Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Polymer Classification: Crystallinity01:21

Polymer Classification: Crystallinity

3.7K
Unlike ionic or small covalent molecules, polymers do not form crystalline solids due to the diffusion limitations of their long-chain structures. However, polymers contain microscopic crystalline domains separated by amorphous domains.
Crystalline domains are the regions where polymer chains are aligned in an orderly manner and held together in proximity by intermolecular forces. For example, chains in the crystalline domains of polyethylene and nylon are bound together by van der Waals...
3.7K
Structures of Solids02:22

Structures of Solids

17.4K
Solids in which the atoms, ions, or molecules are arranged in a definite repeating pattern are known as crystalline solids. Metals and ionic compounds typically form ordered, crystalline solids. A crystalline solid has a precise melting temperature because each atom or molecule of the same type is held in place with the same forces or energy. Amorphous solids or non-crystalline solids (or, sometimes, glasses) which lack an ordered internal structure and are randomly arranged. Substances that...
17.4K
Force Classification01:22

Force Classification

2.2K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.2K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Soft Matter: A Tale of Eco-Friendly Materials, Self-Organised Phases and Biological Impact.

Materials (Basel, Switzerland)·2026
Same author

Diverse helical structures made of achiral mesogenic dimers.

Nature communications·2026
Same author

Investigating room temperature ferroelectric nematogens and their structure-property relationships.

Nature communications·2026
Same author

The effect of thioester linkages on the stability of the ferroelectric nematic phase.

Soft matter·2026
Same author

Interplay of Polar Order and Positional Order in Liquid Crystals-Observation of Re-entrant Ferroelectric Nematic Phase.

Angewandte Chemie (International ed. in English)·2025
Same author

Twist Grain Boundary Phases in Proper Ferroelectric Liquid Crystals Realm.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

相关实验视频

Updated: Jan 9, 2026

High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal
06:24

High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal

Published on: October 31, 2019

6.8K

通过机器学习区分液晶内马特变体.

Alexander R Quinn1, Rebecca Walker2, Naila Tufaha2

  • 1Department of Physics and Astronomy, University of Manchester, Oxford Road, Manchester, M13 9PL, UK. ingo.dierking@manchester.ac.uk.

Soft matter
|December 8, 2025
PubMed
概括

机器学习模型准确地区分液晶相. 具有翻转增强的3层卷积神经网络 (CNN) 达到超过0.96的准确性,证明有效地识别阴性变异.

更多相关视频

Novel Techniques for Observing Structural Dynamics of Photoresponsive Liquid Crystals
10:35

Novel Techniques for Observing Structural Dynamics of Photoresponsive Liquid Crystals

Published on: May 29, 2018

9.1K
Orientational Transition in a Liquid Crystal Triggered by the Thermodynamic Growth of Interfacial Wetting Sheets
06:26

Orientational Transition in a Liquid Crystal Triggered by the Thermodynamic Growth of Interfacial Wetting Sheets

Published on: May 15, 2017

7.5K

相关实验视频

Last Updated: Jan 9, 2026

High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal
06:24

High-Contrast and Fast Photorheological Switching of a Twist-Bend Nematic Liquid Crystal

Published on: October 31, 2019

6.8K
Novel Techniques for Observing Structural Dynamics of Photoresponsive Liquid Crystals
10:35

Novel Techniques for Observing Structural Dynamics of Photoresponsive Liquid Crystals

Published on: May 29, 2018

9.1K
Orientational Transition in a Liquid Crystal Triggered by the Thermodynamic Growth of Interfacial Wetting Sheets
06:26

Orientational Transition in a Liquid Crystal Triggered by the Thermodynamic Growth of Interfacial Wetting Sheets

Published on: May 15, 2017

7.5K

科学领域:

  • 材料科学 材料科学 材料科学
  • 凝聚物质物理学 凝聚物质物理学
  • 机器学习 机器学习

背景情况:

  • 液晶表现出各种各样的相位,包括铁电和扭曲曲线.
  • 区分这些相对于理解它们的特性和应用至关重要.
  • 机器学习为自动化阶段识别提供了潜力.

研究的目的:

  • 评估序列卷积神经网络 (CNN) 和并行开始模型,以识别阴性液晶变体.
  • 为了确定最佳的模型复杂性和数据增强策略,以准确地进行相位分类.
  • 评估不同机器学习架构在区分铁电和扭曲曲内马特相的性能.

主要方法:

  • 在液晶数据上训练CNN (1-5层) 和初始模型 (1-3块).
  • 应用数据增强技术,包括翻转,对比度和亮度.
  • 集成的脱落层规范化,以防止过.
  • 系统地分析了每个模型配置的准确性和错误率.

主要成果:

  • 翻转增强显著提高了准确性,而掉队调整通常会降低准确性.
  • 一个三层CNN或一个单一的初始块模型实现了0.96-0.98±0.01的准确度与翻转增强.
  • 序列CNN足以对多达四个内马特相的序列进行分类.
  • 接近100%的更高准确度可以通过更大,类平衡的数据集实现.

结论:

  • 机器学习模型,特别是三层CNN,可以可靠地区分阴性液晶变体.
  • 翻转增强是提高分类准确性的关键技术.
  • 对于具有四个或更少阶段的数据集,顺序CNN提供了一个计算效率高的解决方案.
  • 初始模型可能为更大的数据集提供好处,只要管理过拟合.