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

Special considerations while measuring pulse

Special considerations while measuring pulse

Assessing a patient's pulse is a fundamental skill in healthcare, but certain situations require special attention:

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

Monte Carlo studies on Fully Bayesian Unfolding for a multi-layer silicon beta-ray spectrometer.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2026

Same author

Development of ecocentric radiation protection: issues, challenges and approaches.

International journal of radiation biology·2025

Same author

NeutralNet: an application of deep neural networks to pulse shape discrimination for use with accelerator-based neutron sources.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2025

Same author

High-rate Gamma Spectrometry Using a LaBr3(Ce) Scintillator with a Fast Pulse Shaping.

Health physics·2024

Same author

Optimization and characterization of a coincidence beta-ray spectrometer.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine·2023

Same author

Isolation of the effects of alpha-related components from total effects of radium at low doses.

International journal of radiation biology·2020

Search research articles

相关实验视频

Updated: May 13, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

中性网:开发和测试用于脉冲形状歧视的机器学习解决方案.

Richard L Garnett¹, Soo Hyun Byun¹

¹Department of Physics and Astronomy, McMaster University, Hamilton, ON, L8S 4K1, Canada.

Applied radiation and isotopes : including data, instrumentation and methods for use in agriculture, industry and medicine

|June 18, 2024

概括

机器学习,特别是修改后的GoogLeNet,使用液体闪器显著改善了中子探测. 这种方法在混合辐射场中实现了高精度的中子与光子的区分.

科学领域:

核仪器仪表和测量核仪器仪表和测量核仪器仪表和测量
应用机器学习应用机器学习
辐射检测物理辐射检测

背景情况:

鉴定中子辐射场的特征是具有挑战性的,因为探测器的灵敏度和混合环境中的二次粒子生成.
液体闪器中的脉冲形状歧视 (PSD) 对于在其他辐射类型中识别中子至关重要.

研究的目的:

开发和评估机器学习架构,以增强液体闪器中的脉冲形状歧视.
调查数字化器采样参数对中子检测机器学习算法性能的影响.

主要方法:

使用了EJ-301液晶闪电器和CAEN DT-5743数字化器 (3.2 GHz,12位分辨率).
使用238Pu9Be和241Am9Be中子源和24Na,60Co,137Cs光子源用于数据生成.
测试了各种机器学习架构,包括修改的GoogLeNet,具有不同的数字化采样率和位深度.

主要成果:

一个经过修改的GoogLeNet架构实现了最高的性能,中子识别的真正阳性率为69.17%.
实现了99.9999%的异常光子排斥率.
性能与中子能量有所不同,从1.30%在>3 MeVee到89.96%在340-1000 keVee之间,其中21.48%的识别低于200 keVee.

关键词:

机器学习机器学习中子的玛分离.脉冲形状的歧视脉冲形状的歧视

更多相关视频

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

相关实验视频

Last Updated: May 13, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

结论:

机器学习,特别是优化的GoogleLeNet,显著提高了混合辐射场中的中子探测能力.
全数字化器采样速率和位深度对于实现基于机器学习的PSD的最佳性能至关重要.
开发的方法显示了准确的中子场表征的前景,特别是在较低的能量范围内.