从大数据公共卫生视角评估身体对运动员情绪和动机行为的影响。

Evaluation of the effects of the body on athletes' emotions and motivational behaviors from the perspective of big data public health.

作者信息

Zhang Qiang, Lian Diandong, Zhang Yiqiao

机构信息

College of Physical Education, Suzhou University, Suzhou, Anhui, China.

Department of Physical Education, Tarim University, Alar, Xinjiang, China.

出版信息

Front Psychol. 2025 Aug 14;16:1640081. doi: 10.3389/fpsyg.2025.1640081. eCollection 2025.

OBJECTIVE

An analysis was conducted on the impact of the body on athletes' emotions and motivation from the perspective of Public Health (PH).

METHODS

PSO-KNN (Particle Swarm Optimization-K-Nearest Neighbor) algorithm and PSO-SVM algorithm (Particle Swarm Optimization-Support Vector Machine) were obtained by combining Particle Swarm Optimization (PSO), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM), and then the recognition rates of the two algorithms were compared.

RESULTS

When comparing the PSO-KNN algorithm and PSO-SVM algorithm on baseline removed and baseline not removed, the average recognition rates of PSO-KNN algorithm and PSO-SVM algorithm under emotional state were 56.66 and 54.75%, respectively. The average recognition rates of PSO-KNN algorithm and PSO-SVM algorithm with baseline removal under tension were 53.16 and 50.58%, respectively.

CONCLUSION

The algorithm that removes the baseline is better than the algorithm that does not remove the baseline, and the PSO-KNN algorithm is better than the PSO-SVM algorithm.

目的

从公共卫生（PH）角度分析身体对运动员情绪和动机的影响。

方法

通过结合粒子群优化算法（PSO）、K近邻算法（KNN）和支持向量机算法（SVM）得到粒子群优化 - K近邻算法（PSO - KNN）和粒子群优化 - 支持向量机算法（PSO - SVM），然后比较这两种算法的识别率。

结果

在去除基线和未去除基线的情况下比较PSO - KNN算法和PSO - SVM算法，情绪状态下PSO - KNN算法和PSO - SVM算法的平均识别率分别为56.66%和54.75%。去除基线情况下紧张状态下PSO - KNN算法和PSO - SVM算法的平均识别率分别为53.16%和50.58%。