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

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

Rare Eating Epilepsy: Co-Occurrence of Focal Cortical Dysplasia and Gray Matter Heterotopia.

Neurology·2026
Same author

Parallel multi-channel chaos synchronization based on electro-optic frequency combs.

Optics express·2026
Same author

Dietary fiber supplementation mitigates gestational diabetes risk and preterm birth via gut microbiota modulation: a randomized controlled trial.

Frontiers in endocrinology·2026
Same author

Integrative Single-Cell Transcriptomics and Network Pharmacology Analysis of Xiao Qing Long Tang in Pediatric Cough-Variant Asthma.

International journal of genomics·2026
Same author

Impact of neoadjuvant imatinib duration and tumor response on recurrence-free survival in locally advanced gastrointestinal stromal tumors: a retrospective multicenter cohort study.

World journal of surgical oncology·2026
Same author

Precision Colloidal Polymerization of Hierarchical Gold Nanocluster Assemblies.

ACS nano·2026

相关实验视频

Updated: Jun 3, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

2.6K

时间逻辑注意网络用于分布式系统中基于日志的异常检测.

Yang Liu1, Shaochen Ren2, Xuran Wang3

  • 1Department of Computer Science, Worcester Polytechnic Institute, Worcester, MA 01609, USA.

Sensors (Basel, Switzerland)
|January 8, 2025
PubMed
概括
此摘要是机器生成的。

本研究介绍了一个时间逻辑注意网络 (TLAN),用于分布式系统中先进的异常检测. TLAN通过建模时间和逻辑依赖来增强日志分析,提高准确性和减少错误报警.

关键词:
检测异常检测异常检测深度学习是一种深度学习.分布式系统日志 分布式系统日志时间逻辑模型模型

更多相关视频

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K
Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

9.8K

相关实验视频

Last Updated: Jun 3, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

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

Published on: December 15, 2023

2.6K
Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example
08:45

Mapping Cortical Dynamics Using Simultaneous MEG/EEG and Anatomically-constrained Minimum-norm Estimates: an Auditory Attention Example

Published on: October 24, 2012

14.6K
Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments
13:00

Measuring Attention and Visual Processing Speed by Model-based Analysis of Temporal-order Judgments

Published on: January 23, 2017

9.8K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 系统工程 系统工程

背景情况:

  • 在分布式系统中检测异常是复杂的,因为时间依赖性,不同的状态和因果关系.
  • 日志分析对于识别各组件间微妙异常至关重要,但具有挑战性.

研究的目的:

  • 引入一种新的深度学习框架,即时间逻辑注意网络 (TLAN),用于在分布式系统日志中进行强大的异常检测.
  • 解决记录数据中捕获复杂的时间和逻辑模式的现有方法的局限性.

主要方法:

  • 开发了一个时间逻辑注意力机制来建模时间序列模式和分布式组件之间的逻辑依赖.
  • 实施了多尺度特征提取模块,以捕捉各种时间细分度的系统行为.
  • 引入了基于系统负载和相互作用的动态检测灵敏度调整的自适应值策略.

主要成果:

  • 与现有方法相比,TLAN在F1得分上取得了9.4%的改善,虚假报警减少了15.3%.
  • 为实时异常检测证明了低延迟.
  • 在识别涉及多个组件和级联故障的复杂异常方面表现出有效性.

结论:

  • TLAN有效地捕捉了日志序列中的时间模式和逻辑相关性,使其适合于现代分布式架构.
  • 该框架在不同的系统尺度和部署场景中表现出强大的概括能力.
  • 在分布式系统日志异常检测方面,TLAN提供了显著的进步.