Convolutional Network Analysis of Optical Micrographs for Liquid Crystal Sensors
Convolutional Network Analysis of Optical Micrographs for Liquid Crystal Sensors
复制标题
DOI：
10.1021/acs.jpcc.0c01942
复制
发表时间：
2020-07-16
影响因子：
3.7
通讯作者：
Zavala, Victor M.
中科院分区：
文献类型：
--
作者：
Smith, Alexander D.;Abbott, Nicholas;Zavala, Victor M.
我们提供了一个深入的卷积神经网络（CNN）分析液晶（LC）暴露于不同化学环境时的光学响应。我们的目标是确定信息功能，可用于构建自动LC为基础的化学传感器，并揭示了一些光的基本现象，管理和区分LC响应。先前的工作表明，通过使用从AlexNet提取的特征，可以以99%的准确率对不同LC响应的灰度显微图像进行分类。然而，要达到如此高的准确度，需要使用大量的特征（数千个数量级），这是计算密集型的，并使主要特征的物理可解释性变得模糊。为了解决这些问题，我们在这里报告了一项关于使用VGG 16从彩色显微照片中提取特征的有效性的研究，VGG 16是一种比Alexnet更紧凑的CNN。我们的分析表明，从VGG 16的第一和第二卷积层提取的特征足以实现完美的分类精度，同时将特征数量减少到100以下。通过递归消除，特征的数量进一步减少到10个，分类精度损失最小（5-10%）。这种还原过程揭示了空间颜色模式的差异在LC响应中在几秒钟内产生。由此，我们得出结论，色调分布提供了一组信息丰富的功能，可用于表征LC传感器的响应。我们还假设，VGG 16与DMMP和水检测到的LC纹理的空间相关长度的差异可能反映了传感器表面上LC的锚定能量的差异。我们的研究结果暗示了新的方法，用于基于LC的传感器的设计的基础上的自发波动的方向（而不是在文献中报道的时间平均方向的变化）的表征。
We provide an in-depth convolutional neural network (CNN) analysis of optical responses of liquid crystals (LCs) when exposed to different chemical environments. Our aim is to identify informative features that can be used to construct automated LC-based chemical sensors and shed some light on the underlying phenomenon that governs and distinguishes LC responses. Previous work demonstrated that, by using features extracted from AlexNet, grayscale micrographs of different LC responses can be classified with an accuracy of 99%. Reaching such high levels of accuracy, however, required the use of a large number of features (on the order of thousands), which was computationally intensive and clouded the physical interpretability of the dominant features. To address these issues, here we report a study on the effectiveness of using features extracted from color micrographs using VGG16, which is a more compact CNN than Alexnet. Our analysis reveals that features extracted from the first and second convolutional layers of VGG16 are sufficient to achieve a perfect classification accuracy while reducing the number of features to less than 100. The number of features is further reduced to 10 via recursive elimination with a minimal loss in classification accuracy (5-10%). This reduction procedure reveals that differences in spatial color patterns are developed within seconds in the LC response. From this, we conclude that hue distributions provide an informative set of features that can be used to characterize LC sensor responses. We also hypothesize that differences in the spatial correlation length of LC textures detected by VGG16 with DMMP and water likely reflect differences in the anchoring energy of the LC on the surface of the sensor. Our results hint at fresh approaches for the design of LC-based sensors based on the characterization of spontaneous fluctuations in the orientation (as opposed to changes in time-average orientations reported in the literature).