Background: An adequate level of health literacy will help university students to better respond to public health emergencies and reduce unintended harm caused by public health events. The objective of this study was to assess the health literacy levels of students from Universities of Shaanxi province of China, in order to provide a basis for the development of health literacy promotion plan for university students. Methods: An online cross-sectional questionnaire survey was conducted at five universities in Shaanxi Province of China on the Wen-Juan-Xing online platform. A purposive sampling method was used to 1578 students via self-administered questionnaire. Comparisons of means were made using the t-test and ANOVA, and comparisons of ratios or composition ratios were made using the χ² test. Results: The mean score for health literacy was (105.33± 10.14) out of 135, and the mean scores for the three dimensions of health knowledge, attitudes and practices were (36.093± 4.192), (34.178± 4.227) and (35.059± 4.515) respectively. Of the total sample, 39.2% were classified as sufficient in health literacy. Female students had higher health literacy level than male students (t=4.064, p=0.044), lower grade students scored higher than higher grade (F=3.194, p=0.013), students from urban cities scored higher than those who came from rural areas (t=16.376, p< 0.001), and university students with health education experience scored higher than those without (t=24.389, p< 0.001). Conclusion: University students’ health literacy is closely related to their gender, grades, family location and health education experience.

Data complexity directly affects the dynamics of complex systems, which in turn influences the accuracy and robustness of forecasting models. However, the load data exhibit complex features such as self-similarity, long-term memory, randomness, and chaos. This study aims to quantify and evaluate the complexity features of natural gas loads and to develop a multi-step-ahead forecasting model that integrates data decomposition and ensemble deep learning while considering these complexity features. Firstly, the complexity features of the series are quantified by rolling the fractal dimension, Hurst exponent, sample entropy, and maximum Lyapunov exponent. The analysis contributes to understanding data characteristics and provides information on complex features. Secondly, the ensemble learning eXtreme Gradient Boosting (XGBoost) can effectively screen complexity features and meteorological factors. Concurrently, variational mode decomposition (VMD) provides frequency-domain decomposition capability, while the gated recurrent unit (GRU) captures long-term dependencies. This synergy enables effective learning of local features and long-term temporal patterns, resulting in precise predictions. The results indicate that compared to other models, the proposed method (XGBoost-VMD-GRU considering complex features) demonstrates superior performance in forecasting, with R² of 0.9922, 0.9860, and 0.9679 for one-step, three-step, and six-step prediction, respectively. This study aims to bring innovative ideas to load forecasting by integrating complex features into the decomposition forecasting framework.