Heuristic optimization using gene navigation with the gravitational search algorithm [articol]

Abstract

Automation is the effective model to reduce the human workload and to increase the accuracy of working process. It is mainly involved by utilizing the architecture of the Artificial Intelligence (AI). AI is primarily developed by using the optimization to reduce the time of the workload. Optimization is the process of identifying the best solution from the large combination of solution sets. The best solution is selected by validating the objective value of the solution set using the objective function. Without explicit programming, creating the ability of learning to the machine is known as machine learning. The machine learning required to solve the various problems raises in the power electronics application. This work mainly involved to perform the pattern matching process using the CCD sensor. And also there is need to identify the optimal position of the CCD sensor in the agriculture region. The knowledge processing exhibits the higher significance in machine learning to the pattern matching and optimal placement. Genetic optimization is the heuristic approach used in the search process, which executes the natural selection in the evolutionary process. The Gravitational Search Algorithm (GSA) is the optimization model based on the law of gravity and interaction between the mass. In this paper, unique solution is designed with the genetic algorithm by merging with the GSA to identify the optimal placement position of CCD sensor to identify the Crop disease. The performance evaluation of GA and proposed GAGSA is conducted using the Matlab, and the evaluation exhibits that the proposed solution achieves better performance in terms of number of iterations and computational complexity.