Also a posteriori probability analysis method is applied to evaluate the uncertainty of inversion results. 并采用后验概率(APP)分布进行反演结果的唯一性分析,改善了全局寻优反演方法的完整性,提高了反演结果的可信度。
A posteriori probability analysis method was proposed based on a parallel optimization algorithm, and applied to quantitative analysis of matched inversion results. 构造了一种基于并行优化算法的后验概率(APP)分析算法,用于对匹配场反演结果进行定量的概率分析。
The application of a Gaussian Markov Random Fields ( GMRF ) based Maximum A Posteriori Probability(APP) ( MAP ) estimation for image Gaussian noise filter was presented. 提出了基于高斯马尔可夫随机场(GMRF)的最大后验概率(APP)(MAP)估计在图像高斯噪声滤波中的应用方法。
Owing to the fact that continuous outliers may occur in noise measurement, a posteriori probability formula used to discriminate continuous outliers, using Bayes theorem, is derived and the robust Kalman filtering insensitive to the above outliers is presented. 针对量测噪声中可能出现成片连续野值的情况,利用Bayes定理,得到了判别成片连续野值的后验概率(APP)公式,并提出了对上述野值不敏感的鲁棒Kalman滤波。
Pseudo-optical flow estimation for medical image sequences based on maximum a posteriori probability and Gibbs random field 基于吉伯斯随机场和最大后验概率(APP)的医学序列图像伪光流估计