Flexible Unsupervised Binary Change Detection Algorithm Identifies Phase Transitions in Continuous Image Streams

Flexible Unsupervised Binary Change Detection Algorithm Identifies Phase Transitions in Continuous Image Streams
复制标题

灵活的无监督二进制变化检测算法识别连续图像流中的相变

DOI:
10.1007/s40192-021-00199-3
复制
发表时间:
2021
影响因子:
3.3
通讯作者:
Shahani, Ashwin J.
Shahani, Ashwin J.
中科院分区:
材料科学3区
文献类型:
--
作者:
Chao, Paul;Xiao, Xianghui;Shahani, Ashwin J.

文献摘要

参考文献

相似文献

在原位层析成像实验中收集的投影图像序列可以捕捉到结晶过程中图案的形成,并得到它们的三维生长形貌。这些图像流生成跨越整个相变范围的海量高维数据集。从连续的图像流中检测相变开始的特征时间和温度是一项挑战,因为相变通常是快速和微妙的。在这里,我们提出了一种灵活的无监督二进制分类算法来识别数据密集型实验中的变化点。该算法基于统计度量进行预测,并且具有可量化的误差界。在同步辐射光源下采集的两个原位X射线层析实验数据上,该方法可以检测到固相在结晶时从母液相中出现的时刻,而不需要进行计算代价高昂的体积重建。使用模拟的X射线体模对我们的方法进行了验证,并根据凝固参数对其性能进行了评估。本文提出的方法可以广泛应用于其他大数据问题,其中时间序列可以在不需要额外训练数据的情况下进行分类。
Sequences of projection images collected during in situ tomography experiments can capture the formation of patterns in crystallization and yield their three-dimensional growth morphologies. These image streams generate enormous and high dimensional datasets that span the full extent of a phase transition. Detecting from the continuous image stream the characteristic times and temperatures at which the phase transition initiates is a challenge because the phase change is often swift and subtle. Here, we show a flexible unsupervised binary classification algorithm to identify a change point during data intensive experiments. The algorithm makes a prediction based on statistical metrics and has a quantifiable error bound. Applied to two in situ X-ray tomography experimental datasets collected at a synchrotron light source, the developed method can detect the moment at which the solid phase emerges from the parent liquid phase upon crystallization and without performing computationally expensive volume reconstructions. Our approach is verified using a simulated X-ray phantom and its performance evaluated with respect to solidification parameters. The method presented here can be broadly applied to other Big Data problems where time series can be classified without the need for additional training data.
DOI: 10.1103/physrevmaterials.4.063403
发表时间: 2020
影响因子: 3.4
作者:
Moniri, Saman;Xiao, Xianghui;Shahani, Ashwin J.
通讯作者: Shahani, Ashwin J.
DOI: 10.1021/acs.jpcb.9b09621
发表时间: 2020-01-09
影响因子: 3.3
作者:
Adorf, Carl S.;Moore, Timothy C.;Glotzer, Sharon C.
通讯作者: Glotzer, Sharon C.
异质成核和微观结构形成:从模型系统到应用金属物理学
DOI: --
发表时间: 2014
期刊:
影响因子: --
作者:
H. Emmerich
通讯作者: H. Emmerich
DOI: 10.1107/s2053273318017114
发表时间: 2019-03-01
影响因子: 1.8
作者:
Han, Insung;Xiao, Xianghui;Shahani, Ashwin J.
通讯作者: Shahani, Ashwin J.
DOI: 10.1038/s41598-017-17821-0
发表时间: 2017-12-12
期刊: Scientific reports
影响因子: 4.6
作者:
Han I;Xiao X;Shahani AJ
通讯作者: Shahani AJ