当前位置: 首页 > 文章 > 本体稀疏矩阵学习以及在相似度计算中的应用 西南大学学报(自然科学版) 2020 (1) 118-123
Position: Home > Articles > Ontology Sparse Matrix Learning and Its Application in Similarity Computation Journal of Southwest University(Natural Science Edition) 2020 (1) 118-123

本体稀疏矩阵学习以及在相似度计算中的应用

作  者:
兰美辉;范全润;高炜
单  位:
曲靖师范学院信息工程学院;云南师范大学信息学院
关键词:
本体;相似度计算;本体映射;稀疏矩阵
摘  要:
在大数据背景下,本体所包含的概念越来越多,其结构也越来越复杂.这要求其对应的本体算法能高效地降低计算的维度,进而减少计算复杂度.将原有的本体稀疏向量学习模型进行扩展,提出本体稀疏矩阵学习模型.通过矩阵导数计算设计一种迭代算法来获取逼近最优解.实验表明新算法在特定的本体应用领域有较高的效率.
译  名:
Ontology Sparse Matrix Learning and Its Application in Similarity Computation
作  者:
LAN Mei-hui;FAN Quan-run;GAO Wei;School of Information Engineering, Qujing Normal University;School of Information, Yunnan Normal University;
关键词:
ontology;;similarity measure;;ontology mapping;;sparse matrix
摘  要:
Under the background of big data, ontology contains more and more concepts, and thus its structure becomes more complex. Therefore, it is required that the corresponding ontology algorithm be able to reduce the computational dimension efficiently, so as to reduce the computation complexity. In this paper, the original ontology sparse vector learning model is extended, and an ontology sparse matrix learning model is proposed to obtain the optimal approximation solution. An iterative algorithm is designed to get this solution by means of matrix derivative computation. Two experiments verify that the new algorithm has higher efficiency in specific ontology specific applications.

相似文章

计量
文章访问数: 1
HTML全文浏览量: 0
PDF下载量: 0

所属期刊

推荐期刊