Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

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

An interactive machine learning platform for analyzing multi-particle coincidence data from cold target recoil ion momentum spectroscopy.

The Review of scientific instruments·2026

Same author

Optimizing inference of segmentation on high-resolution images in MLExchange.

The Journal of supercomputing·2025

Same author

Deploying Machine Learning Based Segmentation for Scientific Imaging Analysis at Synchrotron Facilities.

IS&T International Symposium on Electronic Imaging·2023

Same author

MLExchange: A web-based platform enabling exchangeable machine learning workflows for scientific studies.

Annual Workshop on Extreme-scale Experiment-in-the-Loop Computing : XLOOP. Annual Workshop on Extreme-scale Experiment-in-the-Loop Computing·2023

Same author

A comparison of deep-learning-based inpainting techniques for experimental X-ray scattering.

Journal of applied crystallography·2022

Same author

GPU-accelerated multitiered iterative phasing algorithm for fluctuation X-ray scattering.

Journal of applied crystallography·2021

Same journal

Quantitative analysis of light-induced ion segregation in mixed-halide perovskites.

Journal of applied crystallography·2026

Same journal

Towards machine-learning-based on-the-fly analysis of neutron reflectometry.

Journal of applied crystallography·2026

Same journal

<i>mcstas_gisans</i>: combining ray tracing with the distorted-wave Born approximation using <i>McStas</i> and <i>BornAgain</i> for virtual GISANS experiments.

Journal of applied crystallography·2026

Same journal

Computational methods for automated center determination in electron diffraction patterns.

Journal of applied crystallography·2026

Same journal

Epitaxy of ultrathin Fe<sub>3</sub>O<sub>4</sub> films on SrTiO<sub>3</sub>(001): influence of growth parameters on the formation of coexisting (111)- and (001)-oriented phases.

Journal of applied crystallography·2026

Same journal

Spin excitations near the pressure-induced antiferromagnetic transition in SrCu<sub>2</sub>(BO<sub>3</sub>)<sub>2</sub>.

Journal of applied crystallography·2026

查看所有相关文章

Search research articles

相关实验视频

Updated: Jun 28, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

DLSIA:用于科学图像分析的深度学习

Eric J Roberts^1,2, Tanny Chavez³, Alexander Hexemer^1,3

¹Center for Advanced Mathematics for Energy Research Applications, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.

Journal of applied crystallography

|April 10, 2024

概括

此摘要是机器生成的。

科学图像分析的深度学习 (DLSIA) 为科学家提供了可定制的神经网络,用于图像分析任务. 这个Python库简化了复杂的机器学习,加速了跨科学领域的研究和数据处理.

关键词:

在X射线中散射.卷积神经网络是一种卷积神经网络.数据压缩数据压缩.深度学习是一种深度学习.断层扫描 (tomography) 是一个非常重要的技术.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: Jun 28, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

科学领域:

科学图像分析科学图像分析
机器学习是机器学习.
数据处理数据处理.

背景情况:

实验数据的规模和复杂性越来越大,需要先进的图像分析工具.
传统的方法与大型,复杂的科学图像数据集作斗争.
在研究中需要可访问和可定制的机器学习解决方案.

研究的目的:

介绍科学图像分析的深度学习 (DLSIA),这是一个用于科学图像分析的Python库.
为科学家提供可定制的卷积神经网络 (CNN) 架构,用于各种图像分析任务.
简化深度学习在科学研究中的应用.

主要方法:

开发了DLSIA,这是一个Python库,具有可定制的CNN架构,如自动编码器,U-Nets和混合规模密集网络 (MSDNets).
引入了使用随机图,稀疏连接和扩展卷积的稀疏混合规模网络 (SMSNets).
采用了DLSIA网络和培训脚本,用于包括inpainting,3D光纤细分和数据压缩/集群在内的应用.

主要成果:

展示了DLSIA在使用U-Nets和MSDNets的X射线散射数据的实用性.
在混凝土中使用一组SMSNets.成功地分割了3D纤维.
展示了自动编码器隐藏空间,以进行有效的数据压缩和集群.

结论:

DLSIA提供了可访问的CNN构建,为科学家抽象复杂性.
该图书馆允许量身定制的机器学习方法,加速科学发现.
促进跨学科的合作,并推进科学图像分析研究.