Coal mine disaster prevention is a fundamental course within mining engineering and coal mine safety engineering curricula. Given the complexity and variability of coal mine disasters, it is crucial to cultivate students’ practical awareness to address the challenges encountered in this field. Virtual reality (VR) technology, with its highly realistic and reusable virtual environments, reduces the resource consumption required for on-site training. Additionally, it offers an effective solution for students to safely and efficiently understand coal mine disasters, master the common types of disasters and their causes, and enhance immersive learning, practical skills, and emergency response capabilities. This study integrates virtual simulation experiments with course content and utilizes VR technology to simulate mine environments and disaster processes, which allows students to experience disaster events in a safe virtual setting. By incorporating embodied cognition theory and VR gesture technology, an interactive learning system is developed to improve students’ learning efficiency and engagement. The results indicate that applying VR technology to teaching coal mine disaster prevention and control significantly stimulates students’ interest and facilitates a comprehensive, intuitive understanding of the causes, characteristics, and prevention measures associated with coal mine disasters. Employing virtual reality technology in education not only enhances the students’ awareness of coal mine safety but also provides strong support for the sustainable development of coal mine enterprises.

The classroom video has a complex background and dense targets. This study utilizes small object detection technology to analyze and evaluate students’ behavior in the classroom, aiming to objectively and accurately assess classroom quality. Firstly, noise is removed from the images using a median filter, and the contrast of the images is enhanced through histogram equalization. Label smoothing is applied to reduce the model’s sensitivity to labels. Then, features are extracted from the preprocessed images, and multi-scale feature fusion is employed to enhance semantic expression across multiple scales. Finally, a combination loss function is utilized to improve the accuracy of multi-object recognition tasks. Real-time detection of students’ behaviors in the classroom is performed based on the small object detection model. The average head-up rate in the classroom is calculated, and the quality of teaching is evaluated and analyzed. This study explores the methods and applications of small object detection technology based on actual teaching cases and analyzes and evaluates its effectiveness in evaluating the quality of higher education classroom teaching. The research findings demonstrate the significant importance of small object detection technology in effectively evaluating students’ learning conditions in higher education classrooms, leading to improved teaching quality and personalized education.

Predicting interactions between drugs and their targets is vital for drug discovery and repositioning. Conventional techniques are slow and labor-intensive, while deep learning algorithms offer efficient solutions. However, deep learning often focus on single drug representations or simplistic combinations, leading to suboptimal feature representation. Moreover, the prevalent use of convolutional neural networks (CNNs) in drug image representation neglects the necessity for both local and global drug information in Drug-Target Interaction (DTI) tasks. To address these challenges, we propose TriCvT-DTI, a novel approach that combines molecular images, chemical sequence features, and graph representations of drugs to comprehensively capture structural, spatial, and functional aspects. TriCvT-DTI introduces a bidirectional multi-head attention mechanism for interactive feature learning between drugs and targets, enhancing performance by modeling complex relationships. By using Convolutional Vision Transformers (CvTs), TriCvT-DTI can effectively extract structural and spatial features from drug images. We evaluate our model on three datasets: Human, C. elegans, and Davis, and we compare it with state-of-the-art methods. Then we train TriCvT-DTI with uni-modality and bi-modality to compare then extract the impact of each modality on TriCvT-DTI. Experimental results demonstrate that TriCvT-DTI outperforms existing methods on both balanced and unbalanced datasets. Moreover, it presents impressive generalization capabilities on the Drug-Target Interaction (DTI) task.