This study compares the performance of various convolutional neural network (CNN) models for building an automated deep learning-based letter screening system targeting letters received by inmates in correctional institutions. The models evaluated include well-known architectures such as MobileNet, ResNet, and Inception, as well as recently proposed lightweight models such as ResMobileNet and IGSe, along with GroupConv and SE. Each model was trained on image data containing the Korean word for "knife" ("칼") to assess performance in terms of accuracy, processing time, and model compactness. A total of 1,197 letter image samples were used in the experiment, including 1,140 images with normal words and 57 images containing the target word. The experimental results showed that the MobileNet model had the shortest processing time, making it suitable for real-time applications, while the IGSe model achieved the highest accuracy, demonstrating optimal performance for letter screening tasks. This study suggests that deep learning-based screening techniques can be effectively applied to enhance digital security in the management of inmate correspondence within correctional institutions.

This study proposes a real-time content design pipeline optimized for Unreal Engine, integrating generative AI-based image creation with AI-assisted 3D modeling tools. The pipeline aims to streamline the production of high-quality assets for real-time applications, including games and simulations. Two types of subjects were selected: a bust combining organic character features, and a stone slab characterized by planar and symmetrical structure. Multi-angle image data were first synthesized using advanced generative AI models to simulate diverse viewpoints. These were then processed using AI-enhanced photogrammetry and modeling tools to reconstruct detailed 3D meshes and extract base textures. Post-processing steps, including mesh decimation, UV unwrapping, and texture baking, were performed to ensure compatibility with Physically Based Rendering (PBR) workflows used in Unreal Engine. The final assets were successfully imported into Unreal Engine, demonstrating visual fidelity and performance suitability in a real-time environment. The study confirms the pipeline’s potential for accelerating asset development and suggests promising future directions in AI-driven digital content creation.

In the context of higher education (HE) internationalization, English as a Lingua Franca (ELF) plays a crucial role in academic and interactive communication, often intersecting with local languages. This enables greater flexibility in language use and code-switching (CS) between English and the local language. While previous research on English as a Medium of Instruction (EMI) has predominantly examined the perspectives of local stakeholders, the views of international students have been largely underexplored. To bridge this gap, this study investigates the perceptions of both local and international students regarding CS practices within EMI courses across specific classroom situations. The findings reveal that both groups support the conditional use of the local language to promote comprehension while ensuring inclusivity. Local students demonstrate a broader acceptance of CS compared to their international counterparts, particularly in relation to academic outcomes such as understanding instruction and assessment. In contrast, international students show greater receptiveness to CS during interactive classroom discussions, which reflects their attitudes toward engaging with local peers. These insights contribute to the development of more nuanced EMI policies and deepen our understanding of language dynamics in HE contexts where English is not the native language.