Feature selection method and system based on discrete salmons search mechanism

The invention provides a feature selection method and system based on a discrete salmons search mechanism, and belongs to the field of feature selection methods. The method aims to solve the problems that feature subsets selected by an existing encapsulation type feature selection method are insufficient in precision, the classification accuracy in combination with a follow-up learning algorithm is not high, and time complexity is high. According to the method, discretization processing is carried out on the salmons group search mechanism for solving the continuous optimization problem, the discrete salmons group search mechanism which is excellent in optimization performance and more suitable for solving the feature selection problem is obtained, higher robustness is achieved, the discrete salmons group search mechanism is more suitable for the feature selection problem, and the robustness is improved. The application limitation of a salmons group search mechanism is broken through; and meanwhile, the BP neu