Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations
This paper deals with the drawback of the semi-group properties in variable order fractional mixed Volterra-Fredholm integro-differential equations (VO-FVFIDEs) under Caputo derivative operator. The variable order of the equation is converted to piecewise constant functions by partition it into sub-...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2025
|
| Online Access: | http://journalarticle.ukm.my/26414/1/Paper_6%20-.pdf http://journalarticle.ukm.my/26414/ https://www.ukm.my/jqma/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1855615327317000192 |
|---|---|
| author | Alsa’di, Kawthar Nik Mohd Asri Nik Long, |
| author_facet | Alsa’di, Kawthar Nik Mohd Asri Nik Long, |
| author_sort | Alsa’di, Kawthar |
| building | Tun Sri Lanang Library |
| collection | Institutional Repository |
| content_provider | Universiti Kebangsaan Malaysia |
| content_source | UKM Journal Article Repository |
| continent | Asia |
| country | Malaysia |
| description | This paper deals with the drawback of the semi-group properties in variable order fractional mixed Volterra-Fredholm integro-differential equations (VO-FVFIDEs) under Caputo derivative operator. The variable order of the equation is converted to piecewise constant functions by partition it into sub-intervals. The existence and uniqueness of solutions are investigated. A novel technique using Bernstein Neural Network (BernsteinNN) method is proposed to obtain the approximate solution for the FVFIDEs, which used the basis of Bernstein polynomials instead of the activation function in the artificial neural network method. The loss function is developed by adding the L2 regularization for parameter terms and the hyper-parameter λ to ensure the stability of training process and to control the regularization strength, respectively. Adam optimization approach is applied to training the neural networks and the model performance is computed using the mean square error. The validity of the presented method is demonstrated through the presented example. |
| format | Article |
| id | my-ukm.journal.26414 |
| institution | Universiti Kebangsaan Malaysia |
| language | en |
| publishDate | 2025 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| record_format | eprints |
| spelling | my-ukm.journal.264142026-01-12T09:11:29Z http://journalarticle.ukm.my/26414/ Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations Alsa’di, Kawthar Nik Mohd Asri Nik Long, This paper deals with the drawback of the semi-group properties in variable order fractional mixed Volterra-Fredholm integro-differential equations (VO-FVFIDEs) under Caputo derivative operator. The variable order of the equation is converted to piecewise constant functions by partition it into sub-intervals. The existence and uniqueness of solutions are investigated. A novel technique using Bernstein Neural Network (BernsteinNN) method is proposed to obtain the approximate solution for the FVFIDEs, which used the basis of Bernstein polynomials instead of the activation function in the artificial neural network method. The loss function is developed by adding the L2 regularization for parameter terms and the hyper-parameter λ to ensure the stability of training process and to control the regularization strength, respectively. Adam optimization approach is applied to training the neural networks and the model performance is computed using the mean square error. The validity of the presented method is demonstrated through the presented example. Penerbit Universiti Kebangsaan Malaysia 2025-09 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/26414/1/Paper_6%20-.pdf Alsa’di, Kawthar and Nik Mohd Asri Nik Long, (2025) Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations. Journal of Quality Measurement and Analysis, 21 (3). pp. 99-119. ISSN 2600-8602 https://www.ukm.my/jqma/ |
| spellingShingle | Alsa’di, Kawthar Nik Mohd Asri Nik Long, Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations |
| title | Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations |
| title_full | Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations |
| title_fullStr | Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations |
| title_full_unstemmed | Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations |
| title_short | Bernstein neural networks method for solving variable order fractional mixed Volterra-Fredholm Integro-Differential equations |
| title_sort | bernstein neural networks method for solving variable order fractional mixed volterra-fredholm integro-differential equations |
| url | http://journalarticle.ukm.my/26414/1/Paper_6%20-.pdf http://journalarticle.ukm.my/26414/ https://www.ukm.my/jqma/ |
| url_provider | http://journalarticle.ukm.my/ |