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

相关实验视频

Updated: Jun 28, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

使用二元化卷积神经网络进行芯片上学习的节能心电图分类器.

Rui Zhang, Ranran Zhou, Xinyi Han

    IEEE transactions on biomedical circuits and systems
    |September 17, 2025
    PubMed
    概括

    本研究引入了使用二元卷积神经网络 (bCNNs) 和芯片上学习的节能ECG分类器. 这种新的方法提高了准确性,并降低了可穿戴应用的功耗.

    相关概念视频

    Classification of Signals01:30

    Classification of Signals

    1.3K
    In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
    A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
    1.3K

    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

    Investigating the Shared Mechanisms of Endocrine-Disrupting Chemicals in Urogenital Tumors.

    Biology·2026
    Same author

    A High-Performance Bimetallic Ru<sub>1</sub>Mo<sub>6</sub> Active Site for Thermal Ammonia Synthesis under Mild Conditions.

    Journal of the American Chemical Society·2026
    Same author

    Boosting SERS Performance of TiO<sub>2</sub> Microspheres via Phytic Acid Modification: Application to Bisphenol A Detection in Consumer Products.

    ACS applied materials & interfaces·2026
    Same author

    Nitrogen fertilization increases soil organic carbon through distinct pathways in contrasting cropland soils.

    Science China. Life sciences·2026
    Same author

    Realizing efficient ammonia electrosynthesis enabled by metal-organic framework-derived CuCo-LDH.

    Physical chemistry chemical physics : PCCP·2026
    Same author

    Sustained-Release Reducing Microenvironment Tailors Highly Crystalline FeS<sub><i>x</i></sub> Shells on Zero-Valent Iron for Enhanced Electron Transfer.

    Environmental science & technology·2026

    科学领域:

    • 生物医学工程 生物医学工程
    • 人工智能的人工智能
    • 硬件加速器 硬件加速器

    背景情况:

    • 二元卷积神经网络 (bCNN) 通过1位定量化为心电图分类提供低功耗.
    • 现有的bCNN方法处理完整的ECG图像,忽略稀疏性并增加计算开销.
    • 患者间的变化和二元化引起的准确性损失阻碍了当前bCNN心电图分类器的性能.

    研究的目的:

    • 建议使用bCNN与芯片上学习进行节能ECG分类器.
    • 通过一次补丁计算来减少功耗和内存使用.
    • 通过将R-峰值间隔数据整合到模型更新中来提高患者的分类准确性.

    主要方法:

    • 实施了一种补丁逐补丁计算方法,只处理相关的ECG数据补丁.
    • 采用芯片内学习机制,使用心电图特征和R峰间隔更新bCNN模型重量.
    • 设计了一个可重新配置的卷积处理元件阵列和一个基础-2软max结构,以提高硬件效率.

    主要成果:

    • 在FPGA验证中获得了97.55%的分类准确度和89.15%的特异性.
    • 分类器占据了一个小面积 (0.43毫米2),使用55纳米CMOS工艺.
    • 证明了平均低能耗:每次分类0.12μJ,每次芯片上学习0.09μJ.

    结论:

    • 拟议的bCNN带有芯片上学习,为ECG分类提供了一种节能解决方案.
    • 每次补丁的方法和优化的硬件结构显著降低了资源利用率.
    • 分类器的性能和低功耗配置使其成为可穿戴心电图监测系统的理想选择.

    相关实验视频

    Last Updated: Jun 28, 2026

    Artificial Intelligence-Based System for Detecting Attention Levels in Students
    06:37

    Artificial Intelligence-Based System for Detecting Attention Levels in Students

    Published on: December 15, 2023