4.7 Article

Novel trial functions and rogue waves of generalized breaking soliton equation via bilinear neural network method

Journal

CHAOS SOLITONS & FRACTALS
Volume 154, Issue -, Pages -

Publisher

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.chaos.2021.111692

Keywords

Symbolic computation; BNNM; Physical informed neural networks; (3+1)-Dimensional breaking soliton equation

Funding

  1. National Natural Science Foundation of China [12061054, 61877007, 12161061]
  2. Fundamental Research Funds for the Central Universities [DUT20GJ205]
  3. Special Funds for the Local Science and Technology Development of the Central Government [2020ZY0014]
  4. Natural Science Foundation of Inner Mongolia [2021MS01022]
  5. Program for Young Talents of Science and Technology in Universities of Inner Mongolia [NJYT-19-B21]
  6. Inner Mongolia Talent Development Fund

Ask authors/readers for more resources

In this work, new test functions are constructed by setting generalized activation functions in different artificial network models. The explicit solution of a generalized breaking soliton equation is solved using the bilinear neural network method. Rogue waves of the generalized breaking soliton equation are obtained using symbolic computing technology and displayed intuitively with the help of Maple software.
In this work, some new test functions are constructed by setting generalized activation functions in different artificial network models. Bilinear neural network method is introduced to solve the explicit solution of a generalized breaking soliton equation. Rogue waves of generalized breaking soliton equation are obtained by symbolic computing technology and displayed intuitively with the help of Maple software. (C) 2021 Elsevier Ltd. All rights reserved.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Engineering, Multidisciplinary

Diversity of interaction phenomenon, cross-kink wave, and the bright-dark solitons for the (3+1)-dimensional Kadomtsev-Petviashvili-Boussinesq-like equation

MeiYu Li, Sudao Bilige, Run-Fa Zhang, Lihui Han

Summary: In this paper, the (3 + 1)-dimensional Kadomtsev-Petviashvili-Boussinesq-like equation is used to derive exact solutions, including interaction wave solitons, cross-kink wave solitons, and bright-dark solitons, under certain constraints using the generalized bilinear form and the symbolic computation Maple. The accuracy of the solutions is ensured by a special selection of parameters and the visualization of dynamics through three-dimensional, density, and contour graphs. These solutions have applications in studying certain phenomena in physics.

INTERNATIONAL JOURNAL OF NONLINEAR SCIENCES AND NUMERICAL SIMULATION (2022)

Article Physics, Applied

Multiple exact solutions for the dimensionally reduced p-gBKP equation via bilinear neural network method

Run-Fa Zhang, Ming-Chu Li, Tao Fang, Fu-Chang Zheng, Sudao Bilige

Summary: In this paper, new trial functions are constructed based on the bilinear neural networks method, and multiple solutions of the dimensionally reduced p-generalized Burgers-Kadomtsev-Petviashvili equation are solved. The dynamic properties of the solutions are analyzed with appropriate parameters and different activated functions.

MODERN PHYSICS LETTERS B (2022)

Article Engineering, Mechanical

Bilinear residual network method for solving the exactly explicit solutions of nonlinear evolution equations

Run-Fa Zhang, Ming-Chu Li

Summary: In this study, a bilinear residual network method is proposed to solve nonlinear evolution equations. The method reduces the complexity of the model and provides more interactive results. The exact analytical solution for the Caudrey-Dodd-Gibbon-Kotera-Sawada-like equation is obtained using the steps of solving through the residual network. Characteristic plots and dynamic analysis of these rogue waves are given.

NONLINEAR DYNAMICS (2022)

Article Computer Science, Hardware & Architecture

Deep learning-based early stage detection (DL-ESD) for routing attacks in Internet of Things networks

Mohammed Albishari, Mingchu Li, Runfa Zhang, Esmail Almosharea

Summary: This paper proposes a deep learning-based early stage detection scheme to enhance the detection capability of routing attacks in IoT. The experiments demonstrate its effectiveness and superior performance in terms of prediction accuracy and precision.

JOURNAL OF SUPERCOMPUTING (2023)

Article Engineering, Mechanical

The interference wave and the bright and dark soliton for two integro-differential equation by using BNNM

Run-Fa Zhang, Ming-Chu Li, Amina Cherraf, Shashank Reddy Vadyala

Summary: In this work, the nonlinear property of neural network is utilized to investigate interference wave and bright and dark soliton solutions. The generalized broken soliton-like equation is derived through the generalized bilinear method. Three neural network models are proposed for accurately fitting explicit solutions of the generalized broken soliton-like equations and Boiti-Leon-Manna-Pempinelli-like equation. Interference wave solutions and bright and dark soliton solutions are obtained using the bilinear neural network method, and are visualized through three-dimensional plots and density plots.

NONLINEAR DYNAMICS (2023)

Article Engineering, Industrial

A risk-averse tri-level stochastic model for locating and recovering facilities against attacks in an uncertain environment

Qing Li, Mingchu Li, Yuan Tian, Jianyuan Gan

Summary: This paper presents a tri-level stochastic game-theoretic model that considers risk-averse strategies between a defender and an attacker in supply networks. The model incorporates uncertainty in facility capacity and attack effect, using Conditional-Value-at-Risk (CVaR) to control the risk associated with extreme scenarios. The goal of the model is to minimize the CVaR cost of the defender and locate facilities with capacity backups at different levels for recovery against worst-case attacks.

RELIABILITY ENGINEERING & SYSTEM SAFETY (2023)

Article Engineering, Mechanical

Periodic bright-dark soliton, breather-like wave and rogue wave solutions to a (sic)p-GBS equation in (3+1)-dimensions

Litao Gai, Youhua Qian, Yupeng Qin, Runfa Zhang

Summary: This paper proposes a trilinear neural network method based on the trilinear form of a (3+1)-dimensional p-GBS equation, which can be used to construct new exact traveling wave solutions. By setting the hidden neurons in three types of tensor functions to specific functions, the paper successfully obtains a class of periodic bright-dark soliton solutions, two types of breather-like wave solutions, and three types of rogue wave solutions for the p-GBS equation. The dynamic characteristics are explained through the 3D and density graphs of these solutions.

NONLINEAR DYNAMICS (2023)

Article Engineering, Mechanical

Fission and annihilation phenomena of breather/rogue waves and interaction phenomena on nonconstant backgrounds for two KP equations

Na Lv, Yichao Yue, Runfa Zhang, Xuegang Yuan, Ran Wang

Summary: In this paper, the authors investigate various nonlinear phenomena of two Kadomtsev-Petviashvili (KP) equations using the bilinear neural network method. They present the fission and annihilation phenomena of breather waves and rogue waves on non-zero backgrounds of a (3+1)-dimensional KP equation, and obtain three interaction solutions on nonconstant backgrounds of a (2+1)-dimensional KP equation with variable coefficients. The authors also analyze the dynamic characteristics and evolution behaviors of the obtained solutions through three-dimensional animations. This study demonstrates the effectiveness of the bilinear neural network method combined with symmetry analysis in solving high-dimensional differential equations with constant and variable coefficients.

NONLINEAR DYNAMICS (2023)

Article Automation & Control Systems

Neural network-based analytical solver for Fokker-Planck equation

Yang Zhang, Run-Fa Zhang, Ka-Veng Yuen

Summary: This paper proposes a neural network-based method for obtaining the analytical solution of the Fokker-Planck equation. The method uses the explicit model of neural networks as the trial function and converts the equation solving into the calculation of weights and biases.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2023)

Proceedings Paper Computer Science, Artificial Intelligence

Cooperative Offloading Based on Online Auction for Mobile Edge Computing

Xiao Zheng, Syed Bilal Hussain Shah, Liqaa Nawaf, Omer F. Rana, Yuanyuan Zhu, Jianyuan Gan

Summary: An online auction-based strategy is proposed in the paper, allowing users and mobile devices to interact dynamically with the system, optimizing the long-term utility effectively. Experimental results demonstrate the effectiveness of this strategy.

WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS, PT III (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Aerial-Aerial-Ground Computation Offloading Using High Altitude Aerial Vehicle and Mini-drones

Esmail Almosharea, Mingchu Li, Runfa Zhang, Mohammed Albishari, Ikhlas Al-Hammadi, Gehad Abdullah Amran, Ebraheem Farea

Summary: Unmanned Aerial Vehicles (UAV) supported by 5G networks can provide aerial-aerial/aerial-ground computing services to remote and isolated areas at a low cost. This study proposes an aerial-aerialground network (AAGN) computing architecture using High Altitude Unmanned Aerial Vehicle (HAU) and Mini-Drones (MDs) based on Mobile Edge Computing (MEC) services. The proposed framework aims to reduce energy consumption and processing delay, optimize HAU mobility and MDs scheduling, and enhance task offloading efficiency.

WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS, PT III (2022)

Article Physics, Multidisciplinary

Evolutionary behavior of various wave solutions of the (2+1)-dimensional Sharma-Tasso-Olver equation

Y. Y. Feng, S. D. Bilige, R. F. Zhang

Summary: This paper studies the multiple rogue wave solutions of the (2+1)-dimensional Sharma-Tasso-Olver equation using the bilinear neural network method. Various types of solutions were obtained using the introduced NMM and 3-2-4 NNM models, with detailed analysis of rogue wave solutions centered at the origin or with a fixed center. The results significantly enrich the exact solutions of the equation and enhance our understanding of nonlinear dynamic systems.

INDIAN JOURNAL OF PHYSICS (2022)

Article Mathematics, Interdisciplinary Applications

Stochastic optimal control and piecewise parameterization and optimization method for inventory control system improvement

Bo Li, Tian Huang

Summary: This paper proposes an approximate optimal strategy based on a piecewise parameterization and optimization (PPAO) method for solving optimization problems in stochastic control systems. The method obtains a piecewise parameter control by solving first-order differential equations, which simplifies the control form and ensures a small model error.

CHAOS SOLITONS & FRACTALS (2024)

Article Mathematics, Interdisciplinary Applications

Consensus formation among mobile agents in networks of heterogeneous interaction venues

Guram Mikaberidze, Sayantan Nag Chowdhury, Alan Hastings, Raissa M. D'Souza

Summary: This study explores the collective behavior of interacting entities, focusing on the co-evolution of diverse mobile agents in a heterogeneous environment network. Increasing agent density, introducing heterogeneity, and designing the network structure intelligently can promote agent cohesion.

CHAOS SOLITONS & FRACTALS (2024)

Article Mathematics, Interdisciplinary Applications

Development of a contact force model with a fluid damping factor for immersed collision events

Gengxiang Wang, Yang Liu, Caishan Liu

Summary: This investigation studies the impact behavior of a contact body in a fluidic environment. A dissipated coefficient is introduced to describe the energy dissipation caused by hydrodynamic forces. A new fluid damping factor is derived to depict the coupling between liquid and solid, as well as the coupling between solid and solid. A new coefficient of restitution (CoR) is proposed to determine the actual physical impact. A new contact force model with a fluid damping factor tailored for immersed collision events is proposed.

CHAOS SOLITONS & FRACTALS (2024)