Department of Physical Education, Xi'an International Studies University, Xi'an, Shaanxi 710128, China.
Comput Intell Neurosci. 2022 Jun 17;2022:6776603. doi: 10.1155/2022/6776603. eCollection 2022.
In this paper, we use a particle swarm optimization neural network algorithm to analyze the teaching data of physical education faculties and evaluate the quality of teaching in physical education faculties. By studying and analyzing the optimization problem of the weight parameters of convolutional neural network training, this paper designs a hybrid algorithm combining the improved PSO algorithm and the traditional gradient descent in the framework of the BP algorithm by using the gradient information of the loss function and the principle of group cooperative search through PSO algorithm. The hybrid algorithm takes the loss function as the objective function, based on the principle of the PSO algorithm, and optimizes the objective function by combining the gradient information of the loss function of the convolutional neural network. The convergence speed and global search ability of the algorithm are effectively improved while ensuring an acceptable increase in computation. The weight values of the three-level indicators of teacher teaching behavior, student learning behavior, and teaching environment relative to the teaching quality of physical education classroom are 0.106, 0.634, and 0.260, respectively, which shows that the dimension of student learning behavior has the highest weight value in the evaluation of physical education classroom teaching quality, followed by teaching environment and finally teacher teaching behavior. Teachers' teaching ability will affect the effect of teaching methods, and the stronger the teaching ability is, the better the selection and utilization of teaching methods can be optimized.
在本文中，我们使用粒子群优化神经网络算法分析体育院系的教学数据，并评估体育院系的教学质量。通过研究和分析卷积神经网络训练的权值参数优化问题，本文在 BP 算法的框架内，利用损失函数的梯度信息和 PSO 算法的群体协同搜索原理，设计了一种将改进的 PSO 算法与传统梯度下降相结合的混合算法。混合算法以损失函数为目标函数，基于 PSO 算法的原理，通过结合卷积神经网络损失函数的梯度信息来优化目标函数。该算法有效地提高了算法的收敛速度和全局搜索能力，同时保证了可接受的计算量增加。教师教学行为、学生学习行为和教学环境三个层次指标相对于体育课堂教学质量的权重值分别为 0.106、0.634 和 0.260，这表明在体育课堂教学质量评价中，学生学习行为维度的权重值最高，其次是教学环境，最后是教师教学行为。教师的教学能力会影响教学方法的效果，教学能力越强，教学方法的选择和利用就能得到更好的优化。
