The current study aims to present a swarm-optimized technique for the numerical treatment of dengue fever non-linear model. The model is composed of the coupled nonlinear system comprising the susceptible, infected, and recovered compartments. The system is transformed into an unsupervised single layer feed-forward artificial neural network with a Mexican hat wavelet activation function in the hidden layer. The unknowns of the neural network is optimized with particle swarm optimization as an efficient global search aided by the effective local search technique based on sequential quadratic programming. The presented results are compared with state of art Runge-Kutta method and other modern reported techniques on various performance indicators like absolute error, mean average deviation, global absolute error, global mean average deviation, convergence, and computational complexity. Comprehensive Monte Carlo simulations and their statistical analysis are presented to ensure accuracy, consistency in convergence, and computational complexity in terms of execution time. It is observed that the proposed scheme is accurate, reliable, convergent, and computationally viable in treating the nonlinear coupled system under consideration.
Controlling epidemiology with stochastic intelligence systems, particularly those based on feed-forward artificial neural networks (ANNs), has advanced significantly in recent years. These techniques provide an effective framework for studying the dynamics of epidemic diseases while also addressing the intricacy and nonlinearity of the linked epidemic model based on the differential system. With the computational efficiency of a single-layer feed-forward artificial neural network, the current study designs a swarming-optimized neuro-heuristic technique to solve the nonlinear system based on Leptospirosis disease (LD). The proposed strategies utilize the computational efficiency of Mexican Hat Wavelet (MHW) modeling, i.e. (MHW-ANNs-PSO-SQP), in addition to the optimization process of global search Particle Swarm Optimisation (PSO), which is aided by the efficient local search Sequential Quadratic Programming (SQP). A zoonotic disease called LD spreads from animals to humans and kills them. The mathematical model of LD is based on the conventional susceptible-infected-recovered (SIR) model, which is used to solve the dynamics of the disease's spread. The differential coupled system has been used to solve the LD nonlinear epidemic model by developing an unsupervised error-based merit function. To confirm the accuracy, the outcomes are contrasted with the well-known Runge-Kutta (RK) numerical and genetic algorithms hybrid with active set algorithms, such as the GA-ASA-based ANN solver. Additionally, the correctness and reliability of the MHW-ANNs-PSO-SQP are verified using absolute error and comprehensive statistical analysis employing many statistical operators. Furthermore, the complexity of the suggested approach is examined using the Mean Execution Time. The AE values for mean and best cases are in the range 10− 11 to 10− 14 and 10− 14 to 10− 15 respectively, while the MSE, MAD, and TIC values are in the range 10− 7 to 10− 11, 10− 7 to 10− 11 and 10− 6 to 10− 10 respectively. The results demonstrate that the developed scheme solves the LD model accurately and precisely. The developed scheme is consistent, stable, and reliable.