期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
基于神经网络的量测数据检测及修正系统研究应用
1
作者 石钰 姜林 周茉 《吉林电力》 2022年第4期37-40,52,共5页
为解决电力系统数据量测过程中的不确定性因素和非线性计算等问题,首先构建了基于缩减聚类算法的神经网络最优模型,然后通过反向传播算法建立量测数据模型,最后针对可信量测数据与可疑量测数据给出了相应的解决办法,整体建立了一套智能... 为解决电力系统数据量测过程中的不确定性因素和非线性计算等问题,首先构建了基于缩减聚类算法的神经网络最优模型,然后通过反向传播算法建立量测数据模型,最后针对可信量测数据与可疑量测数据给出了相应的解决办法,整体建立了一套智能量测数据检测与修正系统。 展开更多
关键词 量测数据检测 神经网络 反向传播
下载PDF
Wavefield continuation datuming using a near surface model 被引量:3
2
作者 Cui Xingfu Li Hongbing Hu Ying Liang Hong Qi Li 《Applied Geophysics》 SCIE CSCD 2007年第2期94-100,共7页
When topography and low velocity zone differences vary greatly, conventional vertical static time shifts will cause wavefield distortion and influence wave equation seismic imaging for seismic data acquired on a compl... When topography and low velocity zone differences vary greatly, conventional vertical static time shifts will cause wavefield distortion and influence wave equation seismic imaging for seismic data acquired on a complex near surface. In this paper, we propose an approach to datum correction that combines a joint tomography inversion with wavefield continuation to solve the static problem for seismic data on rugged acquisition topography. First, the near surface model is obtained by refracted wave tomography inversion. Second, the wavefield of sources and receivers are continued downward and upward to accomplish datum correction starting from a flat surface and locating the datum above topography. Based on the reciprocal theorem, Huygens' and Fresnel principles, the location of sources and receivers, and regarding the recorded data on the surface as a secondary emission, the sources and receivers are upward-continued to the datum above topography respectively. Thus, the datum correction using joint tomography inversion and wavefield continuation with the condition of a complex near surface is accomplished. 展开更多
关键词 Complex near surface tomography inversion wavefield continuation datum correction.
下载PDF
New event detection based on sorted subtopic matching algorithm
3
作者 翟东海 CUI Jing-jing +1 位作者 NIE Hong-yu DU Jia 《Journal of Chongqing University》 CAS 2013年第4期179-186,共8页
How to quickly and accurately detect new topics from massive data online becomes a main problem of public opinion monitoring in cyberspace. This paperpresents a new event detection method for the current new event det... How to quickly and accurately detect new topics from massive data online becomes a main problem of public opinion monitoring in cyberspace. This paperpresents a new event detection method for the current new event detection system, based on sorted subtopic matching algorithm and constructs the entire design framework. In this p^per, the subtopics contained in old topics (or news stories) are sorted in descending order according to their importance to the topic(or news stories), and form a sorted subtopic sequence. In the process of subtopic matching, subtopic scoring matrix is used to determine whether a new story is reporting a new event. Experimental results show that the sorted subtopic matching model improved the accuracy and effectiveness ofthenew event detection system in cyberspace. 展开更多
关键词 new event detection topic detection scoring matrix sorted subtopic matching model subtopic sequence
下载PDF
上一页 1 下一页 到第
使用帮助 返回顶部