在微观超光谱数据上的多任务学习能够准确地对氧化石墨烯薄膜进行分类
Xinwei Dong1, Tao Zhang2, Fuxin Zheng1
1School of Electronic Engineering, Guangxi University of Science and Technology, Liuzhou 545006, China; Guangxi Key Laboratory of Multidimensional Information Fusion for Intelligent Vehicles, Liuzhou, China.
我们使用微观超光谱成像 (mHSI) 和深度学习开发了一种新的框架,以快速表征氧化石墨烯 (GO) 薄膜. 这种方法可以实现高精度的GO质量控制,克服传统技术的局限性.
科学领域:
- 材料科学 材料科学 材料科学
- 纳米技术纳米技术
- 数据科学数据科学数据科学
背景情况:
- 石墨烯氧化物 (GO) 的精确表征对于先进的应用至关重要,但因异质性而受到挑战.
- 像AFM这样的现有方法太慢,拉曼光谱受GO的障碍影响.
研究的目的:
- 开发一个新的,高通量框架,用于GO的特征.
- 将微观超光谱成像 (mHSI) 与多任务学习 (MTL) 深度神经网络相结合.
主要方法:
- 利用mHSI从GO电影中捕获详细的光谱信息.
- 开发和训练了一种MTL深度学习模型,用于将GO分类为3个主要类别和12个基于厚度的类别.
- 将MTL模型的性能与单任务学习 (STL) 模型和伪RGB图像分析进行比较.
主要成果:
- 在一个独立的测试套件上,在12类GO厚度任务中获得了97.1%的分类准确度.
- 与STL模型相比,MTL模型的错误率是STL模型的三倍以上.
- 超光谱数据至关重要,在使用伪RGB图像时,精度降至69.4%.
结论:
- 建立了一个强大的,数据驱动的材料表征范式.
- mHSI-MTL框架为GO质量控制提供了一个可扩展的,非破坏性的解决方案.
- 能够在基础研究和高吞吐量生产基于GO的设备方面取得进展.
更多相关视频
08:49Author Spotlight: Unveiling the Potential of VSFG Microscopy in Studying Mesoscopically Heterogeneous Self-Assembled Structures
Published on: December 1, 2023
07:57Author Spotlight: Enhancing CryoEM Sample Preparation Using Graphene Monolayer on Microscopy Grids
Published on: November 10, 2023
相关概念视频
Classifying Matter by Composition
According to its composition, the matter can be classified into two broad categories — pure substances and mixtures.
A pure substance is a form of matter that has a constant composition throughout with uniform properties. For example, any sample of sucrose has the same composition and same physical properties, such as melting point, color, and sweetness, regardless of the source from which it is isolated.
A mixture is composed of two or more types of...
Ultraviolet and Visible (UV–Vis) Spectroscopy: Overview
IR and UV–Vis Spectroscopy of Aldehydes and Ketones
UV–Vis Spectroscopy: Woodward–Fieser Rules
Super-resolution Fluorescence Microscopy
Classification of Titrimetric Analysis Based on Reaction Types
Titrations between an acid and a base lead to neutralization reactions that form...
