Faiza Makhdoom*, Jamshaid Ul Rahman**, Naveed Anjum***

Periodicity:April - June'2024

DOI : https://doi.org/10.26634/jme.14.2.21191

* Abdus Salam School of Mathematical Sciences, Government College University, Lahore, Pakistan.

** School of Mathematical Sciences, Jiangsu University, Zhenjiang, China.

*** Department of Mathematics, Government College University, Faisalabad, Pakistan.

DOI : https://doi.org/10.26634/jme.14.2.21191

Nonlinear differential equations play a pivotal role in modeling various physical phenomena, capturing their oscillatory behaviors. Numerous analytic and numerical methods have been developed to obtain precise or approximate solutions for nonlinear dynamics. This study introduces a novel approach utilizing neural network strategies, known for their computational flexibility. This study proposed a novel architecture for deep neural networks that is intended to simulate the nonlinear oscillations of two systems. It has been modified to include an oscillatory activation function called the amplifying sine unit. This study compares the results from our customized neural networks with those from the conventional stable and reliable numerical technique of the Runge-Kutta method of order four. Remarkably, there is striking agreement between the outcomes of the two methods, highlighting the ability of deep neural networks to identify nonlinear dynamical behaviors without requiring explicit conversion of mathematical models into an equation system.

[1]. Agarap, A. F. (2018). Deep learning using rectified linear units (relu). arXiv preprint arXiv:1803.08375.

[5]. Anjum, N., & Ain, Q. T. (2020). Application of He's fractional derivative and fractional complex transform for time fractional Camassa-Holm equation. Thermal Science, 24(5 Part A), 3023-3030.

[13]. Chauhan, V., & Srivastava, P. K. (2019). Computational techniques based on Runge-Kutta method of various order and type for solving differential equations. International Journal of Mathematical, Engineering and Management Sciences, 4(2), 375-386.

[14]. Chen, M., Xue, H., & Cai, D. (2019). Domain adaptation for semantic segmentation with maximum squares loss. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 2090-2099).

[34]. Rahman, J. U., Makhdoom, F., Rashid, U., Lu, D., & Akgül, A. (2024b). An Oscillatory Deep Neural Network for Coupled Electrical Circuits. Research Square.

[35]. Raissi, M. (2018). Deep hidden physics models: Deep learning of nonlinear partial differential equations. Journal of Machine Learning Research, 19(25), 1-24.

[36]. Rehman, S., Hussain, A., Rahman, J. U., Anjum, N., & Munir, T. (2022). Modified Laplace based variational iteration method for the mechanical vibrations and its applications. Acta Mechanica et Automatica, 16(2), 98-102.

[41]. Sharma, S., Sharma, S., & Athaiya, A. (2017). Activation functions in neural networks. Towards Data Science, 6(12), 310-316.

[45]. Taylanov, N. A., Urinov, S. X. O. G. L., & Abdiev, J. M.
O. G. L. (2022). A fourth-order runge-kutta method for numerical solution of the Kuramoto-Sivashinsky equation. Eurasian Scientific Herald, 7, 58–61.

[53]. ul Rahman, J., Mohyuddin, M. R., Anjum, N., & Zahoor, S. (2015). Mathematical modelling & simulation of mixing of salt in 3-interconnected tanks. Journal of Advances in Civil Engineering, 1(1), 1-6.