期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
旋转森林与极限学习相结合的遥感影像分类方法 被引量:1
1
作者 肖东升 鲁恩铭 刘福臻 《遥感信息》 CSCD 北大核心 2019年第3期93-98,共6页
针对旋转森林算法(rotation forest, RF)处理遥感影像分类时容易出现过拟合现象,以及极限学习算法(extreme learning machine, ELM)泛化性能较差问题,提出一种将旋转森林与极限学习相结合(RF-ELM)的影像分类算法。该方法首先用旋转森林... 针对旋转森林算法(rotation forest, RF)处理遥感影像分类时容易出现过拟合现象,以及极限学习算法(extreme learning machine, ELM)泛化性能较差问题,提出一种将旋转森林与极限学习相结合(RF-ELM)的影像分类算法。该方法首先用旋转森林算法对基分类器进行训练,然后利用极限学习算法作为基分类器解决旋转森林中存在的过拟合问题。通过利用Landsat-8遥感影像分别对比RF、ELM、Bag-ELM和RF-ELM进行分类实验。结果表明,所提出的集成方法比RF、ELM单一算法具有更高的分类精度,相比Bag-ELM具有更高泛化能力,有效改善了分类过拟合现象,计算效率也继承了ELM快速运算的特点。 展开更多
关键词 旋转森林 极限学习 算法互补性 集成分类器 影像分类
下载PDF
A FULL-NEWTON STEP INFEASIBLE INTERIOR-POINT ALGORITHM FOR P_*(κ) LINEAR COMPLEMENTARITY PROBLEM 被引量:1
2
作者 ZHU Danhua ZHANG Mingwang 《Journal of Systems Science & Complexity》 SCIE EI CSCD 2014年第5期1027-1044,共18页
This paper proposes a new infeasible interior-point algorithm with full-Newton steps for P_*(κ) linear complementarity problem(LCP),which is an extension of the work by Roos(SIAM J.Optim.,2006,16(4):1110-1136).The ma... This paper proposes a new infeasible interior-point algorithm with full-Newton steps for P_*(κ) linear complementarity problem(LCP),which is an extension of the work by Roos(SIAM J.Optim.,2006,16(4):1110-1136).The main iteration consists of a feasibility step and several centrality steps.The authors introduce a specific kernel function instead of the classic logarithmical barrier function to induce the feasibility step,so the analysis of the feasibility step is different from that of Roos' s.This kernel function has a finite value on the boundary.The result of iteration complexity coincides with the currently known best one for infeasible interior-point methods for P_*(κ) LCP.Some numerical results are reported as well. 展开更多
关键词 Full-Newton steps infeasible interior-point method P*(κ) linear complementarity problems polynomial complexity
原文传递
Non-reciprocity compensation correction and antenna selection for optical large MIMO system
3
作者 陈洁 迟学芬 赵琳琳 《Optoelectronics Letters》 EI 2015年第6期461-465,共5页
This paper exploits an optical large multiple input multiple output(MIMO) system.We first establish the non-reciprocity compensation correction factor to solve the channel non-reciprocity problem.Then we propose an an... This paper exploits an optical large multiple input multiple output(MIMO) system.We first establish the non-reciprocity compensation correction factor to solve the channel non-reciprocity problem.Then we propose an antenna selection algorithm with the goal of realizing maximum energy efficiency(EE) when satisfying the outage EE.The simulation results prove that this non-reciprocity compensation correction factor can compensate beam energy attenuation gap and spatial correlation gap between uplink and downlink effectively,and this antenna selection algorithm can economize the number of transmit antennas and achieve high EE performance.Finally,we apply direct current-biased optical orthogonal frequency division multiplexing(DCO-OFDM) modulation in our system and prove that it can improve the bit error rate(BER) compared with on-off keying(OOK) modulation,so the DCO-OFDM modulation can resist atmospheric turbulence effectively. 展开更多
关键词 MIMO系统 天线选择算法 校正因子 互易性 补偿 光学 OFDM调制 多输入多输出
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部