A clustering mining method for sports behavior characteristics of athletes based on the ant colony optimization DOI Creative Commons
Dapeng Yang, Junqi Wang,

Jingtang He

и другие.

Heliyon, Год журнала: 2024, Номер 10(12), С. e33297 - e33297

Опубликована: Июнь 1, 2024

This study aims to enhance the precision of analyzing athlete behavior characteristics, thereby optimizing sports training and competitive strategies. introduces an innovative Ant Colony Optimization (ACO) clustering model designed address high-dimensional issues in data by simulating path selection mechanism ants searching for food. The development process this includes fine-tuning ACO parameters, features specific data, comparing it with traditional algorithms, similar research models based on neural network, support vector machines, deep learning. results indicate that significantly outperforms comparison algorithms terms silhouette coefficient (0.72) Davies-Bouldin index (1.05), demonstrating higher effectiveness stability. Particularly noteworthy is recall rate (0.82), a key performance indicator, where accurately captures different behavioral characteristics athletes, validating its reliability analysis. innovation lies not only application algorithm practical field but also showcasing advantages handling complex, data. However, generality efficiency larger scale or types still need further validation. In conclusion, through introduction optimization model, provides novel effective approach deeper understanding analysis characteristics. holds significant importance advancing science applications.

Язык: Английский

A clustering mining method for sports behavior characteristics of athletes based on the ant colony optimization DOI Creative Commons
Dapeng Yang, Junqi Wang,

Jingtang He

и другие.

Heliyon, Год журнала: 2024, Номер 10(12), С. e33297 - e33297

Опубликована: Июнь 1, 2024

This study aims to enhance the precision of analyzing athlete behavior characteristics, thereby optimizing sports training and competitive strategies. introduces an innovative Ant Colony Optimization (ACO) clustering model designed address high-dimensional issues in data by simulating path selection mechanism ants searching for food. The development process this includes fine-tuning ACO parameters, features specific data, comparing it with traditional algorithms, similar research models based on neural network, support vector machines, deep learning. results indicate that significantly outperforms comparison algorithms terms silhouette coefficient (0.72) Davies-Bouldin index (1.05), demonstrating higher effectiveness stability. Particularly noteworthy is recall rate (0.82), a key performance indicator, where accurately captures different behavioral characteristics athletes, validating its reliability analysis. innovation lies not only application algorithm practical field but also showcasing advantages handling complex, data. However, generality efficiency larger scale or types still need further validation. In conclusion, through introduction optimization model, provides novel effective approach deeper understanding analysis characteristics. holds significant importance advancing science applications.

Язык: Английский

Процитировано

5