摘要
针对在训练一个序列家族的Profile HMM时经常会得到局部最优HMM的问题,也就是说找到全局最优Profile HMM的概率不高.通过分析训练一个序列家族Profile HMM方法的特点和Profile HMM本身的结构特点提出了一种结合多个局部最优或次优Profile HMM来寻找最优模型的PSO算法,以提高序列家族Profile HMM寻优的概率.
Aiming at the problem of mostly obtaining a local optimized HMM, namely, the low probability of obtaining a global optimized HMM in training a Profile HMM of sequence family and by analyzing the characteristics of the method of training a sequence family Profile HMM and the structural characteristics of the Profile HMM itself, a PSO of optimizing the HMM is brought forward by combining several local optimized or hypo-optimized Profile HMMs to improve the probability to obtain a global ontimized HMM.
出处
《昆明理工大学学报(理工版)》
2007年第1期50-53,共4页
Journal of Kunming University of Science and Technology(Natural Science Edition)