Deconstruction and Realization of Sports Entity Simulation Based on Fish Swarm Algorithm

Area of Science:

• Sports Science
• Computational Intelligence
• Biomimetic Algorithms

Background:

• Current sports entity simulation struggles with dynamic motion accuracy and is sensitive to noise and brightness.
• Limitations in existing technologies hinder realistic capture of athlete movements.

Purpose of the Study:

• To propose and evaluate a novel sports entity simulation method using the fish swarm algorithm.
• To compare the effectiveness of fish swarm algorithm-based simulation against traditional particle swarm algorithm methods.

Main Methods:

• Implementing a sports entity simulation utilizing the fish swarm algorithm.
• Analyzing figure effectiveness, segmentation, core points, and noise reduction.
• Comparing simulation results with traditional particle swarm algorithm techniques.

Main Results:

• Fish swarm algorithm provides more accurate motion capture and better representation of real moving figures.
• Increased core points correlate with higher motion capture accuracy.
• Achieved a 20.3% improvement in noise reduction, mitigating brightness effects.

Conclusions:

• The fish swarm algorithm demonstrates superior effectiveness for simulating sports entities.
• This approach enhances motion capture accuracy and robustness against environmental factors.