post-test odds

Unlike conventional AOFDM systems which adopt fixed thresholds, the method calculates bit error rate (BER) of a subband when adopting each modulation based on the posterior signal to noise ratio (SNR) under current channel state, and compares it with the target SNR to determine adopted modulation.

提出了一种基于子带的自适应正交频分复用(AOFDM)系统的调制方式的自适应选择方法,不同于传统AOFDM系统采用固定的门限,该方法基于子带中所有子载波的后验信噪比(SNR),计算得到当前信道状况下不同调制方式该子带的误码率(BER),并与系统所要求的目标BER对比从而确定子带所采用的调制方式。

In this paper,an optimal power control method based on post-detection SINR balancing for a cellular V-BLAST system is proposed.

针对多小区V-BLAST系统中的同信道干扰问题,提出了一种基于后验信干比平衡的功率控制方法以及简化的次优算法,通过调整各基站每个发送天线的功率,平衡移动台接收端各路子流的后验信干比。

The authors study a new method on how to classify a sample into one of the several known population in terms of posterior probability ratio established by the sample s predictive density functions when the unknown parameters prior distributions are normal-inverted Wishart distribution.

研究了各总体服从正态分布、分布参数的先验分布均为正态—逆Wishart共轭先验时 ,如何利用待判样品的预报密度函数 ,构造后验概率比和分类判别规则 ,并据此对样品进行分类识别 ;该方法的特点是充分利用了参数分布的信息 ,结论简单、直观 ,并且也不需要假设各总体的协方差阵相

In this paper,the authors study a method on how to classify a sample into one of the several known normal populations in terms of posterior probability ratio established by the samples predictive density functions when the unknown parameters prior distributions are diffuse prior distribution.

本文研究了各总体服从多元正态分布 ,其未知参数的先验分布均为扩散先验分布时 ,如何利用待判样品的预报密度函数、构造后验概率比并据此对样品进行分类与判别 ;此方法并不需要假设各总体分布的协方差相同 ,而且在预试样本容量较小时仍然可行。

Absolute value of relative error between prediction and observant values was about 0 56% to 14 51%,testifying ratio after prediction was 0 280 2,and small error probability was 1 0.

预测结果与实测值的相对误差绝对值介于 0 5 6%～ 1 4 5 1 %之间 ,预测结果后验比与小误差概率分别为0 2 80 2和 1 0。