PPubMed12 Jan 2022Cited 5×

Classification and Optimization of Basketball Players' Training Effect Based on Particle Swarm Optimization

Quanfei Zhu

Abstract

Since the professionalization of basketball in China, the number of teenagers participating in basketball training has gradually increased, which has promoted the improvement of basketball level in China. Teenagers ‘love' for basketball further promotes the improvement of basketball level in China. However, the reality of basketball in China still lags far behind that of developed basketball countries, in which backward training is an important aspect. This paper mainly makes a comprehensive overview of the training effect and classification of basketball players through particle swarm optimization, objectively evaluates the training effect of physical fitness, and proposes corresponding optimization measures, aiming at the scientific optimization of physical training for basketball players in China. In order to rationally arrange the training methods, control the training process, and make the training scientific, the effectiveness of the particle swarm optimization algorithm for the classification of basketball players' training effects is analyzed, and a new population-based optimization method is proposed. The experimental results verify the superiority of the particle swarm optimization algorithm. It is an inevitable choice to enhance the physical strength level of basketball reserve strength by using appropriate methods to train basketball players.

§ The Valyu brief

The paper, in five minutes

Read from the full text via Valyu Contents

A particle swarm optimization algorithm effectively classifies and optimizes basketball players' training effects, outperforming genetic algorithms in accuracy and convergence speed.

What’s new

i.Introduced a population‑based PSO algorithm where each particle represents a feasible training solution with a fitness value.
ii.Applied swarm‑intelligence simulation to classify and optimize basketball players’ training effects, creating a theoretical system centered on swarm intelligence.
iii.Demonstrated fast search speed, high efficiency, and simplicity, making the algorithm suitable for real‑value processing in training optimization.

How they did it

The authors designed a particle swarm optimization (PSO) algorithm with a triangular distribution for velocity and a dynamic inertia‑weight strategy to balance global and local search. They applied the algorithm to classify and optimize basketball players’ training effects and compared its performance against genetic algorithms using benchmark datasets and real training data. Evaluation metrics such as accuracy, error rates, and convergence speed were recorded.

What they found

PSO achieved 83.8% training sample accuracy and 81.34% test sample correctness, with errors of 6.76 and 5.49 respectively (Table 1).
Classification accuracy on benchmark datasets reached 93.39% (Iris), 94.76% (Ionosphere) and 99.5% (Breast cancer) (Table 2).
Average heart rate during training was 4.55 times/10 s and sports density 2.47 % (Table 3).
PSO reduced the number of iterations needed for convergence compared to genetic algorithms, significantly speeding up training.
Classification performance and convergence speed were markedly improved over GA, as shown in Figures 3‑4.

Caveats

✕Short training period and late start of regular physical training limit the applicability of results.
✕Lack of a solid mathematical foundation for PSO may affect theoretical guarantees.
✕The study’s experimental validation is limited to specific datasets and may not generalize to all basketball training scenarios.
✕Absence of long‑term follow‑up to assess sustained impact of optimized training.

§ The Valyu brief

Reading the full paper and taking notes. This takes a few seconds…

§ Ask this paper

Ask a question about this paper

Valyu reads the full text and answers from what the paper actually says.

§ Related work in other archives

Classification and Optimization of Basketball Players' Training Effect Based on Particle Swarm Optimization

The paper, in five minutes

Ask a question about this paper

Similar papers in all four archives

Similar papers in all four archives

The paper, in five minutes