A Bilinear Neural Network Framework for the Fourth-Order Ablowitz-Kaup-Newell-Segur Equation and Physics-Informed Wireless MCS Prediction

This paper presents a novel hybrid analytical–computational framework based on the bilinear neural network method (BNNM) for solving the fourth-order Ablowitz–Kaup–Newell–Segur (4AKNS) water wave equation with perturbation. By employing Hirota's bilinear transformation, the original nonlinear partial differential equation is systematically converted into a bilinear form, providing the construction of a test function representation. Instead of directly approximating the physical solution, the proposed approach learns the test function using a feedforward neural network combined with automatic differentiation. To enhance training stability and convergence, a softmax-based adaptive weighting strategy is incorporated into the loss function, allowing the model to focus on low-residual regions. Several analytical solution structures, including kink waves, soliton–periodic interactions, and periodic waves, are constructed and validated through multiple case studies. Numerical experiments demonstrate that the proposed method achieves stable convergence, high accuracy, and strong robustness across diverse solution types. The results confirm that the bilinear neural network framework is an effective and flexible tool for solving nonlinear integrable systems, providing both accurate approximations and the ability to maintain complex wave dynamics.

Authors

Institutions

Publication Details

Journal
International Journal of Analysis and Applications
Published
2026-11-16
DOI
https://doi.org/10.28924/2291-8639-24-2026-384
Primary Topic
Nonlinear Waves and Solitons
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Bilinear Neural Network Framework for the Fourth-Order Ablowitz-Kaup-Newell-Segur Equation and Physics-Informed Wireless MCS Prediction

Chaiyod Kamthorncharoen, Sekson Sirisubtawee, Surattana Sungnul, Chukiat Saksurakan et al.
7 links
International Journal of Analysis and Applications
Nonlinear Waves and Solitons
article

A Bilinear Neural Network Framework for the Fourth-Order Ablowitz-Kaup-Newell-Segur Equation and Physics-Informed Wireless MCS Prediction

Chaiyod Kamthorncharoen, Sekson Sirisubtawee, Surattana Sungnul, Chukiat Saksurakan, Nguyen Minh Tuan
article en

Abstract

This paper presents a novel hybrid analytical–computational framework based on the bilinear neural network method (BNNM) for solving the fourth-order Ablowitz–Kaup–Newell–Segur (4AKNS) water wave equation with perturbation. By employing Hirota's bilinear transformation, the original nonlinear partial differential equation is systematically converted into a bilinear form, providing the construction of a test function representation. Instead of directly approximating the physical solution, the proposed approach learns the test function using a feedforward neural network combined with automatic differentiation. To enhance training stability and convergence, a softmax-based adaptive weighting strategy is incorporated into the loss function, allowing the model to focus on low-residual regions. Several analytical solution structures, including kink waves, soliton–periodic interactions, and periodic waves, are constructed and validated through multiple case studies. Numerical experiments demonstrate that the proposed method achieves stable convergence, high accuracy, and strong robustness across diverse solution types. The results confirm that the bilinear neural network framework is an effective and flexible tool for solving nonlinear integrable systems, providing both accurate approximations and the ability to maintain complex wave dynamics.

International Journal of Analysis and ApplicationsVol. 24
Centre of Excellence in Mathematics (TH), Ministry of Higher Education, Science, Research and Innovation (TH), King Mongkut's University of Technology North Bangkok (TH)
King Mongkut's University of Technology North Bangkok
Nonlinear Waves and Solitons
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon