DESIGN OF NEURO-SWARMING HEURISTIC SOLVER FOR MULTI-PANTOGRAPH SINGULAR DELAY DIFFERENTIAL EQUATION

This research work is to design a neural-swarming heuristic procedure for numerical investigations of Singular Multi-Pantograph Delay Differential (SMP-DD) equation by applying the function approximation aptitude of Artificial Neural Networks (ANNs) optimized efficient swarming mechanism based on Particle Swarm Optimization (PSO) integrated with convex optimization with Active Set (AS) algorithm for rapid refinements, named as ANN-PSO-AS. A merit function (MF) on mean squared error sense is designed by using the differential ANN models and boundary condition. The optimization of this MF is executed with the global PSO and local search AS approaches. The planned ANN-PSO-AS approach is instigated for three different SMP-DD model-based equations. The assessment with available standard results relieved the effectiveness, robustness and precision that is further authenticated through statistical investigations of Variance Account For, Root Mean Squared Error, Semi-Interquartile Range and Theil's inequality coefficient performances.

Automated summary

This research introduces the ANN-PSO-AS method, which utilizes the function approximation ability of Artificial Neural Networks and the optimized mechanism of Particle Swarm Optimization to solve the Singular Multi-Pantograph Delay Differential equation. The method demonstrates effectiveness, robustness, and precision in various numerical investigations.