• 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

基于循环神经网络 LSTM 的生命日志异常检测

LLAD: Life-Log Anomaly Detection Based on Recurrent Neural Network LSTM.

机构信息

Department of Computer Science and Engineering, Sun Moon University, Asan 31460, Republic of Korea.

Genome-based BioIT Convergence Institute, Sun Moon University, Asan 31460, Republic of Korea.

出版信息

J Healthc Eng. 2021 Feb 24;2021:8829403. doi: 10.1155/2021/8829403. eCollection 2021.

DOI:10.1155/2021/8829403
PMID:33708367
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7932773/
Abstract

Life-Log is a term used for the daily monitoring of health conditions and recognizing anomalies from data generated by sensor devices. The development of smart sensors enables collection of health data, which can be considered as a solution to risks associated with personal healthcare by raising awareness regarding health conditions and wellness. Therefore, Life-Log analysis methods are important for real-life monitoring and anomaly detection. This study proposes a method for the improvement and combination of previous methods and techniques in similar fields to detect anomalies in health log data generated by various sensors. Recurrent neural networks with long short-term memory units are used for analyzing the Life-Log data. The results indicate that the proposed model performs more effectively than conventional health data analysis methods, and the proposed approach can yield a satisfactory accuracy in anomaly detection.

摘要

生活日志是指通过传感器设备生成的数据来监测健康状况和识别异常的日常行为。智能传感器的发展使得健康数据的收集成为可能，这可以通过提高对健康状况和健康的认识来解决与个人医疗保健相关的风险。因此，生活日志分析方法对于实时监测和异常检测非常重要。本研究提出了一种改进和结合先前方法和技术的方法，用于检测各种传感器生成的健康日志数据中的异常。使用具有长短期记忆单元的递归神经网络来分析生活日志数据。结果表明，所提出的模型比传统的健康数据分析方法更有效，并且所提出的方法在异常检测中可以达到令人满意的准确性。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/c9e9e58707fc/JHE2021-8829403.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/f4bb7df11118/JHE2021-8829403.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/16d8be35e732/JHE2021-8829403.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/54527c046cd3/JHE2021-8829403.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/549649a6966c/JHE2021-8829403.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/7dd0b75653a6/JHE2021-8829403.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/dae27d5215bb/JHE2021-8829403.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/c9e9e58707fc/JHE2021-8829403.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/f4bb7df11118/JHE2021-8829403.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/16d8be35e732/JHE2021-8829403.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/54527c046cd3/JHE2021-8829403.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/549649a6966c/JHE2021-8829403.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/7dd0b75653a6/JHE2021-8829403.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/dae27d5215bb/JHE2021-8829403.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/19a4/7932773/c9e9e58707fc/JHE2021-8829403.007.jpg

相似文献

1
LLAD: Life-Log Anomaly Detection Based on Recurrent Neural Network LSTM.基于循环神经网络 LSTM 的生命日志异常检测
J Healthc Eng. 2021 Feb 24;2021:8829403. doi: 10.1155/2021/8829403. eCollection 2021.
2
Anomaly detection in groundwater monitoring data using LSTM-Autoencoder neural networks.基于 LSTM-Autoencoder 神经网络的地下水监测数据异常检测。
Environ Monit Assess. 2024 Jul 4;196(8):692. doi: 10.1007/s10661-024-12848-z.
3
A Correlation-Based Anomaly Detection Model for Wireless Body Area Networks Using Convolutional Long Short-Term Memory Neural Network.基于卷积长短时记忆神经网络的无线体域网相关异常检测模型。
Sensors (Basel). 2022 Mar 2;22(5):1951. doi: 10.3390/s22051951.
4
LSTM Networks Using Smartphone Data for Sensor-Based Human Activity Recognition in Smart Homes.基于智能手机数据的 LSTM 网络在智能家居中用于基于传感器的人体活动识别。
Sensors (Basel). 2021 Feb 26;21(5):1636. doi: 10.3390/s21051636.
5
Unsupervised Anomaly Detection for Cars CAN Sensors Time Series Using Small Recurrent and Convolutional Neural Networks.基于小型递归和卷积神经网络的汽车 CAN 传感器时间序列的无监督异常检测。
Sensors (Basel). 2023 May 23;23(11):5013. doi: 10.3390/s23115013.
6
Intelligent Brushing Monitoring Using a Smart Toothbrush with Recurrent Probabilistic Neural Network.使用带有递归概率神经网络的智能牙刷进行智能刷牙监测。
Sensors (Basel). 2021 Feb 10;21(4):1238. doi: 10.3390/s21041238.
7
Device-Free Human Activity Recognition with Low-Resolution Infrared Array Sensor Using Long Short-Term Memory Neural Network.基于长短期记忆神经网络的低分辨率红外阵列传感器的无设备人体活动识别。
Sensors (Basel). 2021 May 20;21(10):3551. doi: 10.3390/s21103551.
8
Data-Driven Anomaly Detection Approach for Time-Series Streaming Data.用于时间序列流数据的数据驱动异常检测方法
Sensors (Basel). 2020 Oct 2;20(19):5646. doi: 10.3390/s20195646.
9
An Efficient Anomaly Recognition Framework Using an Attention Residual LSTM in Surveillance Videos.基于注意力残差 LSTM 的监控视频高效异常识别框架
Sensors (Basel). 2021 Apr 16;21(8):2811. doi: 10.3390/s21082811.
10
Unsupervised Anomaly Detection With LSTM Neural Networks.基于长短期记忆神经网络的无监督异常检测。
IEEE Trans Neural Netw Learn Syst. 2020 Aug;31(8):3127-3141. doi: 10.1109/TNNLS.2019.2935975. Epub 2019 Sep 13.

引用本文的文献

1
Predicting Site Energy Usage Intensity Using Machine Learning Models.运用机器学习模型预测现场能源使用强度。
Sensors (Basel). 2022 Dec 22;23(1):82. doi: 10.3390/s23010082.

本文引用的文献

1
Heart rate and sentiment experimental data with common timeline.具有共同时间轴的心率和情绪实验数据。
Data Brief. 2017 Oct 23;15:851-861. doi: 10.1016/j.dib.2017.10.037. eCollection 2017 Dec.
2
A mobile device system for early warning of ECG anomalies.一种用于心电图异常早期预警的移动设备系统。
Sensors (Basel). 2014 Jun 20;14(6):11031-44. doi: 10.3390/s140611031.
3
Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data.使用无监督特征学习在嘈杂、稀疏和不规则的临床数据上进行计算表型发现。
PLoS One. 2013 Jun 24;8(6):e66341. doi: 10.1371/journal.pone.0066341. Print 2013.
4
Long short-term memory.长短期记忆
Neural Comput. 1997 Nov 15;9(8):1735-80. doi: 10.1162/neco.1997.9.8.1735.