文献类型：期刊文献

英文题名：Computer data processing method of map manifold based on derivative transfer approach

作者：Jia, Meng[1];Sun, Zheren[2]

第一作者：贾蒙

通讯作者：Jia, M[1]

机构：[1]Xinxiang Univ, Dept Elect Engn, Xinxiang, Peoples R China;[2]Beijing Univ Chem Technol, Dept Elect Engn, Beijing, Peoples R China

第一机构：新乡学院机电工程学院

通讯机构：[1]corresponding author), Xinxiang Univ, Dept Elect Engn, Xinxiang, Peoples R China.|[1107111]新乡学院机电工程学院;[11071]新乡学院;

年份：2023

外文期刊名：CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE

收录：;EI(收录号：20232114124820);Scopus(收录号：2-s2.0-85159669105);WOS:【SCI-EXPANDED(收录号:WOS:000990202200001)】；

基金：ACKNOWLEDGMENTS This Project was Supported by National Natural Science Foundation of China (Grant 61501391), Science and Technology Innovation Talent Project of Henan Province (21HASTIT021), Major Science and Technology Projects of Xinxiang City (21ZD009).

语种：英文

外文关键词：derivative transfer; high-dimensional manifold; manifold calculation; manifold orbit

摘要：With the rapid development of Internet technology and the rapid upgrade of hardware devices such as computers and smartphones, the data processed by computers often presents a high dimension. How to reduce data dimension and improve data processing speed is a hot research topic in the computer field. One shortcoming of one-dimensional manifold calculation methods via sequence points is that the position of new points on the manifold is determined by searching the existing manifold by dichotomy, which is tedious and time-consuming. This paper improved this method based on derivative transfer. According to the calculation results of one-dimensional stable and unstable manifolds, they exhibited a special property, that is, for any point on the manifold orbit, its image and preimage must also be on the manifold orbit. Based on this, the derivative transfer method was used to improve the calculation of one-dimensional manifolds for the map, and a three-step calculation method of "prediction-correction-accuracy verification" was proposed. Then this method was applied to the simulation of high-dimensional manifolds. The simulation results revealed that the proposed method refined the manifold calculation and greatly enhanced the computation speed.