arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.15224stat.ME
收藏

稀疏光滑函数型数据聚类

Sparse and Smooth Functional Data Clustering

Fabio Centofanti, Antonio Lepore, Biagio Palumbo

AI总结:

本研究提出稀疏光滑函数型聚类方法SaS-Funclust,结合函数型高斯混合模型与双重惩罚项,通过期望-条件最大化算法估计,在模拟和真实数据上均表现出更优的聚类性能与可解释性,已实现为R包开源可用。

摘要:

本文提出了一种基于模型的函数型数据稀疏聚类新流程,旨在将曲线样本划分为同质组,同时联合检测定义域中最具信息量的部分。该方法被称为稀疏光滑函数型聚类(SaS-Funclust),依托通用函数型高斯混合模型构建,通过最大化经函数型自适应成对惩罚项与粗糙度惩罚项惩罚的对数似然函数来估计模型参数。其中,自适应成对惩罚项通过将分离簇的均值收缩至某些共同值,识别出定义域内无信息的部分;粗糙度惩罚项则通过对估计的簇均值施加一定程度的平滑处理,提升可解释性。模型采用期望-条件最大化算法结合交叉验证流程进行估计。通过蒙特卡洛模拟研究证实,SaS-Funclust方法在聚类性能和可解释性两方面均优于现有文献中的其他方法。最后,本文通过三个真实数据示例,进一步验证了所提方法的优异性能。SaS-Funclust方法已在R包sasfunclust中实现,可通过链接https://github.com/unina-sfere/sasfunclust在线获取。

英文摘要:

A new model-based procedure is developed for sparse clustering of functional data that aims to classify a sample of curves into homogeneous groups while jointly detecting the most informative portions of domain. The proposed method is referred to as sparse and smooth functional clustering (SaS-Funclust) and relies on a general functional Gaussian mixture model whose parameters are estimated by maximizing a log-likelihood function penalized with a functional adaptive pairwise penalty and a roughness penalty. The former allows identifying the noninformative portion of domain by shrinking the means of separated clusters to some common values, whereas the latter improves the interpretability by imposing some degree of smoothing to the estimated cluster means. The model is estimated via an expectation-conditional maximization algorithm paired with a cross-validation procedure. Through a Monte Carlo simulation study, the SaS-Funclust method is shown to outperform other methods already appeared in the literature, both in terms of clustering performance and interpretability. Finally, three real-data examples are presented to demonstrate the favourable performance of the proposed method. The SaS-Funclust method is implemented in the $\textsf{R}$ package $\textsf{sasfunclust}$, available online at https://github.com/unina-sfere/sasfunclust.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑