• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

时频时空长短时记忆网络在生理信号鲁棒分类中的应用

Time-frequency time-space LSTM for robust classification of physiological signals.

机构信息

Center for Artificial Intelligence, Prince Mohammad Bin Fahd University, Khobar, 31952, Saudi Arabia.

出版信息

Sci Rep. 2021 Mar 25;11(1):6936. doi: 10.1038/s41598-021-86432-7.

DOI:10.1038/s41598-021-86432-7
PMID:33767352
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7994826/
Abstract

Automated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time-frequency and time-space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.

摘要

生理时间序列的自动分析被广泛应用于医学和生命科学领域的许多临床应用中。长短期记忆（LSTM）是一种深度递归神经网络架构，用于分类时间序列数据。在这里，时间-频率和时间-空间特性被引入作为 LSTM 处理生理学中长序列数据的强大工具。基于从两个传感器诱导的生理信号数据库中获得的分类结果，所提出的方法具有以下潜力：（1）实现非常高的分类准确性；（2）为数据学习节省大量时间；（3）通过减少用于数据记录的多个可穿戴传感器，降低成本并为临床试验提供用户舒适度。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/87bf7d6bb62e/41598_2021_86432_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/6f09faeb4364/41598_2021_86432_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/06090b80ea4b/41598_2021_86432_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/c15fa95d5ba3/41598_2021_86432_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/87bf7d6bb62e/41598_2021_86432_Fig4_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/6f09faeb4364/41598_2021_86432_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/06090b80ea4b/41598_2021_86432_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/c15fa95d5ba3/41598_2021_86432_Fig3_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3c90/7994826/87bf7d6bb62e/41598_2021_86432_Fig4_HTML.jpg

相似文献

1
Time-frequency time-space LSTM for robust classification of physiological signals.时频时空长短时记忆网络在生理信号鲁棒分类中的应用
Sci Rep. 2021 Mar 25;11(1):6936. doi: 10.1038/s41598-021-86432-7.
2
A new approach for arrhythmia classification using deep coded features and LSTM networks.基于深度编码特征和长短期记忆网络的心律失常分类新方法。
Comput Methods Programs Biomed. 2019 Jul;176:121-133. doi: 10.1016/j.cmpb.2019.05.004. Epub 2019 May 10.
3
Classification of normal sinus rhythm, abnormal arrhythmia and congestive heart failure ECG signals using LSTM and hybrid CNN-SVM deep neural networks.使用 LSTM 和混合 CNN-SVM 深度神经网络对正常窦性节律、异常心律失常和充血性心力衰竭 ECG 信号进行分类。
Comput Methods Biomech Biomed Engin. 2021 Feb;24(2):203-214. doi: 10.1080/10255842.2020.1821192. Epub 2020 Sep 21.
4
Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification.基于可解释时间序列的神经基础扩展分析（N-BEATS）与循环神经网络在心脏功能障碍分类中的比较。
Physiol Meas. 2022 Jun 28;43(6). doi: 10.1088/1361-6579/ac6e55.
5
Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals.基于单通道 EEG 信号的级联 LSTM 递归神经网络的自动睡眠分期方法。
Comput Biol Med. 2019 Mar;106:71-81. doi: 10.1016/j.compbiomed.2019.01.013. Epub 2019 Jan 19.
6
Applying deep neural networks and inertial measurement unit in recognizing irregular walking differences in the real world.应用深度神经网络和惯性测量单元在现实世界中识别不规则行走差异。
Appl Ergon. 2021 Oct;96:103414. doi: 10.1016/j.apergo.2021.103414. Epub 2021 Jun 1.
7
Human activity recognition from inertial sensor time-series using batch normalized deep LSTM recurrent networks.使用批归一化深度长短期记忆循环网络从惯性传感器时间序列中进行人类活动识别。
Annu Int Conf IEEE Eng Med Biol Soc. 2018 Jul;2018:1-4. doi: 10.1109/EMBC.2018.8513115.
8
Deep learning for predicting respiratory rate from biosignals.深度学习在生物信号呼吸率预测中的应用。
Comput Biol Med. 2022 May;144:105338. doi: 10.1016/j.compbiomed.2022.105338. Epub 2022 Mar 2.
9
Deep Learning-Based Stroke Disease Prediction System Using Real-Time Bio Signals.基于深度学习的实时生物信号脑卒中疾病预测系统。
Sensors (Basel). 2021 Jun 22;21(13):4269. doi: 10.3390/s21134269.
10
Time-frequency time-space long short-term memory networks for image classification of histopathological tissue.基于时频时空长短时记忆网络的组织病理图像分类。
Sci Rep. 2021 Jul 1;11(1):13703. doi: 10.1038/s41598-021-93160-5.

引用本文的文献

1
Time Series Forecasting Model Based on the Adapted Transformer Neural Network and FFT-Based Features Extraction.基于自适应变压器神经网络和基于快速傅里叶变换的特征提取的时间序列预测模型
Sensors (Basel). 2025 Jan 23;25(3):652. doi: 10.3390/s25030652.
2
The Importance of Antimicrobial Strategies Associated with Clinical Cure and Increased Microbiological Eradication in Patients with Complicated Urinary Tract Infections and High Risk of Relapse.抗菌策略与复杂尿路感染及复发高风险患者临床治愈和微生物清除率提高的相关性的重要性
Eur Urol Open Sci. 2024 Dec 31;71:165-171. doi: 10.1016/j.euros.2024.12.001. eCollection 2025 Jan.
3

本文引用的文献

1
Deep learning-based BCI for gait decoding from EEG with LSTM recurrent neural network.基于深度学习的 EEG 脑机接口的 LSTM 递归神经网络步态解码
J Neural Eng. 2020 Jul 13;17(4):046011. doi: 10.1088/1741-2552/ab9842.
2
Comparing the Usability and Acceptability of Wearable Sensors Among Older Irish Adults in a Real-World Context: Observational Study.在真实环境中比较可穿戴传感器在爱尔兰老年成年人中的可用性和可接受性：观察性研究。
JMIR Mhealth Uhealth. 2020 Apr 20;8(4):e15704. doi: 10.2196/15704.
3
Heterogeneous local dynamics revealed by classification analysis of spatially disaggregated time series data.
Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies.
用于化学、生物、放射、核及爆炸物（CBRNE）紧急情况中低氧血症严重程度分类的机器学习和深度学习模型
Diagnostics (Basel). 2024 Dec 8;14(23):2763. doi: 10.3390/diagnostics14232763.
4
A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning.基于脑电图信号处理与深度学习的癫痫检测与预测方法综述
Front Neurosci. 2024 Nov 15;18:1468967. doi: 10.3389/fnins.2024.1468967. eCollection 2024.
5
Discrete Time Series Forecasting of Hive Weight, In-Hive Temperature, and Hive Entrance Traffic in Non-Invasive Monitoring of Managed Honey Bee Colonies: Part I.管理型蜂群非侵入式监测中的蜂箱重量、蜂箱内温度和蜂箱入口交通的离散时间序列预测：第一部分。
Sensors (Basel). 2024 Oct 4;24(19):6433. doi: 10.3390/s24196433.
6
Artificial Intelligence-Driven Prognosis of Respiratory Mechanics: Forecasting Tissue Hysteresivity Using Long Short-Term Memory and Continuous Sensor Data.人工智能驱动的呼吸力学预后：使用长短期记忆和连续传感器数据预测组织滞后性。
Sensors (Basel). 2024 Aug 27;24(17):5544. doi: 10.3390/s24175544.
7
IoT-Based Solution for Detecting and Monitoring Upper Crossed Syndrome.基于物联网的检测和监测上交叉综合征的解决方案。
Sensors (Basel). 2023 Dec 26;24(1):135. doi: 10.3390/s24010135.
8
Detecting major depressive disorder presence using passively-collected wearable movement data in a nationally-representative sample.利用全国代表性样本中被动采集的可穿戴运动数据检测主要抑郁障碍的存在。
Psychiatry Res. 2024 Feb;332:115693. doi: 10.1016/j.psychres.2023.115693. Epub 2023 Dec 30.
9
Frontal-occipital phase synchronization predicts occipital alpha power in perceptual decision-making.额枕相位同步可预测知觉决策中的枕叶阿尔法波功率。
Cogn Neurodyn. 2023 Aug;17(4):815-827. doi: 10.1007/s11571-022-09862-7. Epub 2022 Aug 24.
10
Classification of Low Earth Orbit (LEO) Resident Space Objects' (RSO) Light Curves Using a Support Vector Machine (SVM) and Long Short-Term Memory (LSTM).使用支持向量机（SVM）和长短期记忆网络（LSTM）对近地轨道（LEO）常驻空间物体（RSO）的光曲线进行分类
Sensors (Basel). 2023 Jul 20;23(14):6539. doi: 10.3390/s23146539.
通过对空间离散时间序列数据的分类分析揭示异质局部动力学。
Epidemics. 2019 Dec;29:100357. doi: 10.1016/j.epidem.2019.100357. Epub 2019 Jul 22.
4
A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures.递归神经网络综述：长短期记忆细胞和网络架构。
Neural Comput. 2019 Jul;31(7):1235-1270. doi: 10.1162/neco_a_01199. Epub 2019 May 21.
5
Deep learning for electroencephalogram (EEG) classification tasks: a review.深度学习在脑电图（EEG）分类任务中的应用：综述。
J Neural Eng. 2019 Jun;16(3):031001. doi: 10.1088/1741-2552/ab0ab5. Epub 2019 Feb 26.
6
Classification of gait patterns between patients with Parkinson's disease and healthy controls using phase space reconstruction (PSR), empirical mode decomposition (EMD) and neural networks.基于相空间重构（PSR）、经验模态分解（EMD）和神经网络对帕金森病患者与健康对照者的步态模式进行分类。
Neural Netw. 2019 Mar;111:64-76. doi: 10.1016/j.neunet.2018.12.012. Epub 2019 Jan 6.
7
Tensor Decomposition of Gait Dynamics in Parkinson's Disease.帕金森病步态动力学的张量分解。
IEEE Trans Biomed Eng. 2018 Aug;65(8):1820-1827. doi: 10.1109/TBME.2017.2779884. Epub 2017 Dec 4.
8
Pattern analysis of computer keystroke time series in healthy control and early-stage Parkinson's disease subjects using fuzzy recurrence and scalable recurrence network features.使用模糊递归和可扩展递归网络特征分析健康对照组和早期帕金森病患者的计算机按键时间序列模式。
J Neurosci Methods. 2018 Sep 1;307:194-202. doi: 10.1016/j.jneumeth.2018.05.019. Epub 2018 May 30.
9
How many strides are required for a reliable estimation of temporal gait parameters? Implementation of a new algorithm on the phase coordination index.可靠估计步态时间参数需要多少步幅？一种基于相位协调指数的新算法的实现。
PLoS One. 2018 Feb 8;13(2):e0192049. doi: 10.1371/journal.pone.0192049. eCollection 2018.
10
Biosignals learning and synthesis using deep neural networks.使用深度神经网络进行生物信号学习和合成。
Biomed Eng Online. 2017 Sep 25;16(1):115. doi: 10.1186/s12938-017-0405-0.