Design of Gudermannian Neuroswarming to solve the singular Emden–Fowler nonlinear model numerically
- Zulqurnain Sabir(corresponding author),
- Muhammad Asif Zahoor Raja,
- Dumitru Baleanu,
- ,
- Muhammad Shoaib
- Hazara University,
- National Yunlin University of Science and Technology,
- Cankaya University,
- Insitute of Space Science,
- Trakya University,
- COMSATS University Islamabad
Open access
Abstract
The current investigation is related to the design of novel integrated neuroswarming heuristic paradigm using Gudermannian artificial neural networks (GANNs) optimized with particle swarm optimization (PSO) aid with active-set (AS) algorithm, i.e., GANN-PSOAS, for solving the nonlinear third-order Emden–Fowler model (NTO-EFM) involving single as well as multiple singularities. The Gudermannian activation function is exploited to construct the GANNs-based differential mapping for NTO-EFMs, and these networks are arbitrary integrated to formulate the fitness function of the system. An objective function is optimized using hybrid heuristics of PSO with AS, i.e., PSOAS, for finding the weights of GANN. The correctness, effectiveness and robustness of the designed GANN-PSOAS are verified through comparison with the exact solutions on three problems of NTO-EFMs. The assessments on statistical observations demonstrate the performance on different measures for the accuracy, consistency and stability of the proposed GANN-PSOAS solver.
Research Output Information
Output type
Original language
EnglishPages from-to (Number of pages)
Pages 3199-3214 (16 pages)Journal (Volume, Issue Number)
Nonlinear Dynamics (Volume 106, Issue 4)Publication milestones
- Published - 12/2021
Publication status
ISSN
0924-090XPublication IDs
- Scopus: 85118858995
