Although deep learning models, especially the Artificial Neural Network (ANN), are widely used for student performance prediction, their “black-box” nature often leads to unreliable learned relationships that contradict educational domain knowledge, limiting both trustworthiness and further performance improvement. Based on Shapley Additive Explanations (SHAP), this study developed an ANN using a public dataset containing 395 Portuguese high school students’ mathematics performance records. The analysis identified key features influencing students’ mathematics performance and revealed that the original correlations learned by the ANN were inconsistent with established educational domain knowledge. To address this issue, we proposed the Student Performance Prediction Explanation (SPPE) algorithm for optimizing ANN, which reassessed the contribution of 30 features under the guidance of educational domain knowledge. Both global and local interpretability analyses were conducted to examine the process of importance changes. Furthermore, this study found that after aligning the model with educational domain knowledge, the prediction accuracy of the proposed ANN achieved a 26.9% improvement compared with the original model. In addition, it outperformed some typical traditional machine learning algorithms. Additional experiments further confirmed that the proposed SPPE strategy is applicable to various ANN architectures, supporting its robustness across model structures within this dataset and reinforcing its generalizability and practical value. The findings of this study demonstrated that integrating educational domain knowledge can improve student performance prediction, contributing to the development of interpretable neural network frameworks and offering actionable insights for other educational applications.

Blue-and-white porcelain patterns embody rich symbolic meanings and play a pivotal role in the transmission of Chinese intangible cultural heritage. However, their contemporary application often faces challenges due to complex visual forms and contextual interpretations. This study adopts a semiotic perspective to reinterpret blue-and-white porcelain motifs as cultural heritage symbols, aiming to assess their potential for sustainable preservation and modern revitalization. A hybrid evaluation framework is proposed, combining Grey System Theory and the Fuzzy Evaluation Method to quantitatively analyze 40 representative patterns across five key dimensions: cultural symbolism, esthetic value, communicative potential, modern applicability, and sustainability. Data were collected from expert panels, public surveys, and market performance, with the Analytic Hierarchy Process (AHP) employed to determine the relative importance of each dimension. The results reveal that plant and geometric patterns exhibit high adaptability and symbolic clarity, making them ideal for reinterpretation in modern design. Conversely, complex narrative and animal-based motifs demonstrate weaker performance in communicative efficiency and sustainability, indicating the need for visual simplification and semantic transformation. This study provides a theoretical and methodological foundation for the revitalization of traditional porcelain heritage in contemporary design practice, contributing to the global dissemination and sustainable development of cultural heritage symbols.

With the rapid development of digital technologies, augmented reality (AR) has created new possibilities for the presentation and dissemination of cultural heritage. However, conventional digital guide systems in historic districts are typically dominated by static information delivery, lacking interactivity and user engagement, which limits their effectiveness in enhancing public understanding of historic architectural environments and related cultural knowledge. To address this limitation, this study focuses on historic architectural districts and proposes a narrative-based AR cultural exploration approach embedded in real architectural space. The Hubu Mountain historic architectural district in Xuzhou, China, was selected as the case study. First, grounded theory was employed to systematically analyze the cultural resources of the district and extract key cultural narrative elements. Based on these elements, a design framework for a narrative AR cultural exploration system was constructed. Subsequently, a mobile AR interactive system was developed using the Unity 2022.3 LTS and Vuforia Engine 10. A total of 80 participants were recruited and randomly assigned to either an experimental or a control group. Cultural knowledge tests, an immersive experience scale, and a dissemination intention scale were used to evaluate the outcomes, and the collected data were analyzed statistically. The results indicate that, compared with a conventional text–image guide condition, the narrative AR exploration condition significantly improved participants’ cultural cognition and dissemination intention. Specifically, the experimental group achieved significantly higher post-test scores in cultural knowledge than the control group, and a significant between-group difference was also observed in dissemination intention. In terms of immersive experience, although the experimental group reported higher mean scores than the control group, the difference did not reach statistical significance, showing only a possible improving trend. These findings suggest that an integrated narrative AR cultural exploration condition can enhance public understanding of historic architectural districts and strengthen the communication potential of heritage experiences in real built environments. This study provides a digital interpretation approach for historic architectural districts and offers empirical support for the use of AR-based interactive systems in architectural heritage communication and public engagement.