Objective: To investigate the effect of physical exercise on sleep quality and the mediating effect of smartphone use behavior in college students.Methods: A cross-sectional study design was adopted. An online survey of 5,075 college students was conducted using the Physical Activity Rating Scale-3, the Pittsburgh Sleep Quality Index, and the Mobile Phone Addiction Tendency Scale.Results: The sleep quality of college students was poor, and the proportion of college students with good sleep quality was 23.567%. A significant correlation existed between sleep quality and physical exercise (r = −0.159,P< 0.001) and mobile phone addiction (r = 0.355,P< 0.001). Physical exercise can predict sleep quality in college students (β = −0.011,P< 0.001). Smartphone use plays a part in mediating the process by which physical exercise affects sleep quality.Conclusion: Chinese college students have poor sleep quality. Physical exercise and smartphone use behavior are important factors affecting the sleep quality of college students. Physical exercise can directly predict the sleep quality of college students and can predict the sleep quality of college students through the mediating effect of smartphone use behavior.

College physical education is too one-sided, which makes the teaching process evaluation meaningless. Based on this, based on neural network technology, this article combines artificial intelligence teaching system to build an artificial intelligence sports teaching evaluation model based on neural network. The artificial intelligence model starts from the process evaluation and the final evaluation. Moreover, it uses a recurrent neural network for data training and analysis, and introduces a new decoder to perform data processing, and introduces a simplified gated neural network internal structure diagram to build the internal structure of the model.In addition, this study designs a control experiment to evaluate the performance of the model constructed in this study. The research results show that the artificial intelligence model constructed in this paper has a good effect in the performance prediction and evaluation of college sports students.

Objective: Negative moods in college students have caused frequent extreme behaviors. This study analyzed the current status and correlation between physical activity and negative moods in college students. Methods: A cross-sectional study design was used in the present research. Data on college students’ physical activity and negative moods were collected using the Sports Questionnaire Star software. The questionnaires were administered to college students in five colleges and universities in Henan and Jiangsu Provinces, China, and a total of 3711 correctly completed questionnaires were returned. Data on sociological and demographic information, the International Physical Activity Questionnaire Short Form (IPAQ-SF), and the Depression Anxiety and Stress Scale (DASS) were collected. The research was conducted in December 2021. Results: The low-intensity physical activity rate among college students was 55.56%, while depression, anxiety, and stress symptoms were detected in 35.14%, 65.29%, and 10.99%of the college students, respectively. Depression (K = 35.58, p < 0.001) and anxiety (K = 15.56, p < 0.001) rates were significantly different among the different physical activity intensity groups. The proportion of students who perform high-intensity physical activities was lower than those who perform low- and moderate-intensity physical activities. Conclusion: Low physical activity and high anxiety are evident among college students, and prolonged moderate-to-low-intensity physical activity (including static behavior) induces depression and anxiety. In the future, further studies can be conducted on improving the physical activity intensity of college students, improving the mental health monitoring and intervention systems of college students, and exploring the dose–effect relationship between physical activity and negative moods.

In this paper, an Apriori association rule optimization model based on the combination of transaction compression and Hash technology is proposed for the relationship between core strength exercises and the explosive strength quality of throwing track and field athletes. In order to improve the efficiency of mining, the Hash function is set on the basis of the FP-growth algorithm, and its grouping strategy is improved by the load optimization algorithm of the greedy strategy, and it is fused with the improved Apriori algorithm. Finally, we set up an athletic training comparison experiment with or without core strength exercises to explore the effect of core strength exercises on the improvement of explosive strength quality with the help of the fusion algorithm. After core strength exercises, the grip strength and vertical jump events of throwing athletes increased from 30.94 and 36.03 to 33.52 and 38.28, respectively, and the quality of explosive force was significantly improved. While comparing with the conventional strength exercises, the athletes who performed core strength exercises had a P-value of less than 0.05 in all the other five test items except static squat jump; the effect of the exercises was significantly better than that of the conventional strength exercises, and the lower limbs, trunk and waist and abdominal muscle groups, and the upper limbs explosive strength were also effectively improved.