ID 原文 译文
11364 建立了基于SN的目标融合检测系统,提出了一种非理想信道条件下在线决策融合的目标检测方法。 Based on SN target fusion detection system, puts forward a kind of ideal channel conditions online method for target detection decision fusion.
11365 该方法依据解调后数据构建了节点未知虚警概率、检测概率以及节点与融合中心信道平均传输错误概率等未知参数求解模型,并采用非线性最小二乘方法在线地估计出这些未知参数。 ‭The method is based on the data to construct a node after demodulation false-alarm probability and detection probability and the unknown node and the fusion center channel average transmission error probability of the unknown parameters to solve the model, and USES the nonlinear least squares method to estimate the unknown parameters online.
11366 进而通过选择性能优的节点参与融合,最大化融合检测系统检测概率。 ‭Then by selecting the optimal fusion nodes involved in performance, maximize fusion detection system detection probability.
11367 仿真结果表明:这种在线决策融合方法能够准确地估计出传感器节点的概率参数以及信道的平均传输错误率; ‭The simulation results show that the online decision fusion method can accurately estimate the probability parameters of the sensor node and the average transmission channel error rate;
11368 ‭相比于已知先验的最优似然比融合规则,在线决策融合规则检测性能相当。 ‭Compared with the known a priori optimal likelihood ratio fusion rules, online detection performance decision fusion rules.
11369 针对合成孔径雷达(synthetic aperture radar,SAR)图像分割这一研究热点,综合论述了基于主动轮廓模型(active contour model,ACM)的SAR图像分割方法。 For synthetic aperture radar (synthetic aperture radar, SAR) image segmentation, a hot research topic, comprehensive discussed based on the active contour model (active contour model, ACM) SAR image segmentation method.
11370 首先,介绍了经典的ACM及其数学原理,并通过理论和实验分析了这些模型应用于SAR图像分割时存在的问题; First, this paper introduces the classical ACM and mathematics principle, and through theoretical and experimental analysis of the model is applied to the problem of SAR image segmentation;
11371 然后,对目前基于ACM的SAR图像分割方法进行了系统的梳理和分类讨论; Then, the current SAR image segmentation method based on the ACM system carding and classification discussed;
11372 最后,对基于ACM的SAR图像分割方法作了总结,并对将来的研究方向进行了展望。 Finally, the SAR image segmentation method based on the ACM summarized, and the future research direction was prospected.
11373 纠错输出编码能有效地将多类问题分解为一系列二类子问题进行求解,已受到众多机器学习研究者的关注。 Error correcting output codes can effectively will be much problem is decomposed into a series of second class are applied to solve the subproblems have been many machine learning researchers' attention.