization of actual gases and fluids. There may be discontinuities in the distribution of all flow parameters during motion in such idealized media (the temperature, the pressure, the velocity, the density, etc.). The collection of flow parameter discontinuity spots may be highly intricate when this set has piecewise-smooth surfaces of discontinuity made up of discontinuity points of the first kind; only the most elementary basic cases have been carefully taken into account. In the general scenario, discontinuous two-dimensional surfaces move in the three-dimensional space $\mathbb{R}^{3}$ as time passes. Conservation laws are among the characteristics shared by all continuum physics theories. By connecting the values of the primary vector field $\mathbb{J}$ to the flux $f$ , constitutive relations that characterize the specific medium in question are added to the laws. By connecting the principal vector field $\mathbb{J}$ values to the flux $f$ , constitutive relations that characterize the specific medium in question are added to the laws.

Since we are assuming that these relations are represented by smooth forms in this scenario, the conservation laws lead to nonlinear hyperbolic PDEs, which are expressed in their most basic form as

$\begin{equation} \mathbb{J}_{\vartheta}(\kappa, \vartheta)+f(\mathbb{J}(\kappa, \vartheta))_{\kappa} = 0, \quad \kappa\in\mathbb{R}, \; \vartheta > 0, \end{equation}$

(1.1)

subjected to the initial condition

$\begin{equation*} \mathbb{J}(\kappa, 0) = \mathbb{J}_{0}(\kappa), \quad \kappa\in\mathbb{R}. \end{equation*}$

A model for a variety of physical phenomena, including shock waves and three-phase flow in porous media, uses (1.1). Traffic flow, explosions, aeroplanes breaking the sound barrier, glacier waves, and other phenomena all use shock waves. Nonlinear hyperbolic PDEs are used to formulate them ^[32,33,34]. The Adomian decomposition method (ADM) ^[35,36,37] and the homotopy perturbation method (HPM) ^[38,39,40] have both been used to study the shock wave and wave equations. Since solutions are simple to find, the classical shock wave and wave equations provide excellent predictive equations. We introduce a fractional-order generalization of shock wave (1.1) in this article, which has the following form:

$\begin{equation} D_{\vartheta}^{\rho}\mathbb{J}(\kappa, \vartheta)+f(\mathbb{J}(\kappa, \vartheta))_{\kappa} = 0, \quad \kappa\in\mathbb{R}, \; \vartheta > 0, \end{equation}$

(1.2)

where a parameter named $\rho$ designates the order of the time-derivative. In the Caputo sense, the derivative is regarded. A parameter specifying the order of the fractional-order shock wave equation is included in the general response expression and can be changed to generate different responses. The fractional-order shock wave equation is reduced to the standard shock wave equation when $\rho = 1$ .

This study solves the fractional-order shock wave and wave equations analytically and numerically using the new homotopy perturbation transform technique and the Yang transform decomposition method. This method's ability to combine two effective approaches for generating precise and approximative analytical solutions for nonlinear equations is an advantage. It is important to note that the suggested methodology can perform better overall since it can reduce the amount of computational work required compared to the other techniques while still keeping the high accuracy of the numerical result.

The rest of the paper is organized as follows: In Section 2, we introduce some fundamental preliminaries. In Section 3, we presented the general methodology of HPYTM to obtain the solution of general arbitrary order PDE, while in Section 4, we presented the general method of YDTM to get the solution of general arbitrary order PDE. In Section 5, the suggested techniques are implemented for solving nonlinear fractional-order shock wave equations, and in Section 6, results and discussion are given. Similarly, in the end, a brief conclusion is given in Section 7.

2. Preliminaries

In this section, we discuss a number of important concepts, terminology and ideas relevant to the fractional derivative operators used in the current study.

Definition 2.1. The fractional Caputo derivative is stated as

$\begin{equation} D_{\mathbb{J}}^{\rho}\mathbb{J}(\kappa, \vartheta) = \frac{1}{\Gamma(k-\rho)}\int_{0}^{\vartheta}(\vartheta-\rho)^{k-\rho-1}\mathbb{J}^{(k)}(\kappa, \rho)d\rho, \quad k-1 < \rho\leq k, \quad k\in\mathbb{N}. \end{equation}$

(2.1)

Definition 2.2. The Yang transform (YT) of a function $\mathbb{J}(\vartheta)$ is stated as

$\begin{equation} Y\left(\mathbb{J}(\vartheta)\right) = M(u) = \int_0^{\infty}e^{\frac{-\vartheta}{u}}\mathbb{J}(\vartheta)d\vartheta, \quad \vartheta > 0, \; u\in(-\vartheta_1, \vartheta_2), \end{equation}$

(2.2)

having Yang inverse transform as

$\begin{equation} Y^{-1}\{M(u)\} = \mathbb{J}(\vartheta). \end{equation}$

(2.3)

Definition 2.3. The Yang transform of $n$ th derivatives is stated as

$\begin{equation} Y(\mathbb{J}^{n}(\vartheta)) = \frac{M(u)}{u^{n}}-\sum\limits_{k = 0}^{n-1}\frac{\mathbb{J}^{k}(0)}{u^{n-k-1}}, \end{equation}$

(2.4)

for all $n = 1, 2, 3, \dots.$

Definition 2.4. The Yang transform of fractional-order derivative is stated as

$\begin{equation} Y(\mathbb{J}^{\rho}(\vartheta)) = \frac{M(u)}{u^{\rho}}-\sum\limits_{k = 0}^{n-1}\frac{\mathbb{J}^{k}(0)}{u^{\rho-(k+1)}}, \quad 0 < \rho \leq n. \end{equation}$

(2.5)

3. General methodology of HPYTM

This section is concerned with fundamental solution process of HPYTM to get the solution of general arbitrary order partial differential equation

$\begin{equation} D_{\vartheta}^{\rho}\mathbb{J}(\kappa, \vartheta) = \mathcal{P}_1[\kappa]\mathbb{J}(\kappa, \vartheta)+\mathcal{Q}_1[\kappa]\mathbb{J}(\kappa, \vartheta), \quad 0 < \rho\leq2, \end{equation}$

(3.1)

subjected to the initial conditions

$\mathbb{J}(\kappa, 0) = \xi(\kappa), \quad \frac{\partial}{\partial\vartheta}\mathbb{J}(\kappa, 0) = \zeta(\kappa),$

where $D_{\vartheta}^{\rho} = \frac{\partial^{\rho}}{\partial \vartheta^{\rho}}$ is the fractional Caputo derivative, $\mathcal{P}_1[\kappa]$ and $\mathcal{Q}_1[\kappa]$ are linear and nonlinear operators.

By employing YT, we have

$\begin{align} Y\left[D_{\vartheta}^{\rho}\mathbb{J}(\kappa, \vartheta)\right]& = Y[\mathcal{P}_1[\kappa]\mathbb{J}(\kappa, \vartheta)+\mathcal{Q}_1[\kappa]\mathbb{J}(\kappa, \vartheta)], \end{align}$

(3.2)

$\begin{align} \frac{1}{u^{\rho}}\left\{M(u)- u \mathbb{J}(0)- u^2\mathbb{J}^{'}(0)\right\}& = Y[\mathcal{P}_1[\kappa]\mathbb{J}(\kappa, \vartheta)+\mathcal{Q}_1[\kappa]\mathbb{J}(\kappa, \vartheta)]. \end{align}$

(3.3)

On simplification, we get

$\begin{equation} M(\mathbb{J}) = u \mathbb{J}(0)+ u^2 \mathbb{J}^{'}(0)+u^{\rho}Y[\mathcal{P}_1[\kappa]\mathbb{J}(\kappa, \vartheta)+\mathcal{Q}_1[\kappa]\mathbb{J}(\kappa, \vartheta)]. \end{equation}$

(3.4)

Operating inverse YT both sides, we have

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = \mathbb{J}(0)+ \mathbb{J}^{'}(0)+Y^{-1}[u^{\rho}Y[\mathcal{P}_1[\kappa]\mathbb{J}(\kappa, \vartheta)+\mathcal{Q}_1[\kappa]\mathbb{J}(\kappa, \vartheta)]]. \end{equation}$

(3.5)

Now, by using the HPM

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = \sum\limits_{k = 0}^{\infty}\epsilon^{k}\mathbb{J}_{k}(\kappa, \vartheta), \end{equation}$

(3.6)

with perturbation parameter $\epsilon\in[0, 1]$ .

The nonlinear terms are decomposed as

$\begin{equation} \mathcal{Q}_1[\kappa]\mathbb{J}(\kappa, \vartheta) = \sum\limits_{k = 0}^{\infty}\epsilon^{k}H_{n}(\mathbb{J}), \end{equation}$

(3.7)

and He's polynomials $H_{k}(\mathbb{J})$ are given as

$\begin{equation} H_{n}(\mathbb{J}_{0}, \mathbb{J}_{1}, \ldots, \mathbb{J}_{n}) = \frac{1}{\Gamma(n+1)}D_{\epsilon}^{k}\left[\mathcal{Q}_1\left(\sum\limits_{k = 0}^{\infty}\epsilon^{i}\mathbb{J}_{i}\right)\right]_{\epsilon = 0}, \end{equation}$

(3.8)

where $D_{\epsilon}^{k} = \frac{\partial^{k}}{\partial \epsilon^{k}}.$

Using (3.7) and (3.8) in (3.5), we have

$\begin{equation} \sum\limits_{k = 0}^{\infty}\epsilon^{k}\mathbb{J}_{k}(\kappa, \vartheta) = \mathbb{J}(0)+ \mathbb{J}^{'}(0)+\epsilon\left(Y^{-1}\left\{u^{\rho}Y\left(\mathcal{P}_1\sum\limits_{k = 0}^{\infty}\epsilon^{k}\mathbb{J}_{k}(\kappa, \vartheta)+\sum\limits_{k = 0}^{\infty}\epsilon^{k}H_{k}(\mathbb{J})\right)\right\}\right). \end{equation}$

(3.9)

Thus, by equating the coefficient of $\epsilon$ , we get

$\begin{equation} \ \begin{split} &\epsilon^{0}:\mathbb{J}_{0}(\kappa, \vartheta) = \mathbb{J}(0)+ \mathbb{J}^{'}(0), \\ &\epsilon^{1}:\mathbb{J}_{1}(\kappa, \vartheta) = Y^{-1}\left[u^{\rho}Y(\mathcal{P}_1[\kappa]\mathbb{J}_{0}(\kappa, \vartheta)+H_{0}(\mathbb{J}))\right], \\ &\epsilon^{2}:\mathbb{J}_{2}(\kappa, \vartheta) = Y^{-1}\left[u^{\rho}Y(\mathcal{P}_1[\kappa]\mathbb{J}_{1}(\kappa, \vartheta)+H_{1}(\mathbb{J}))\right], \\ &\quad\, \vdots\\ &\epsilon^{k}:\mathbb{J}_{k}(\kappa, \vartheta) = Y^{-1}\left[u^{\rho}Y(\mathcal{P}_1[\kappa]\mathbb{J}_{k-1}(\kappa, \vartheta)+H_{k-1}(\mathbb{J}))\right], \end{split} \end{equation}$

(3.10)

for $k > 0$ , $k\in\mathbb{N}$ .

Finally, we use truncated series to approximate the analytical solution $\mathbb{J}_{k}(\kappa, \vartheta)$ ,

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = \lim\limits_{M\rightarrow \infty}\sum\limits_{k = 1}^{M}\mathbb{J}_{k}(\kappa, \vartheta). \end{equation}$

(3.11)

The solutions to the aforementioned series usually converge quickly.

4. General methodology of YTDM

This section is concerned with the fundamental solution process of YTDM to get the solution of general arbitrary order partial differential equation

$\begin{equation} D_\vartheta^\rho{\mathbb{J}(\kappa, \vartheta)} = \mathcal{P}_1(\kappa, \vartheta)+\mathcal{Q}_1(\kappa, \vartheta), \quad 0 < \rho \leq 1, \end{equation}$

(4.1)

subjected to the initial conditions

$\mathbb{J}(\kappa, 0) = \xi(\kappa), \quad\frac{\partial}{\partial\vartheta}\mathbb{J}(\kappa, 0) = \zeta(\kappa),$

where $D_\vartheta^\rho = \frac{\partial^\rho}{\partial \vartheta^\rho}$ is the fractional Caputo derivative, $\mathcal{P}_1$ and $\mathcal{Q}_1$ are linear and non-linear operators, respectively.

By employing YT, we have

$\begin{equation} Y\left[D_\vartheta^\rho{\mathbb{J}(\kappa, \vartheta)}\right] = Y\left[\mathcal{P}_1(\kappa, \vartheta)+\mathcal{Q}_1(\kappa, \vartheta)\right], \end{equation}$

(4.2)

using the differentiation property of the YT, we have

$\begin{equation} \frac{1}{u^{\rho}}\left\{M(u)- u \mathbb{J}(0)- u^2\mathbb{J}^{'}(0)\right\} = Y\left[\mathcal{P}_1(\kappa, \vartheta)+\mathcal{Q}_1(\kappa, \vartheta)\right]. \end{equation}$

(4.3)

On simplification, we get

$\begin{equation} M(\mathbb{J}) = u \mathbb{J}(0)+ u^2 \mathbb{J}^{'}(0)+u^{\rho}Y\left[\mathcal{P}_1(\kappa, \vartheta)+\mathcal{Q}_1(\kappa, \vartheta)\right]. \end{equation}$

(4.4)

Operating inverse YT both sides, we have

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = \mathbb{J}(0)+ \mathbb{J}^{'}(0)+Y^{-1}[u^{\rho}Y[\mathcal{P}_1(\kappa, \vartheta)+\mathcal{Q}_1(\kappa, \vartheta)]. \end{equation}$

(4.5)

Thus, by means of YTDM the infinite series solution of $\mathbb{J}(\kappa, \vartheta)$ ,

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta). \end{equation}$

(4.6)

The decomposition of of nonlinear terms $\mathcal{Q}_1$ in terms of the Adomian polynomials are given as

$\begin{equation} \mathcal{Q}_1(\kappa, \vartheta) = \sum\limits_{m = 0}^{\infty}\mathcal{A}_m, \end{equation}$

(4.7)

where

$\begin{equation} \mathcal{A}_m = \frac{1}{m!}\left[\frac{\partial^m}{\partial\ell^m}\left\{\mathcal{Q}_1\left(\sum\limits_{k = 0}^{\infty}\ell^k\kappa_k, \sum\limits_{k = 0}^{\infty}\ell^k\vartheta_k\right)\right\}\right]_{\ell = 0}. \end{equation}$

(4.8)

By putting (4.6) and (4.8) into (4.5), we obtain

$\begin{equation} \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta) = \mathbb{J}(0)+ \mathbb{J}^{'}(0)+Y^{-1} u^\rho \left[Y\left(\mathcal{P}_1\left(\sum\limits_{m = 0}^{\infty}\kappa_m, \sum\limits_{m = 0}^{\infty}\vartheta_m\right)+\sum\limits_{m = 0}^{\infty}\mathcal{A}_m\right)\right]. \end{equation}$

(4.9)

We illustrate the below terms:

$\begin{align} \mathbb{J}_0(\kappa, \vartheta)& = \mathbb{J}(0)+ \vartheta\mathbb{J}^{'}(0), \end{align}$

(4.10)

$\begin{align} \mathbb{J}_1(\kappa, \vartheta)& = Y^{-1}\left[u^\rho Y^+\left\{\mathcal{P}_1(\kappa_0, \vartheta_0)+\mathcal{A}_0\right\}\right]. \end{align}$

(4.11)

Hence, in general for $m\geq1$ , we have

$\begin{equation*} \mathbb{J}_{m+1}(\kappa, \vartheta) = Y^{-1}\left[u^\rho Y^+\{\mathcal{P}_1(\kappa_m, \vartheta_m)+\mathcal{A}_m\}\right]. \end{equation*}$

5. Applications

This section is concerned with the implementation of YTDM and HPYTM to solve fractional-order nonlinear shock wave equations.

Example 5.1. Consider the nonlinear fractional-order shock wave equation

$\begin{equation} \frac{\partial^{\rho}\mathbb{J}}{\partial\vartheta^{\rho}}+\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa} = 0, \quad 0 < \rho\leq1, \end{equation}$

(5.1)

with the initial condition

$\begin{equation*} \mathbb{J}(\kappa, 0) = \exp\left(-\frac{\kappa^{2}}{2}\right), \end{equation*}$

where $c_{0}$ and $\Upsilon$ are constants with $\Upsilon$ representing the specific heat. In the present study, we choose $c_{0} = 2$ and $\Upsilon = 1.5,$ which represent the airflow.

By employing YT, we have

$\begin{equation} Y\left(\frac{\partial^{\rho}\mathbb{J}}{\partial \vartheta^{\rho}}\right) = -Y\left[\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right]. \end{equation}$

(5.2)

Now, by YT differentiation property, we get

$\begin{equation} \frac{1}{u^{\rho}}\{M(u)- u \mathbb{J}(0)\} = -Y\left[\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right] \end{equation}$

(5.3)

and

$\begin{equation} M(u) = u\mathbb{J}(0)-u^{\rho}Y\left[\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right]. \end{equation}$

(5.4)

Operating inverse YT both sides, we have

$\begin{equation} \begin{split} &\mathbb{J}(\kappa, \vartheta) = \mathbb{J}(0)-Y^{-1}\left\{u^\rho\left[Y\left(\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right)\right]\right\}, \\ &\mathbb{J}(\kappa, \vartheta) = \exp\left(-\frac{\kappa^{2}}{2}\right)-Y^{-1}\left\{u^\rho\left[Y\left(\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right)\right]\right\}. \end{split} \end{equation}$

(5.5)

Thus, by using the HPM, we obtain

$\begin{equation} \ \sum\limits_{k = 0}^{\infty}\epsilon^{k}\mathbb{J}_{k}(\kappa, \vartheta) = \gamma+\epsilon\left(Y^{-1}\left\{u^{\rho}Y\left[\frac{1}{c_{0}}\frac{\partial\mathbb{J}}{\partial \kappa}\left(\sum\limits_{k = 0}^{\infty}\epsilon^{k}\mathbb{J}_{k}(\kappa, \vartheta)\right) -\frac{\Upsilon+1}{2}\frac{1}{c_{0}^{2}}\left(\sum\limits_{k = 0}^{\infty}\epsilon^{k}H_{k}(\mathbb{J})\right)\right]\right\}\right), \end{equation}$

(5.6)

where non-linear terms are represented by He's polynomial $H_{k}(\mathbb{J})$ and is stated as

$\begin{equation} \sum\limits_{k = 0}^{\infty}\epsilon^{k}H_{k}(\mathbb{J}) = \mathbb{J}\frac{\partial\mathbb{J}}{\partial \kappa}. \end{equation}$

(5.7)

Some components of He's polynomials are calculated as

$H_{0}(\mathbb{J}) = \mathbb{J}_{0}\frac{\partial\mathbb{J}_{0}}{\partial \kappa}, \quad H_{1}(\mathbb{J}) = \mathbb{J}_{0}\frac{\partial\mathbb{J}_{1}}{\partial \kappa}+\mathbb{J}_{1}\frac{\partial\mathbb{J}_{0}}{\partial \kappa}.$

By comparing the coefficient of $\epsilon$ , we obtain

$\begin{equation*} \begin{split} &\epsilon^{0}:\mathbb{J}_{0}(\kappa, \vartheta) = \exp\left(-\frac{\kappa^{2}}{2}\right), \\ &\epsilon^{1}:\mathbb{J}_{1}(\kappa, \vartheta) = Y^{-1}\left\{u^{\rho}Y\left(\frac{1}{c_{0}}\frac{\partial\mathbb{J}_{0}}{\partial \kappa}-\frac{\Upsilon+1}{2}\frac{1}{c_{0}^{2}}H_{0}(\mathbb{J})\right)\right\} = \\ &-\left[\frac{1}{c_{0}}-\frac{\Upsilon+1}{2c_{0}^{2}}\exp\left(-\frac{\kappa^{2}}{2}\right)\right]\kappa\exp\left(-\frac{\kappa^{2}}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}, \\ &\epsilon^{2}:\mathbb{J}_{2}(\kappa, \vartheta) = Y^{-1}\left\{u^{\rho}Y\left[(\frac{1}{c_{0}}\frac{\partial\mathbb{J}_{1}}{\partial \kappa}-\frac{\Upsilon+1}{2}\frac{1}{c_{0}^{2}}H_{1}(\mathbb{J})\right)\right\} = \\ &\exp\left(-\frac{\kappa^{2}}{2}\right)\left[-\frac{1}{c_{0}^{2}}+\frac{\kappa^{2}}{c_{0}^{2}}-\frac{\Upsilon+1}{c_{0}^{3}}\exp\left(-\frac{\kappa^{2}}{2}\right)\right.\\ &\;\left.-\frac{2(\Upsilon+1)}{c_{0}^{3}}\kappa^{2}\exp\left(-\frac{\kappa^{2}}{2}\right)-\frac{(\Upsilon+1)^{2}}{4c_{0}^{4}}\exp\left(-\kappa^{2}\right)+\frac{3(\Upsilon+1)^{2}}{4c_{0}^{4}}\kappa^{2}\exp\left(-\kappa^{2}\right)\right]\\ &\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}, \\ &\quad\;\vdots \end{split} \end{equation*}$

The remaining elements of the HPYTM solution can be achieved by continuing in the same way. Thus,

$\begin{align*} \mathbb{J}(\kappa, \vartheta)& = \exp\left(-\frac{\kappa^{2}}{2}\right)-\left[\frac{1}{c_{0}}-\frac{\Upsilon+1}{2c_{0}^{2}}\exp\left(-\frac{\kappa^{2}}{2}\right)\right]\kappa\exp\left(-\frac{\kappa^{2}}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}+\exp\left(-\frac{\kappa^{2}}{2}\right)\\ &\quad\times\left[-\frac{1}{c_{0}^{2}}+\frac{\kappa^{2}}{c_{0}^{2}}-\frac{\Upsilon+1}{c_{0}^{3}}\exp\left(-\frac{\kappa^{2}}{2}\right)-\frac{2(\Upsilon+1)}{c_{0}^{3}}\kappa^{2}\exp\left(-\frac{\kappa^{2}}{2}\right)-\frac{(\Upsilon+1)^{2}}{4c_{0}^{4}}\exp\left(-\kappa^{2}\right)\right.\\ &\quad\left.+\frac{3(\Upsilon+1)^{2}}{4c_{0}^{4}}\kappa^{2}\exp\left(-\kappa^{2}\right)\right]\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}+\cdots. \end{align*}$

By employing YT, we have

$\begin{equation} Y\left(\frac{\partial^{\rho}\mathbb{J}}{\partial \vartheta^{\rho}}\right) = -Y\left(\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right). \end{equation}$

(5.8)

Now, by YT differentiation property, we get

$\begin{align} \frac{1}{u^{\rho}}\left\{M(u)- u \mathbb{J}(0)\right\}& = -Y\left(\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right), \end{align}$

(5.9)

$\begin{align} M(u)& = u \mathbb{J}(0)+u^{\rho}Y\left(\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right). \end{align}$

(5.10)

Operating inverse YT both sides, we have

$\begin{equation} \begin{split} \mathbb{J}(\kappa, \vartheta)& = \mathbb{J}(0)-Y^{-1}\left\{u^\rho\left[Y\left(\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right)\right]\right\}, \\ \mathbb{J}(\kappa, \vartheta)& = \exp\left(-\frac{\kappa^{2}}{2}\right)-Y^{-1}\left\{u^\rho\left[Y\left(\left(\frac{1}{c_{0}}-\frac{\Upsilon+1}{2}\frac{\mathbb{J}}{c_{0}^{2}}\right)\frac{\partial\mathbb{J}}{\partial \kappa}\right)\right]\right\}. \end{split} \end{equation}$

(5.11)

Thus, by means of YTDM the infinite series solution of $\mathbb{J}(\kappa, \vartheta)$ ,

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta), \end{equation}$

(5.12)

and by means of Adomian polynomial, the nonlinear terms are derived as $\mathbb{J}\frac{\partial\mathbb{J}}{\partial \kappa} = \sum_{m = 0}^{\infty}\mathcal{A}_m$ , we have

$\begin{equation} \begin{split} &\sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta) = \mathbb{J}(\kappa, 0) -Y^{-1}\left\{u^\rho\left[Y\left(\left(\frac{1}{c_{0}}\frac{\partial\mathbb{J}}{\partial \kappa}-\frac{\Upsilon+1}{2c_{0}^{2}}\sum\limits_{m = 0}^{\infty}\mathcal{A}_m\right)\right)\right]\right\}, \\ &\sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta) = \exp\left(-\frac{\kappa^{2}}{2}\right) -Y^{-1}\left\{u^\rho\left[Y\left(\left(\frac{1}{c_{0}}\frac{\partial\mathbb{J}}{\partial \kappa}-\frac{\Upsilon+1}{2c_{0}^{2}}\sum\limits_{m = 0}^{\infty}\mathcal{A}_m\right)\right)\right]\right\}. \end{split} \end{equation}$

(5.13)

In this way, the nonlinear terms are decomposed as

$\begin{equation*} \mathcal{A}_0 = \mathbb{J}_{0}\frac{\partial\mathbb{J}_{0}}{\partial \kappa}, \quad \mathcal{A}_1 = \mathbb{J}_{0}\frac{\partial\mathbb{J}_{1}}{\partial \kappa}+\mathbb{J}_{1}\frac{\partial\mathbb{J}_{0}}{\partial \kappa}. \end{equation*}$

On comparing both sides, we get

$\begin{equation*} \mathbb{J}_0(\kappa, \vartheta) = \exp\left(-\frac{\kappa^{2}}{2}\right). \end{equation*}$

On $m = 0$ , we have

$\begin{equation*} \mathbb{J}_1(\kappa, \vartheta) = -\left[\frac{1}{c_{0}}-\frac{\Upsilon+1}{2c_{0}^{2}}\exp\left(-\frac{\kappa^{2}}{2}\right)\right]\kappa\exp\left(-\frac{\kappa^{2}}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}. \end{equation*}$

On $m = 1$ , we have

$\begin{align*} \mathbb{J}_2(\kappa, \vartheta)& = \exp\left(-\frac{\kappa^{2}}{2}\right)\left[-\frac{1}{c_{0}^{2}}+\frac{\kappa^{2}}{c_{0}^{2}}-\frac{\Upsilon+1}{c_{0}^{3}}\exp\left(-\frac{\kappa^{2}}{2}\right)-\frac{2(\Upsilon+1)}{c_{0}^{3}}\kappa^{2}\exp\left(-\frac{\kappa^{2}}{2}\right)\right.\\ &\quad\left.-\frac{(\Upsilon+1)^{2}}{4c_{0}^{4}}\exp\left(-\kappa^{2}\right)+\frac{3(\Upsilon+1)^{2}}{4c_{0}^{4}}\kappa^{2}\exp\left(-\kappa^{2}\right)\right]\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}. \end{align*}$

Thus, the remaining elements $\rho_m$ of YTDM for $(m\geq2)$ are easy to get. Hence, we write the series form solution as

$\begin{align*}& \mathbb{J}(\kappa, \vartheta)= \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta) = \mathbb{J}_0(\kappa, \vartheta)+\mathbb{J}_1(\kappa, \vartheta)+\mathbb{J}_2(\kappa, \vartheta)+\cdots, \\ &\mathbb{J}(\kappa, \vartheta) = \exp\left(-\frac{\kappa^{2}}{2}\right)-\left[\frac{1}{c_{0}}-\frac{\Upsilon+1}{2c_{0}^{2}}\exp\left(-\frac{\kappa^{2}}{2}\right)\right]\kappa\exp\left(-\frac{\kappa^{2}}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}\\ &+\exp\left(-\frac{\kappa^{2}}{2}\right)\\ &\left[-\frac{1}{c_{0}^{2}}+\frac{\kappa^{2}}{c_{0}^{2}}-\frac{\Upsilon+1}{c_{0}^{3}}\exp\left(-\frac{\kappa^{2}}{2}\right)-\frac{2(\Upsilon+1)}{c_{0}^{3}}\kappa^{2}\exp\left(-\frac{\kappa^{2}}{2}\right)-\frac{(\Upsilon+1)^{2}}{4c_{0}^{4}}\exp\left(-\kappa^{2}\right)\right.\\ &\left.+\frac{3(\Upsilon+1)^{2}}{4c_{0}^{4}}\kappa^{2}\exp\left(-\kappa^{2}\right)\right]\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}+\cdots. \end{align*}$

Example 5.2. Consider the nonlinear fractional-order shock wave equation

$\begin{equation} \frac{\partial^{\rho}\mathbb{J}}{\partial\vartheta^{\rho}}+\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}-\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}} = 0, \quad 0 < \rho\leq1, \end{equation}$

(5.14)

with initial source

$\begin{equation*} \mathbb{J}(\kappa, 0) = 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15}{2}\right). \end{equation*}$

By employing YT, we have

$\begin{equation} Y\left(\frac{\partial^{\rho}\mathbb{J}}{\partial \vartheta^{\rho}}\right) = Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right). \end{equation}$

(5.15)

Now, by YT differentiation property, we get

$\begin{equation} \frac{1}{u^{\rho}}\left\{M(u)- u \mathbb{J}(0)\right\} = Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right) \end{equation}$

(5.16)

and

$\begin{equation} M(u) = u \mathbb{J}(0)+u^{\rho} Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right). \end{equation}$

(5.17)

Operating inverse YT both sides, we have

$\begin{equation} \begin{split} &\mathbb{J}(\kappa, \vartheta) = \mathbb{J}(0)+Y^{-1}\left\{u^\rho\left[Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right)\right]\right\}, \\ &\mathbb{J}(\kappa, \vartheta) = 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15}{2}\right)+Y^{-1}\left\{u^\rho\left[Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right)\right]\right\}. \end{split} \end{equation}$

(5.18)

Now, by using the HPM, we obtain

$\begin{equation} \sum\limits_{k = 0}^{\infty}\epsilon^{k}\mathbb{J}_{k}(\kappa, \vartheta) = 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15}{2}\right)+\epsilon\left(Y^{-1}\left\{u^{\rho}Y\left[\left(\sum\limits_{k = 0}^{\infty}\epsilon^{k}\mathbb{J}_{k}(\kappa, \vartheta)\right)_{\kappa\kappa\vartheta} -\left(\sum\limits_{k = 0}^{\infty}\epsilon^{k}H_{k}(\mathbb{J})\right)\right]\right\}\right), \end{equation}$

(5.19)

where non-linear terms are presented by He's polynomial $H_{k}(\mathbb{J})$ and is stated as

$\begin{equation} \sum\limits_{k = 0}^{\infty}\epsilon^{k}H_{k}(\mathbb{J}) = \mathbb{J}\frac{\partial\mathbb{J}}{\partial \kappa}. \end{equation}$

(5.20)

Some terms of He's polynomials are calculated as

By comparing the coefficient of $\epsilon$ , we obtain

$\begin{equation*} \ \begin{split} &\epsilon^{0}:\mathbb{J}_{0}(\kappa, \vartheta) = 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15}{2}\right), \\ &\epsilon^{1}:\mathbb{J}_{1}(\kappa, \vartheta) = Y^{-1}\left\{u^{\rho}Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}_{0}}{\partial \kappa^{2}}-H_{0}(\mathbb{J})\right)\right\}\\ & = 9\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh\left(\frac{\kappa-15}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}, \\& \epsilon^{2}:\mathbb{J}_{2}(\kappa, \vartheta) = Y^{-1}\left\{u^{\rho}Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}_{1}}{\partial \kappa^{2}}-H_{1}(\mathbb{J})\right)\right\}\\ & = \left[\frac{189}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\tanh^{2}\left(\frac{\kappa-15}{2}\right)-\frac{27}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\right]\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}\\ &+\left[\frac{135}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh^{3}\left(\frac{\kappa-15}{2}\right)-\frac{63}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\tanh\left(\frac{\kappa-15}{2}\right)\right)\right]\\ &\frac{\Gamma(\rho+1)\vartheta^{2\rho-1}}{\Gamma(2\rho)}, \\ &\;\;\vdots\\ \end{split} \end{equation*}$

The remaining elements of the HPYTM solution can be achieved by continuing in the same way. Thus,

$\begin{align*} &\mathbb{J}(\kappa, \vartheta) = 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15}{2}\right)+9\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh\left(\frac{\kappa-15}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}\\ &+\left[\frac{189}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\tanh^{2}\left(\frac{\kappa-15}{2}\right)-\frac{27}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\right]\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}\\ &+\left[\frac{135}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh^{3}\left(\frac{\kappa-15}{2}\right)-\frac{63}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\tanh\left(\frac{\kappa-15}{2}\right)\right)\right]\\ &\frac{\Gamma(\rho+1)\vartheta^{2\rho-1}}{\Gamma(2\rho)}\\ &+\cdots. \end{align*}$

By employing YT, we have

(5.21)

Now, by YT differentiation property, we have

$\begin{equation} \frac{1}{u^{\rho}}\{M(u)- u \mathbb{J}(0)\} = Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right) \end{equation}$

(5.22)

and

$\begin{equation} M(u) = u \mathbb{J}(0)+u^{\rho}Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right). \end{equation}$

(5.23)

Operating inverse YT both sides, we have

$\begin{equation} \begin{split} &\mathbb{J}(\kappa, \vartheta) = \mathbb{J}(0)+Y^{-1}\left\{u^\rho\left[Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right)\right]\right\}, \\ &\mathbb{J}(\kappa, \vartheta) = \frac{1}{(1+\exp(\kappa))^{2}}+Y^{-1}\left\{u^\rho\left[Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa}\right)\right]\right\}. \end{split} \end{equation}$

(5.24)

Thus, by means of YTDM the infinite series solution of $\mathbb{J}(\kappa, \vartheta)$ ,

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta), \end{equation}$

(5.25)

and by means of Adomian polynomial, the nonlinear terms are derived as $\mathbb{J}\frac{\partial\mathbb{J}}{\partial\kappa} = \sum_{m = 0}^{\infty}\mathcal{A}_m$ , we have

$\begin{equation} \begin{split} \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta)& = \mathbb{J}(\kappa, 0)+Y^{-1}\left\{u^\rho\left[ Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\sum\limits_{m = 0}^{\infty}\mathcal{A}_m\right)\right]\right\}, \\ \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta)& = \frac{1}{(1+\exp(\kappa))^{2}}+Y^{-1}\left\{u^\rho\left[Y\left(\frac{\partial}{\partial \vartheta}\frac{\partial\mathbb{J}^{2}}{\partial \kappa^{2}}-\sum\limits_{m = 0}^{\infty}\mathcal{A}_m\right)\right]\right\}. \end{split} \end{equation}$

(5.26)

In this way, the nonlinear terms are decomposed as

On comparing both sides, we get

$\begin{equation*} \mathbb{J}_0(\kappa, \vartheta) = 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15}{2}\right). \end{equation*}$

On $m = 0$ , we have

$\begin{equation*} \mathbb{J}_1(\kappa, \vartheta) = 9\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh\left(\frac{\kappa-15}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}. \end{equation*}$

On $m = 1$ , we have

$\begin{align*} &\mathbb{J}_2(\kappa, \vartheta) = \left[\frac{189}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\tanh^{2}\left(\frac{\kappa-15}{2}\right)-\frac{27}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\right]\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}\\ &+\left[\frac{135}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh^{3}\left(\frac{\kappa-15}{2}\right)-\frac{63}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\tanh\left(\frac{\kappa-15}{2}\right)\right)\right]\\ &\frac{\Gamma(\rho+1)\vartheta^{2\rho-1}}{\Gamma(2\rho)}. \end{align*}$

Thus, the remaining elements $\rho_m$ of YTDM for $(m\geq3)$ are easy to get. Hence, we write the series form solution as

$\begin{align*}& \mathbb{J}(\kappa, \vartheta) = \sum\limits_{m = 0}^{\infty}\mathbb{J}_m(\kappa, \vartheta) = \mathbb{J}_0(\kappa, \vartheta)+\mathbb{J}_1(\kappa, \vartheta)+\cdots, \\ & \mathbb{J}(\kappa, \vartheta)= 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15}{2}\right)+9\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh\left(\frac{\kappa-15}{2}\right)\frac{\vartheta^{\rho}}{\Gamma(\rho+1)}\\ &+\left[\frac{189}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\tanh^{2}\left(\frac{\kappa-15}{2}\right)-\frac{27}{2}\ {\rm{sech}}^{6}\left(\frac{\kappa-15}{2}\right)\right]\frac{\vartheta^{2\rho}}{\Gamma(2\rho+1)}\\ &+\left[\frac{135}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\right)\tanh^{3}\left(\frac{\kappa-15}{2}\right)-\frac{63}{2}\ {\rm{sech}}^{4}\left(\frac{\kappa-15}{2}\tanh\left(\frac{\kappa-15}{2}\right)\right)\right]\\ &\frac{\Gamma(\rho+1)\vartheta^{2\rho-1}}{\Gamma(2\rho)}\\ &+\cdots. \end{align*}$

At $\rho = 1$ , we get in closed form the exact solution as

$\begin{equation} \mathbb{J}(\kappa, \vartheta) = 3\ {\rm{sech}}^{2}\left(\frac{\kappa-15-\vartheta}{2}\right). \end{equation}$

(5.27)

6. Results and discussion

In this section, we present the physical explanations for the presented problems. We note that our approaches can handle time fractional-order shock wave equations perfectly. It can be shown that $\mathbb{J}(\kappa, \vartheta)$ reduces with the growth of $\kappa$ and $\vartheta$ for $\rho = 0.25, 0.50, 0.75$ and $1$ in , which shows the surface solutions of $\mathbb{J}(\kappa, \vartheta)$ for various time fractional equations in Brownian. The analytical solution derived using the suggested approaches is shown in , together with the exact solution for various values of $\kappa$ and $\vartheta$ . also shows the surface solutions of $\mathbb{J}(\kappa, \vartheta)$ . shows the absolute error behavior of Example 5.2. Similarly, in , we show the behavior of the accurate and proposed method solutions at various fractional orders of $\rho$ having different values of $\kappa$ and $\vartheta$ . The figures and table show that the solution of the proposed method is in good contact with the exact solution.

Figure 1. The

$\mathbb{J}(\kappa, \vartheta)$ surface solutions with regard to

$\kappa$ and

$\vartheta$ for various

$\rho$ values within the domain

$-1\leq\kappa, \vartheta\leq1$ . (a) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 0.25$ . (b) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 0.50$ . (c) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 0.75$ . (d) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 1$ .

DownLoad: Full-Size Img PowerPoint

Figure 2. The

$\mathbb{J}(\kappa, \vartheta)$ surface solutions with regard to

$\kappa$ and

$\vartheta$ for various

$\rho$ values within the domain

$0\leq\kappa, \vartheta\leq10$ . (a) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 0.25$ . (b) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 0.50$ . (c) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 0.75$ . (d) Surface solution of the function

$\mathbb{J}(\kappa, \vartheta)$ at the value of

$\rho = 1$ .

DownLoad: Full-Size Img PowerPoint

Figure 3. The absolute error graph for

$\mathbb{J}(\kappa, \vartheta)$ of Example 5.2.

DownLoad: Full-Size Img PowerPoint

Table 1. Example 5.1: Exact, YTDM and HPYTM solution for

$\mathbb{J}(\kappa, \vartheta)$ at different fractional-order of

$\rho$ ,

${\kappa}$ and

$\vartheta$ .

$\vartheta$	$\kappa$	$\rho=0.6$	$\rho=0.8$	$\rho=1 (approx)$	$\rho=1 (approx)$	$\rho=1 (exact)$
	0.2	0.000004490	0.000004487	0.000004483	0.000004483	0.000004479
	0.4	0.000005481	0.000005479	0.000005476	0.000005476	0.000005470
0.01	0.6	0.000006693	0.000006691	0.000006688	0.000006688	0.000006681
	0.8	0.000008171	0.000008171	0.000008169	0.000008169	0.000008161
	1	0.000009982	0.000009980	0.000009978	0.000009978	0.000009968
	0.2	0.000004490	0.000004487	0.000004483	0.000004483	0.000004474
	0.4	0.000005482	0.000005478	0.000005476	0.000005476	0.000005465
0.02	0.6	0.000006693	0.000006690	0.000006688	0.000006688	0.000006675
	0.8	0.000008177	0.000008172	0.000008169	0.000008169	0.000008153
	1	0.000009987	0.000009982	0.000009978	0.000009978	0.000009958
	0.2	0.000004489	0.000004485	0.000004483	0.000004483	0.000004470
	0.4	0.000005489	0.00000583	0.000005476	0.000005476	0.000005459
0.03	0.6	0.000006693	0.000006690	0.000006688	0.000006688	0.000006668
	0.8	0.000008179	0.000008174	0.000008169	0.000008169	0.000008145
	1	0.000009989	0.000009982	0.000009978	0.000009978	0.000009948
	0.2	0.000004492	0.000004487	0.000004483	0.000004483	0.000004465
	0.4	0.000005487	0.000005481	0.000005476	0.000005476	0.000005454
0.04	0.6	0.000006699	0.000006691	0.000006688	0.000006688	0.000006661
	0.8	0.000008183	0.000008177	0.000008169	0.000008169	0.000008136
	1	0.000009999	0.000009983	0.000009978	0.000009978	0.000009938
	0.2	0.000004497	0.000004489	0.000004483	0.000004483	0.000004461
	0.4	0.000005490	0.000005479	0.000005476	0.000005476	0.000005448
0.05	0.6	0.000006697	0.000006691	0.000006688	0.000006688	0.000006655
	0.8	0.000008191	0.000008185	0.000008169	0.000008169	0.000008128
	1	0.000009997	0.000009988	0.000009978	0.000009978	0.000009928

| Show Table

DownLoad: CSV

7. Conclusions

The approximate and analytical solutions of the fractional-order nonlinear shock wave and wave equations are successfully obtained using the HPYTM and YTDM. The proposed methods are completed in two steps. First, we implement the Yang transform to simplify the proposed problems. After simplification, Adomian decomposition and homotopy perturbation methods are used to get the close form solution to the issues presented. The significance of fractional derivatives and the method for handling the recurrence relation are both shown in this study. The HPYTM and YTDM are used directly to generate the series solutions. Compared to previous methods examined in the literature, the current schemes exhibit more efficiency and require less computation. With the aid of MAPLE Software, all iterations were calculated. According to the solution graphs, this method can be applied to a wide range of nonlinear fractional differential equations in science and engineering. In subsequent research, these strategies could be expanded to address diverse nonlinear obstacle issues.

Funding

This work was supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project (No. PNURSP2022R183).

Acknowledgements

This work was supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project (No. PNURSP2022R183).

Conflict of interest

The authors declare that they have no competing interests.

References

[1]	T. Alladi, V. Kohli, V. Chamola, F. R. Yu, A deep learning-based misbehavior classification scheme for intrusion detection in cooperative intelligent transportation systems, Digit. Commun. Netw., 9 (2023), 1113–1122. https://doi.org/10.1016/j.dcan.2022.06.018 doi: 10.1016/j.dcan.2022.06.018
[2]	K. H. Park, E. Park, H. K. Kim, Unsupervised intrusion detection system for unmanned aerial vehicle with less labeling effort. In: Information security applications: 21st international conference, Springer, Cham. 2020, 45–58. https://doi.org/10.1007/978-3-030-65299-9_4
[3]	S. Jeong, E. Park, K. U. Seo, J. Do Yoo, H. K. Kim, MUVIDS: false MAVLink injection attack detection in communication for unmanned vehicles. In: Workshop on automotive and autonomous vehicle security (AutoSec), 2021. https://doi.org/10.14722/autosec.2021.23036
[4]	D. Basavaraj, S. Tayeb, Towards a lightweight intrusion detection framework for in-vehicle networks, J. Sensor Actuator Netw., 11 (2022), 6. https://doi.org/10.3390/jsan11010006 doi: 10.3390/jsan11010006
[5]	P. Mansourian, N. Zhang, A. Jaekel, M. Kneppers, Deep learning-based anomaly detection for connected autonomous vehicles using spatiotemporal information, IEEE T. Intell. Transp. Syst., 24 (2023), 16006–16017. https://doi.org/10.1109/TITS.2023.3286611 doi: 10.1109/TITS.2023.3286611
[6]	L. Yang, A. Moubayed, A. Shami, MTH-IDS: A multitiered hybrid intrusion detection system for internet of vehicles, IEEE Internet Things J., 9 (2022), 616–632. https://doi.org/10.1109/JIOT.2021.3084796 doi: 10.1109/JIOT.2021.3084796
[7]	N. Vanitha, P. Ganapathi, Traffic analysis of UAV networks using enhanced deep feed forward neural networks (EDFFNN). In: Handbook of research on machine and deep learning applications for cyber security. 2020. https://doi.org/10.4018/978-1-5225-9611-0.ch011
[8]	S. Aziz, M. T. Faiz, A. M. Adeniyi, K. H. Loo, K. N. Hasan, L. Xu, et al., Anomaly detection in the internet of vehicular networks using explainable neural networks (xnn), Mathematics, 10 (2022), 1267. https://doi.org/10.3390/math10081267 doi: 10.3390/math10081267
[9]	S. Anbalagan, G. Raja, S. Gurumoorthy, R. D. Suresh, K. Dev, ⅡDS: Intelligent intrusion detection system for sustainable development in autonomous vehicles, IEEE T. Intell. Transp. Syst., 24 (2023), 15866–15875. https://doi.org/10.1109/TITS.2023.3271768 doi: 10.1109/TITS.2023.3271768
[10]	R. Fotohi, E. Nazemi, F. S. Aliee, An agent-based self-protective method to secure communication between UAVs in unmanned aerial vehicle networks, Veh. Commun., 26 (2020), 100267. https://doi.org/10.1016/j.vehcom.2020.100267 doi: 10.1016/j.vehcom.2020.100267
[11]	F. Kateb, M. Ragab, Archimedes optimization with deep learning based aerial image classification for cybersecurity enabled UAV networks, Comput. Syst. Sci. Eng., 47 (2023), 2171–2185. https://doi.org/10.32604/csse.2023.039931 doi: 10.32604/csse.2023.039931
[12]	M. A. Sayeed, R. Kumar, V. Sharma, Safeguarding unmanned aerial systems: An approach for identifying malicious aerial nodes, IET Commun., 14 (2020), 3000–3012. https://doi.org/10.1049/iet-com.2020.0073 doi: 10.1049/iet-com.2020.0073
[13]	J. Tao, T. Han, R. Li, Deep-reinforcement-learning-based intrusion detection in aerial computing networks, IEEE Netw., 35 (2021), 66–72. https://doi.org/10.1109/MNET.011.2100068 doi: 10.1109/MNET.011.2100068
[14]	A. Masadeh, M. Alhafnawi, H. A. B. Salameh, A. Musa, Y. Jararweh, Reinforcement learning-based security/safety uav system for intrusion detection under dynamic and uncertain target movement, IEEE T. Eng. Manage., 2022, 1–11. https://doi.org/10.1109/TEM.2022.3165375 doi: 10.1109/TEM.2022.3165375
[15]	R. Kumar, P. Kumar, R. Tripathi, G. P. Gupta, T. R. Gadekallu, G. Srivastava, SP2F: A secured privacy-preserving framework for smart agricultural Unmanned Aerial Vehicles, Comput. Netw., 187 (2021), 107819. https://doi.org/10.1016/j.comnet.2021.107819 doi: 10.1016/j.comnet.2021.107819
[16]	L. Almutairi, R. Daniel, S. Khasimbee, E. L. Lydia, S. Acharya, H. Kim, Quantum dwarf mongoose optimization with ensemble deep learning based intrusion detection in cyber-physical systems, IEEE Access, 11 (2023), 66828–66837. https://doi.org/10.1109/ACCESS.2023.3287896 doi: 10.1109/ACCESS.2023.3287896
[17]	I. U. Khan, A. Abdollahi, M. A. Khan, I. Uddin, I. Ullah, Securing against DoS/DDoS attacks in internet of flying things using experience-based deep learning algorithm, 2021. (Preprint) https://doi.org/10.21203/rs.3.rs-271920/v1
[18]	Q. Abu Al-Haija, A. Al Badawi, High-performance intrusion detection system for networked UAVs via deep learning, Neural Comput. Appl., 34 (2022), 10885–10900. https://doi.org/10.1007/s00521-022-07015-9 doi: 10.1007/s00521-022-07015-9
[19]	M. S. Minu, R. Aroul Canessane, S. S. Subashka Ramesh, Optimal squeeze net with deep neural network-based arial image classification model in Unmanned Aerial Vehicles, Traitement du Signal, 39 (2022), 275–281. https://doi.org/10.18280/ts.390128 doi: 10.18280/ts.390128
[20]	J. Tian, B Wang, R. Guo, Z. Wang, K. Cao, X. Wang, Adversarial attacks and defenses for deep-learning-based unmanned aerial vehicles, IEEE Internet Things J., 9 (2021), 22399–22409. https://doi.org/10.1109/JIOT.2021.3111024 doi: 10.1109/JIOT.2021.3111024
[21]	V. F. S. Francelin, J. Daniel, S. Velliangiri, Intelligent agent and optimization‐based deep residual network to secure communication in UAV network, Int. J. Intell. Syst., 37 (2022), 5508–5529. https://doi.org/10.1002/int.22800 doi: 10.1002/int.22800
[22]	H. Zhang, J. Xue, Q. Wang, Y. Li, A security optimization scheme for data security transmission in UAV-assisted edge networks based on federal learning, Ad Hoc Netw., 150 (2023), 103277. https://doi.org/10.1016/j.adhoc.2023.103277 doi: 10.1016/j.adhoc.2023.103277
[23]	A. M. Elshewey, M. Y. Shams, N. El-Rashidy, A. M. Elhady, S. M. Shohieb, Z. Tarek, Bayesian optimization with support vector machine model for Parkinson disease classification, Sensors, 23 (2023), 2085. https://doi.org/10.3390/s23042085 doi: 10.3390/s23042085
[24]	M. Stankovic, J. Gavrilovic, D. Jovanovic, M. Zivkovic, M. Antonijevic, N. Bacanin, et al., Tuning multi-layer perceptron by hybridized arithmetic optimization algorithm for healthcare 4.0, Procedia Comput. Sci., 215 (2022), 51–60. https://doi.org/10.1016/j.procs.2022.12.006 doi: 10.1016/j.procs.2022.12.006
[25]	H. Al-Khazraji, A. R. Nasser, A. M. Hasan, A. K. Al Mhdawi, H. Al-Raweshidy, A. J. Humaidi, Aircraft engines remaining useful life prediction based on a hybrid model of autoencoder and deep belief network, IEEE Access, 10 (2022), 82156–82163. https://doi.org/10.1109/ACCESS.2022.3188681 doi: 10.1109/ACCESS.2022.3188681
[26]	P. Krishnadoss, V. K. Poornachary, P. Krishnamoorthy, L. Shanmugam, Improvised seagull optimization algorithm for scheduling tasks in heterogeneous cloud environment, Comput. Mater. Con., 74 (2023), 2461–2478. https://doi.org/10.32604/cmc.2023.031614 doi: 10.32604/cmc.2023.031614
[27]	N. Moustafa, A new distributed architecture for evaluating AI-based security systems at the edge: Network TON_IoT datasets, Sustain. Cities Soc., 72 (2021), 102994. https://doi.org/10.1016/j.scs.2021.102994 doi: 10.1016/j.scs.2021.102994
[28]	R. A. Ramadan, A. H. Emara, M. Al-Sarem, M. Elhamahmy, Internet of drones intrusion detection using deep learning, Electronics, 10 (2021), 2633. https://doi.org/10.3390/electronics10212633 doi: 10.3390/electronics10212633
[29]	L. Kou, S. Ding, T. Wu, W. Dong, Y. Yin, An intrusion detection model for drone communication network in SDN environment, Drones, 6 (2022), 342. https://doi.org/10.3390/drones6110342 doi: 10.3390/drones6110342

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)