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

Design Example01:23

Design Example

698
The innovation of touch-tone telephony revolutionized the telecommunications industry by replacing the traditional rotary dial with a dual-tone multi-frequency (DTMF) signaling system. This system uses a matrix-style keypad with buttons arranged in four rows and three columns, creating 12 distinct signals each assigned to a pair of frequencies. Each button press results in a simultaneous generation of two sinusoidal tones – one from a low-frequency group (697 to 941 Hz) and one from a...
698

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

Detection of <i>Streptococcus uberis</i> in Bovine Milk Using a Simplified DNA Preparation Method and Colorimetric LAMP Assay.

Animals : an open access journal from MDPI·2026
Same author

Beyond diagnosis: AI-based surgical risk assessment in Acanthamoeba keratitis with real-world validation.

The ocular surface·2026
Same author

Artificial intelligence-assisted diagnosis and subtype differentiation of infectious keratitis.

Eye (London, England)·2026
Same author

Loop-Mediated Isothermal Amplification (LAMP) Assay for the Detection of Bacterial Bovine Mastitis: A Systematic Review.

Veterinary medicine and science·2026
Same author

A field-ready colourimetric LAMP assay for detection of Mycoplasma gallisepticum using rapid DNA extraction.

Research in veterinary science·2026
Same author

Field-deployable molecular workflow for detection, resistance screening, and genotyping of Staphylococcus aureus in bovine mastitis.

Veterinary journal (London, England : 1997)·2026

相关实验视频

Updated: May 3, 2026

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K

有效地改进基于Wi-Fi的人类活动识别,使用听觉功能,自动编码器和微调.

Amir Rahdar1, Mahnaz Chahoushi1, Seyed Ali Ghorashi2

  • 1AIFA, Dotin, Tehran, 1915718181, Iran.

Computers in biology and medicine
|March 14, 2024
PubMed
概括

这项研究通过使用Wi-Fi通道状态信息 (CSI) 和深度学习来增强人类活动识别 (HAR). 预训练的编码器在有限的数据中显著提高了准确性,性能提高了17.7%.

关键词:
自动编码器自动编码器频道状态信息 频道状态信息深度学习是一种深度学习.精细调整 微调 精细调整人类活动识别 人类活动识别机器学习 机器学习梅尔的频率是塞普斯特拉尔系数.

更多相关视频

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K
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

3.8K

相关实验视频

Last Updated: May 3, 2026

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

8.9K
Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.0K
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

3.8K

科学领域:

  • * 计算机科学 计算机科学
  • * * 信号处理 信号处理
  • * 机器学习 * 机器学习

背景情况:

  • *使用Wi-Fi信号的人类活动识别 (HAR) 正在因基础设施的可用性而获得吸引力.
  • *有限的培训数据是实现HAR高精度的一个重大挑战.
  • *通道状态信息 (CSI) 反映了Wi-Fi信号传播,但需要大量数据进行有效分析.

研究的目的:

  • *为HAR开发深度学习模型,以显著减少的训练数据实现高精度.
  • * 为了利用预训练的编码器在基于Wi-Fi的HAR中高效地提取功能.
  • * 评估预训练编码器在数据约束下提高HAR性能方面的有效性.

主要方法:

  • * 采用了经过 Mel 频率 Cepstral 系数 (MFCC) 训练的多输入多输出自动编码器 (MIMO AE) 的预训练编码器.
  • *采用了微调策略,将预训练的编码器纳入深度学习分类器中的固定层.
  • *使用K倍交叉验证 (K=5) 评估模型性能,训练数据有限 (30%的可用数据).

主要成果:

  • * 拟议的方法仅使用30%的培训/验证数据实现了90.3%的准确性,比没有编码器的分类器提高了17.7% (79.3%的准确性).
  • *使用预训练的编码器作为固定层证明了显著的效率,当作为可训练层处理时,准确度增长最小 (2.4%).
  • * 这种方法有效地解决了基于Wi-Fi的HAR中的数据稀缺性挑战.

结论:

  • * 一个预训练的编码器显著提高了使用Wi-Fi信号的HAR准确性,即使训练数据有限.
  • * 拟议的微调方法为数据受限制的HAR应用提供了高效和有效的解决方案.
  • * 这种技术对依赖Wi-Fi基础设施的实际HAR系统具有很大的前景.