Applied Mathematics and Nonlinear Sciences, Journal Year: 2025, Volume and Issue: 10(1)
Published: Jan. 1, 2025
Abstract Accurately grasping the training load of athletes is a prerequisite for developing scientific and reasonable competition programs. This paper realizes coupling genetic algorithm BP neural network to design prediction method based on IAGABP algorithm. In part, N chromosomes are randomly generated using real number coding form initial population algorithm, then operation continuously performed improve overall fitness until evolution reaches specified generations when terminated. firstly, structure other parameters should be determined, optimal individuals obtained in part disassembled into set networks. The connection weights thresholds used as network, adjusted by error back propagation output termination condition final model obtained. dataset test, mean square average this paper’s 0.00122875, smaller than that GA-BP model, which proves superior performance similarity between actual predicted values 99.15% real-world application athletes. can provide accurate track field sprinters, reliable reference planning arrangements, recover from development plan standardization standardized technology.
Language: Английский