This paper proposes a HMM training algorithm which is based on grouping multiple observations by multiple correlation coefficient. 本文在不附加任何假设的前提下,提出了一种用多观察序列训练HMM的算法,从理论上解决了上述问题。
A new method is given to choose the best values in the multiple observations, and the higher precision of adjusting result could be taken with this way. 本文以误差理论为基础,分析了这种方法的不足,从测量结果的实际误差出发,给出了选择最优观测值的新方法,大大提高了平差结果的精度。
The new algorithm avoids computing the conditional probabilities directly and considers the correlativity between successive observation vector, it is very useful for training HMM when the group of multiple observations are uniformly dependent. 所获算法避免了直接计算条件概率的困难,考虑了训练序列间的相关性,故使计算过程更为便捷,在观测序列分组均匀相关情况下非常有用。
A HMM training algorithm based on grouping multiple observations by multiple correlation coefficient 基于多相关分组的HMM训练算法
Inside the tunnel, the integral consummation of errors for multiple observations was used, which is simple and convenient for calculation and especially suitable for long linear tunnel. 洞内采用多期观测整体平差方法,计算简单,方便,尤其适应于长大直线隧道,省时省力,提高工效。