Design of Gudermannian Neuroswarming to solve the singular Emden–Fowler nonlinear model numerically
Nonlinear Dynamics, cilt.106, sa.4, ss.3199-3214, 2021 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 106 Sayı: 4
- Basım Tarihi: 2021
- Doi Numarası: 10.1007/s11071-021-06901-6
- Dergi Adı: Nonlinear Dynamics
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Aerospace Database, Applied Science & Technology Source, Communication Abstracts, Compendex, Computer & Applied Sciences, INSPEC, Metadex, zbMATH, Civil Engineering Abstracts
- Sayfa Sayıları: ss.3199-3214
- Anahtar Kelimeler: Active-set scheme, Emden–Fowler, Gudermannian function, Particle swarm optimization, Statistical analysis
- Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
- Trakya Üniversitesi Adresli: Evet
Özet
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.