Enhancing Efficiency of Affordable Sensors: An Advanced Neural Network Paradigm with Metaheuristic Optimization Algorithms

Abstract

This project report gives a thorough investigation into how combining ANN models with metaheuristic optimization methods might improve the performance of low-cost sensors. Although low-cost sensors have a wide range of uses, they frequently lack the accuracy and dependability of their more expensive counterparts. The strength of ANN models is combined with optimization approaches in a novel way to address this restriction. In order to optimize the parameters and design of the neural network, the project focuses on creating an ANN framework that uses metaheuristic techniques like Particle Swarm Optimization (PSO), Osprey Optimization Algorithm(OOA), Driving Training Based Optimization(DTBO), Salp Swarm Algorithm(SSA),Harris Hawk Optimization (HHO. By significantly enhancing the accuracy, precision, and robustness of low-cost sensors, this combination intends to enhance their overall performance.