Minh Duc Nguyen

Minh Duc Nguyen, Alexander Kryukov

Space Monitoring Data Center (SMDC) of SINP MSU is one of the several centers in the world that collects data on the radiational conditions in near-Earth orbit from various Russian (Lomonosov, Electro-L1, Electro-L2, Meteor-M1, Meteor-M2, etc.) and foreign (GOES 13, GOES 15, ACE, SDO, etc.) satellites. The primary purposes of SMDC are: aggregating heterogeneous data from different sources; providing a unified interface for data retrieval, visualization, analysis, as well as development and testing new space weather models; and controlling the correctness and completeness of data. Space weather models rely on data provided by SMDC to produce forecasts. Therefore, monitoring the whole data processing cycle is crucial for further success in the modelling of physical processes in near-Earth orbit based on the collected data. To solve the problem described above, we have developed a framework called Live Monitor at SMDC. Live Monitor allows watching all stages and program components involved in each data processing cycle. All activities of each stage are logged by Live Monitor and shown in real-time on a web interface. When an error occurs, a notification message will be sent to satellite operators via email and the Telegram messenger service so that they could take measures in time. The Live Monitor's API can be used to create a customized monitoring service with minimum coding.

Quang Vinh Nguyen, Minh Duc Nguyen, Thanh Hoang Son Vo et al.

Automated Radiology report generation (RRG) aims at producing detailed descriptions of medical images, reducing radiologists' workload and improving access to high-quality diagnostic services. Existing encoder-decoder models only rely on visual features extracted from raw input images, which can limit the understanding of spatial structures and semantic relationships, often resulting in suboptimal text generation. To address this, we propose Anatomical Attention Alignment Network (A3Net), a framework that enhance visual-textual understanding by constructing hyper-visual representations. Our approach integrates a knowledge dictionary of anatomical structures with patch-level visual features, enabling the model to effectively associate image regions with their corresponding anatomical entities. This structured representation improves semantic reasoning, interpretability, and cross-modal alignment, ultimately enhancing the accuracy and clinical relevance of generated reports. Experimental results on IU X-Ray and MIMIC-CXR datasets demonstrate that A3Net significantly improves both visual perception and text generation quality. Our code is available at \href{https://github.com/Vinh-AI/A3Net}{GitHub}.

Hai-Dang Kieu, Delvin Ce Zhang, Minh Duc Nguyen et al.

Personalized news recommendation systems often struggle to effectively capture the complexity of user preferences, as they rely heavily on shallow representations, such as article titles and abstracts. To address this problem, we introduce a novel method, namely PNR-LLM, for Large Language Models for Personalized News Recommendation. Specifically, PNR-LLM harnesses the generation capabilities of LLMs to enrich news titles and abstracts, and consequently improves recommendation quality. PNR-LLM contains a novel module, News Enrichment via LLMs, which generates deeper semantic information and relevant entities from articles, transforming shallow contents into richer representations. We further propose an attention mechanism to aggregate enriched semantic- and entity-level data, forming unified user and news embeddings that reveal a more accurate user-news match. Extensive experiments on MIND datasets show that PNR-LLM outperforms state-of-the-art baselines. Moreover, the proposed data enrichment module is model-agnostic, and we empirically show that applying our proposed module to multiple existing models can further improve their performance, verifying the advantage of our design.

Minh DUc Nguyen, Cong Thuong Le, Trong Lam Nguyen

The accurate alignment of 3D woodblock geometrical models with 2D orthographic projection images presents a significant challenge in the digital preservation of Vietnamese cultural heritage. This paper proposes a unified image processing algorithm to address this issue, enhancing the registration quality between 3D woodblock models and their 2D representations. The method includes determining the plane of the 3D character model, establishing a transformation matrix to align this plane with the 2D printed image plane, and creating a parallel-projected depth map for precise alignment. This process minimizes disocclusions and ensures that character shapes and strokes are correctly positioned. Experimental results highlight the importance of structure-based comparisons to optimize alignment for large-scale Han-Nom character datasets. The proposed approach, combining density-based and structure-based methods, demonstrates improved registration performance, offering an effective normalization scheme for digital heritage preservation.