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

Aliasing01:18

Aliasing

154
Accurate signal sampling and reconstruction are crucial in various signal-processing applications. A time-domain signal's spectrum can be revealed using its Fourier transform. When this signal is sampled at a specific frequency, it results in multiple scaled replicas of the original spectrum in the frequency domain. The spacing of these replicas is determined by the sampling frequency.
If the sampling frequency is below the Nyquist rate, these replicas overlap, preventing the original...
154
Discrete Fourier Transform01:15

Discrete Fourier Transform

318
The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
318
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

106
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
106
Upsampling01:22

Upsampling

254
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
254

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

Integrated policies could raise China's soybean self-sufficiency and ease global land-use pressure.

Nature food·2026
Same author

Exploring Toxicological Mechanisms of Typical PFAS-Induced NAFLD through Integrated Computational Toxicology and AOP Frameworks.

Environment & health (Washington, D.C.)·2026
Same author

Interpretable machine learning distinguishes skip from continuous metastasis in N1b papillary thyroid carcinoma.

Scientific reports·2026
Same author

Distribution of urinary stone composition and its associations with age, sex, and temporal factors among 3901 patients in Xiamen: A 13-year single-center retrospective study.

Medicine·2026
Same author

Ubiquitin-specific peptidase 39 promotes hepatocyte proliferation by targeting the Wnt/β-catenin signaling pathway.

International journal of biological macromolecules·2026
Same author

Ionomic, metabolomic, and enzymatic responses of the sea cucumber Apostichopus japonicus to single and combined salinity and metal stress.

Comparative biochemistry and physiology. Part D, Genomics & proteomics·2026

相关实验视频

Updated: Jul 16, 2025

Functional Near-Infrared Spectroscopy Hyperscanning Study in Psychological Counseling
06:04

Functional Near-Infrared Spectroscopy Hyperscanning Study in Psychological Counseling

Published on: January 17, 2025

588

一个对抗性的时间频率重建网络,用于无监督的异常检测.

Jin Fan1, Zehao Wang2, Huifeng Wu2

  • 1Department of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China; Zhejiang Provincial Key Laboratory of Industrial Internet in Discrete Industries, China.

Neural networks : the official journal of the International Neural Network Society
|September 23, 2023
PubMed
概括

本研究介绍了对抗性时间频率重建网络用于无监督异常检测 (ATF-UAD),以改进多变量时间序列数据中的异常检测. 通过准确识别和定位异常,ATF-UAD提高了系统稳定性,优于现有的方法.

关键词:
异常检测检测异常检测神经网络的神经网络的神经网络没有监督的异常检测检测.

更多相关视频

Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.4K
Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.4K

相关实验视频

Last Updated: Jul 16, 2025

Functional Near-Infrared Spectroscopy Hyperscanning Study in Psychological Counseling
06:04

Functional Near-Infrared Spectroscopy Hyperscanning Study in Psychological Counseling

Published on: January 17, 2025

588
Cortical Source Analysis of High-Density EEG Recordings in Children
09:32

Cortical Source Analysis of High-Density EEG Recordings in Children

Published on: June 30, 2014

21.4K
Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients
09:32

Network Analysis of Foramen Ovale Electrode Recordings in Drug-resistant Temporal Lobe Epilepsy Patients

Published on: December 18, 2016

12.4K

科学领域:

  • 数据科学数据科学数据科学
  • 机器学习 机器学习
  • 信号处理 信号处理

背景情况:

  • 在大规模的多变量时间序列数据中检测异常,特别是来自物联网 (IoT) 的数据,对于系统稳定性至关重要.
  • 现有的基于重建的异常检测方法与未标记的数据作斗争,这阻碍了它们区分正常和异常样本的能力,并准确地重建异常.
  • 当前模型的局限性包括异常值的重建不良以及不精确的异常定位.

研究的目的:

  • 为多变量时间序列数据开发一个先进的无监督异常检测模型.
  • 解决现有方法在处理未标记数据和准确重建异常方面的局限性.
  • 引入对抗性时间频率重建网络用于无监督异常检测 (ATF-UAD).

主要方法:

  • ATF-UAD采用双视图对抗式学习机制,具有单独的时间和频率重建器.
  • 时间重建器使用平价采样,注意力机制和图形卷积网络 (GCNs) 来削弱点依赖性和稀释异常影响.
  • 频率重建器利用里埃变换来分析和重建异常频段.

主要成果:

  • 在9个不同的数据集中,ATF-UAD表现出卓越的性能.
  • 与最先进的方法相比,该模型实现了6.94%的F1平均得分改善.
  • 双视图对抗式学习有效地减少了重建错误,并最大限度地识别了异常.

结论:

  • 在复杂的时间序列数据中,ATF-UAD提供了一个强大的解决方案,用于无监督的异常检测.
  • 拟议的网络有效地区分正常和异常的数据点,并精确地定位异常.
  • 该方法显示了物联网和其他需要可靠异常检测的领域的应用的巨大潜力.