An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems

Recently, one artificial intelligence technique, known as artificial neural network (ANN), has brought advanced development to the arena of mathematical research. It competes effectively with other traditional methods in providing accurate solutions for fractional differential equations (FDEs). This...

Full description

Bibliographic Details
Main Authors: Admon, Mohd Rashid, Senu, Norazak, Ahmadian, Ali, Abdul Majid, Zanariah
Format: Article
Published: Springer Nature 2024
Online Access:http://psasir.upm.edu.my/id/eprint/113731/
_version_ 1848866305998848000
author Admon, Mohd Rashid
Senu, Norazak
Ahmadian, Ali
Abdul Majid, Zanariah
author_facet Admon, Mohd Rashid
Senu, Norazak
Ahmadian, Ali
Abdul Majid, Zanariah
author_sort Admon, Mohd Rashid
building UPM Institutional Repository
collection Online Access
description Recently, one artificial intelligence technique, known as artificial neural network (ANN), has brought advanced development to the arena of mathematical research. It competes effectively with other traditional methods in providing accurate solutions for fractional differential equations (FDEs). This work aims to implement a feedforward ANN with two hidden layers to solve nonlinear systems based on the fractional Riccati differential equation (FRDE). The network parameters are trained using the Adam optimization method with the aid of automatic differentiation. A vectorization algorithm is designated for the selected step to make the computation process more efficient. Two different initial value problems in integer-order derivatives and fractional-order derivatives are discussed. Numerical results demonstrate that the proposed method not only closely matches the exact solutions and reference solutions but also is more accurate than other existing methods. © The Author(s) under exclusive licence to Sociedade Brasileira de Matemática Aplicada e Computacional 2024.
first_indexed 2025-11-15T14:18:30Z
format Article
id upm-113731
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T14:18:30Z
publishDate 2024
publisher Springer Nature
recordtype eprints
repository_type Digital Repository
spelling upm-1137312025-01-15T07:56:07Z http://psasir.upm.edu.my/id/eprint/113731/ An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems Admon, Mohd Rashid Senu, Norazak Ahmadian, Ali Abdul Majid, Zanariah Recently, one artificial intelligence technique, known as artificial neural network (ANN), has brought advanced development to the arena of mathematical research. It competes effectively with other traditional methods in providing accurate solutions for fractional differential equations (FDEs). This work aims to implement a feedforward ANN with two hidden layers to solve nonlinear systems based on the fractional Riccati differential equation (FRDE). The network parameters are trained using the Adam optimization method with the aid of automatic differentiation. A vectorization algorithm is designated for the selected step to make the computation process more efficient. Two different initial value problems in integer-order derivatives and fractional-order derivatives are discussed. Numerical results demonstrate that the proposed method not only closely matches the exact solutions and reference solutions but also is more accurate than other existing methods. © The Author(s) under exclusive licence to Sociedade Brasileira de Matemática Aplicada e Computacional 2024. Springer Nature 2024 Article PeerReviewed Admon, Mohd Rashid and Senu, Norazak and Ahmadian, Ali and Abdul Majid, Zanariah (2024) An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems. Computational and Applied Mathematics, 43 (6). art. no. 362. ISSN 2238-3603; eISSN: 1807-0302 https://link.springer.com/article/10.1007/s40314-024-02865-6?error=cookies_not_supported&code=0cf46fe4-c73d-4503-babd-00f86730c80d 10.1007/s40314-024-02865-6
spellingShingle Admon, Mohd Rashid
Senu, Norazak
Ahmadian, Ali
Abdul Majid, Zanariah
An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems
title An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems
title_full An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems
title_fullStr An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems
title_full_unstemmed An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems
title_short An advanced scheme based on Artificial Intelligence technique for solving nonlinear Riccati systems
title_sort advanced scheme based on artificial intelligence technique for solving nonlinear riccati systems
url http://psasir.upm.edu.my/id/eprint/113731/
http://psasir.upm.edu.my/id/eprint/113731/
http://psasir.upm.edu.my/id/eprint/113731/