Detecting Clusters in Atom Probe Data with Gaussian Mixture Models
Detecting Clusters in Atom Probe Data with Gaussian Mixture Models
复制标题
使用高斯混合模型检测原子探针数据中的簇
DOI：
10.1017/s1431927617000320
复制
发表时间：
2017
影响因子：
2.8
通讯作者：
M. Moody
中科院分区：
文献类型：
--
作者：
J. Zelenty;A. Dahl;J. Hyde;George D. W. Smith;M. Moody
摘要从原子探针层析成像（APT）重建中准确识别和提取团簇是一项极具挑战性的工作，但对许多应用至关重要。目前，最流行的方法来检测集群是最大的分离方法，启发式，严重依赖于用户手动选择的参数。在这项工作中，一个新的聚类算法，高斯混合模型的期望最大化算法（GEMA）的发展。GEMA利用高斯混合模型从概率上区分集群和矩阵中的随机波动。这种机器学习方法通过期望最大化来最大化数据可能性：给定原子位置，算法学习每个聚类的位置，大小和宽度。GEMA的一个关键优势是原子被概率性地分配到簇，从而反映了关于位于沉淀物/基质界面附近的原子的科学上有意义的不确定性。GEMA优于最大分离方法的聚类检测精度时，应用到几个现实的模拟数据集。最后，将GEMA方法成功地应用于真实的APT数据。
Abstract Accurately identifying and extracting clusters from atom probe tomography (APT) reconstructions is extremely challenging, yet critical to many applications. Currently, the most prevalent approach to detect clusters is the maximum separation method, a heuristic that relies heavily upon parameters manually chosen by the user. In this work, a new clustering algorithm, Gaussian mixture model Expectation Maximization Algorithm (GEMA), was developed. GEMA utilizes a Gaussian mixture model to probabilistically distinguish clusters from random fluctuations in the matrix. This machine learning approach maximizes the data likelihood via expectation maximization: given atomic positions, the algorithm learns the position, size, and width of each cluster. A key advantage of GEMA is that atoms are probabilistically assigned to clusters, thus reflecting scientifically meaningful uncertainty regarding atoms located near precipitate/matrix interfaces. GEMA outperforms the maximum separation method in cluster detection accuracy when applied to several realistically simulated data sets. Lastly, GEMA was successfully applied to real APT data.
影响因子：
9.4
作者：
A. London;S. Santra;S. Amirthapandian;B. Panigrahi;R. M. Sarguna;S. Balaji;R. Vijay;C. S. Sundar-C.-S.-Sun
通讯作者：
A. London;S. Santra;S. Amirthapandian;B. Panigrahi;R. M. Sarguna;S. Balaji;R. Vijay;C. S. Sundar-C.-S.-Sun