Searcharxiv⌕ Search

arXiv subjects

Nana Han

Publications and source records attributed to Nana Han.

2 recordsLinked to original sources
arXiv2026

S*-well-filtered spaces and d*-spaces

Recently, Xu proposed a strongly well-filtered space in [24] and systematically investigated some of its properties and characterizations. In this paper, we introduce a new class of T0-spaces called S*-well-filtered spaces, which is strictly larger than the class of strongly well-filtered spaces. First, we establish some connections among S*-well-filtered spaces, d*-spaces and weak well-filtered spaces. Then it is demonstrated that for any dcpo P, the Scott space {\Sigma}P is a d*-space if and only if it is S*-well-filtered. Furthermore, some basic properties of S*-well-filtered spaces are discussed. We prove that if Y is an S*-well-filtered space, the function space TOP(X,Y) equipped with the Isbell topology may not be an S*-well-filtered space. Finally, we study the S*-well-filteredness of Smyth power spaces. In addition, Johnstone's non-sober dcpo example is shown to be S*-well-filtered yet it is not strongly well-filtered, thereby establishing an obvious distinction between these two classes of dcpos.

math.GN↗
arXiv2025

Towards an AI-based knowledge assistant for goat farmers based on Retrieval-Augmented Generation

Large language models (LLMs) are increasingly being recognised as valuable knowledge communication tools in many industries. However, their application in livestock farming remains limited, being constrained by several factors not least the availability, diversity and complexity of knowledge sources. This study introduces an intelligent knowledge assistant system designed to support health management in farmed goats. Leveraging the Retrieval-Augmented Generation (RAG), two structured knowledge processing methods, table textualization and decision-tree textualization, were proposed to enhance large language models' (LLMs) understanding of heterogeneous data formats. Based on these methods, a domain-specific goat farming knowledge base was established to improve LLM's capacity for cross-scenario generalization. The knowledge base spans five key domains: Disease Prevention and Treatment, Nutrition Management, Rearing Management, Goat Milk Management, and Basic Farming Knowledge. Additionally, an online search module is integrated to enable real-time retrieval of up-to-date information. To evaluate system performance, six ablation experiments were conducted to examine the contribution of each component. The results demonstrated that heterogeneous knowledge fusion method achieved the best results, with mean accuracies of 87.90% on the validation set and 84.22% on the test set. Across the text-based, table-based, decision-tree based Q&A tasks, accuracy consistently exceeded 85%, validating the effectiveness of structured knowledge fusion within a modular design. Error analysis identified omission as the predominant error category, highlighting opportunities to further improve retrieval coverage and context integration. In conclusion, the results highlight the robustness and reliability of the proposed system for practical applications in goat farming.

cs.AI↗