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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

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

Development and validation of an explainable prediction model for post-stroke epilepsy in patients with ischaemic stroke following mechanical thrombectomy: a multicentre retrospective cohort study.

Stroke and vascular neurology·2026

Same author

Evaluation of Changes in Peri-Pelvic Musculature in Ankylosing Spondylitis Using mDixon-Quant and T2 Mapping.

Academic radiology·2026

Same author

AI-assisted MRI segmentation analysis of brain region volume alterations in Parkinson's disease.

Frontiers in human neuroscience·2025

Same author

Impact of Collateral Circulation on Poststroke Epilepsy After Mechanical Thrombectomy for Large Vessel Occlusive Stroke: A Multicenter Cohort Study.

European journal of neurology·2025

Same author

Clinical Application of an AI-Driven Framework for Accurate Endometrial Thickness Measurement in Transvaginal Ultrasound.

Ultrasound in medicine & biology·2025

Same author

FLT3L combined with GM-CSF induced dendritic cells drive broad tumor-specific CD8<sup>+</sup> T cell responses and remodel the tumor microenvironment to enhance anti-tumor efficacy.

Frontiers in immunology·2025

Search research articles

相关实验视频

Updated: Jul 5, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

基于并行学习的异常检测选择组合方法.

Yansong Liu^1,2, Li Zhu¹, Lei Ding³

¹School of Software Engineering, Xi'an Jiao Tong University, Xi'an, China.

Scientific reports

|January 16, 2024

概括

本研究引入了使用并行学习 (SEAD-PL) 进行异常检测的选择组合方法. 它解决了数据不平衡和计算需求,提高了有效检测异常的概括能力.

更多相关视频

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

相关实验视频

Last Updated: Jul 5, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Design and Analysis for Fall Detection System Simplification

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

科学领域:

数据科学数据科学数据科学
机器学习机器学习
人工智能的人工智能

背景情况:

在数据分析中,异常检测至关重要,但传统方法在数据特征方面存在困难.
合并方法提高了概括性,但面临着数据不平衡和资源需求等挑战.
现有的集体异常检测技术需要仔细选择基探测器.

研究的目的:

提出一种基于并行学习 (SEAD-PL) 的新型选择组合方法来检测异常.
解决整体异常检测的关键挑战,包括数据不平衡,时间/空间复杂性和基础探测器选择.
提高异常检测系统的概括能力和性能.

主要方法:

实施了差异化分层抽样方法,以减轻数据不平衡.
开发了一个分布式并行训练框架,以优化基础探测器训练的时间和空间效率.
利用基于集群的集合选择策略来平衡探测器的准确性和多样性.

主要成果:

拟议的SEAD-PL方法比其他四种选择的方法具有显著的优势.
在六个不同的数据集上进行的实验验验证了SEAD-PL方法的有效性.
该方法成功地缓解了数据不平衡,并减少了计算资源需求.

结论:

SEAD-PL方法为异常检测提供了有效的解决方案,特别是在数据不平衡和大数据集的场景中.
平行学习框架和基于集群的选择策略提高了整体异常检测的性能和可扩展性.
这种方法为传统的异常检测技术提供了强大而有效的替代方案.