arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.10232cs.AI
收藏

人工智能排序的3D顶点重要性

Artificial Intelligence ordered 3D vertex importance

Faverde SA(Faverde公司);Poslovni i pravni fakultet, Univerzitet „Union – Nikola Tesla“(Union – Nikola Tesla大学商业与法律学院)

Iva Vasic, Bata Vasic, Zorica Nikolic

摘要:

多维网络的顶点排序在许多研究领域中至关重要,包括选择和确定决策的重要性。有些决策比其他决策重要得多,它们的权重分类也很重要。针对三维网络顶点重要性排序问题,提出了一种全新的基于人工智能的权重决策方法,改进了现有的基于量化索引调制(QIM)和纠错码的有序统计顶点提取与跟踪算法(OSVETA)。我们在本文中提出的技术提供了显着的改进的效率,确定网络顶点的重要性有关的统计OSVETA标准,取代探试法与现代神经网络的精确预测方法。新的人工智能技术能够显著更好地定义3D网格并更好地评估其拓扑特征。新的方法的贡献,在定义稳定的顶点,显着降低删除网格顶点的概率更高的精度。

英文摘要:

Ranking vertices of multidimensional networks is crucial in many areas of research, including selecting and determining the importance of decisions. Some decisions are significantly more important than others, and their weight categorization is also imortant. This paper defines a completely new method for determining the weight decisions using artificial intelligence for importance ranking of three-dimensional network vertices, improving the existing Ordered Statistics Vertex Extraction and Tracking Algorithm (OSVETA) based on modulation of quantized indices (QIM) and error correction codes. The technique we propose in this paper offers significant improvements the efficiency of determination the importance of network vertices in relation to statistical OSVETA criteria, replacing heuristic methods with methods of precise prediction of modern neural networks. The new artificial intelligence technique enables a significantly better definition of the 3D meshes and a better assessment of their topological features. The new method contributions result in a greater precision in defining stable vertices, significantly reducing the probability of deleting mesh vertices.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑