Abstract
This study aims to comprehensively analyze and evaluate the quality of college physical dance education using Convolutional Neural Network (CNN) models and deep learning methods. The study introduces a teaching quality evaluation (TQE) model based on one-dimensional CNN, addressing issues such as subjectivity and inconsistent evaluation criteria in traditional assessment methods. By constructing a comprehensive TQE system comprising 24 evaluation indicators, this study innovatively applies deep learning technology to quantitatively assess the quality of physical dance education. This TQE model processes one-dimensional evaluation data by extracting local features through convolutional layers, reducing dimensions via pooling layers, and feeding feature vectors into a classifier through fully connected layers to achieve an overall assessment of teaching quality. Experimental results demonstrate that after 150 iterations of training and validation on the TQE model, convergence is achieved, with mean squared error (MSE) decreasing to 0.0015 and 0.0216 on the training and validation sets, respectively. Comparatively, the TQE model exhibits significantly lower MSE on the training, validation, and test sets compared to the Back-Propagation Neural Network, accompanied by a higher R(2) value, indicating superior accuracy and performance in data fitting. Further analysis on robustness, parameter sensitivity, multi-scenario adaptability, and long-term learning capabilities reveals the TQE model's strong resilience and stability in managing noisy data, varying parameter configurations, diverse teaching contexts, and extended time-series data. In practical applications, the TQE model is implemented in physical dance courses at X College to evaluate teaching quality and guide improvement strategies for instructors, resulting in notable enhancements in teaching quality and student satisfaction. In conclusion, this study offers a comprehensive evaluation of university physical dance education quality through a multidimensional assessment system and the application of the 1D-CNN model. It introduces a novel and effective approach to assessing teaching quality, providing a scientific foundation and practical guidance for future educational advancements.