Accurate drug-drug interaction (DDI) prediction is essential to prevent adverse effects, especially with the increased use of multiple medications during the COVID-19 pandemic. Traditional machine learning methods often miss the complex relationships necessary for effective DDI prediction. This study introduces a deep learning-based classification framework to assess adverse effects from interactions between Fluvoxamine and Curcumin. Our model integrates a wide range of drug-related data (e.g., molecular structures, targets, side effects) and synthesizes them into high-level features through a specialized deep neural network (DNN). This approach significantly outperforms traditional classifiers in accuracy, precision, recall, and F1-score. Additionally, our framework enables real-time DDI monitoring, which is particularly valuable in COVID-19 patient care. The model’s success in accurately predicting adverse effects demonstrates the potential of deep learning to enhance drug safety and support personalized medicine, paving the way for safer, data-driven treatment strategies.

This research investigates the impact of digital academic supervision (DAS) on teacher professionalism (TP), with a focus on the mediating role of personal learning networks (PLNs) and their implication for educational policy. Using Partial Least Squares Structural Equation Modeling (PLS-SEM), data were collected from 276 teachers in prestigious secondary schools in East Java, Indonesia. The study uses a regression model design to explore direct and mediated effects between DAS, PLNs, and TP. Findings demonstrate that DAS directly impacts both PLNs (0.638) and TP (0.550), while PLNs also directly influence TP (0.293). Mediated analysis indicates that DAS enhances TP through PLNs (0.187). These results underscore the importance of digital tools in academic supervision, fostering collaboration, and promoting teacher professional development. The empirical evidence supports the effectiveness of DAS in enhancing teacher professionalism, suggesting significant implications for educational policy and practice in Indonesia in terms of regulatory framework, such as data privacy and security, standardization, training programs, and certification and accreditation.

Accurate demand forecasting is key for companies to optimize inventory management and satisfy customer demand efficiently. This paper aims to Investigate on the application of generative AI models in demand forecasting. Two models were used: Long Short-Term Memory (LSTM) networks and Variational Autoencoder (VAE), and results were compared to select the optimal model in terms of performance and forecasting accuracy. The difference of actual and predicted demand values also ascertain LSTM’s ability to identify latent features and basic trends in the data. Further, some of the research works were focused on computational efficiency and scalability of the proposed methods for providing the guidelines to the companies for the implementation of the complicated techniques in demand forecasting. Based on these results, LSTM networks have a promising application in enhancing the demand forecasting and consequently helpful for the decision-making process regarding inventory control and other resource allocation.

With the continuous development of science and technology, network technology has been applied to various fields, and the education model of universities has also made innovations with the application of network technology. In ideological and political education in universities, influenced by traditional educational models and other factors, the quality of education is uneven, and the learning effectiveness of students needs to be improved. Therefore, integrating network technology and innovating teaching methods in ideological and political education in universities is very important. Conducting online ideological and political education in universities can enhance students' interest in learning, while also helping them develop good moral qualities and providing assistance for their future development. This article focuses on the research goal of ideological and political education models in universities, exploring the importance and methods of integrating online ideological and political education in universities, hoping to provide some help for relevant universities.

The public health emergency has changed the environment and conditions of art teaching. Based on the abnormal teaching background, we can use this as an opportunity to explore new teaching forms. Relying on the unique functions of the network platform, the Art Cloud Classroom explores a new style of home-based art learning that is vivid, autonomous and interactive, develops students' art skills, develops positive interests and emotions, and makes every life a better place in the nourishment of art.

Under the background of the development of the network information age, the current Internet industry has obtained more development opportunities, but it has also brought corresponding challenges in the process of wide application. In the development and construction of modernization, society pays more attention to the supervision and determination of the characteristics of online public opinion. From the perspective of the current characteristics of network public opinion, because social information is more extensive and involves many fields, network public opinion has a high degree of complexity and diffusion. Therefore, it is necessary to strengthen the analysis and application of relevant data mining systems in order to achieve efficient management of network public opinion. The key to the disadvantage of the traditional excavation of public opinion communication characteristics lies in the lag of the excavation process, and it is difficult to deal with malignant public opinion in a timely and effective manner. Therefore, in order to truly solve the lagging problem of public opinion data dissemination feature mining technology, it is necessary to strengthen the application of artificial intelligence technology in it.