基于完整似然最短信息长度准则的高斯混合模型聚类(英文)

Gaussian mixture model clustering with completed likelihood minimum message length criterion

针对数据真实的概率分布不符合事先假设的高斯混合模型的情形,提出了一种鲁棒的基于高斯混合模型的聚类方法.首先,提出了一种新的模型选择准则,即完整似然最短信息长度准则.该准则不仅能衡量模型对数据的拟合优度,还能度量该模型对数据分组的性能.然后,将该准则作为聚类的代价函数,提出了一种新的期望最大化算法来估计模型参数.与标准的期望最大化算法相比,新算法能较好地避免不理想的局部最优解.实验结果表明:当数据概率分布模型不符合假设的高斯混合模型时,所提方法可克服现有的基于高斯混合模型聚类方法过拟合的缺点,鲁棒地得到准确的聚类结果.

An improved Gaussian mixture model （GMM）- based clustering method is proposed for the difficult case where the true distribution of data is against the assumed GMM. First, an improved model selection criterion, the completed likelihood minimum message length criterion, is derived. It can measure both the goodness-of-fit of the candidate GMM to the data and the goodness-of-partition of the data. Secondly, by utilizing the proposed criterion as the clustering objective function, an improved expectation- maximization （EM） algorithm is developed, which can avoid poor local optimal solutions compared to the standard EM algorithm for estimating the model parameters. The experimental results demonstrate that the proposed method can rectify the over-fitting tendency of representative GMM-based clustering approaches and can robustly provide more accurate clustering results.