一种利用随机森林方法检测睡眠呼吸暂停的研究

doi:10.13190/j.jbupt.2019-255

北京邮电大学学报 ›› 2020, Vol. 43 ›› Issue (5): 64-70.doi: 10.13190/j.jbupt.2019-255

一种利用随机森林方法检测睡眠呼吸暂停的研究

吕兴凤¹, 李金宝²

1. 黑龙江大学计算机科学技术学院, 哈尔滨 150080;
2. 齐鲁工业大学(山东省科学院) 山东省人工智能研究院, 济南 250353

收稿日期:2019-12-12 发布日期:2021-03-11
通讯作者: 李金宝(1969-),男,教授,博士生导师,E-mail:lijinb@sdas.org. E-mail:lijinb@sdas.org
作者简介:吕兴凤(1980-),女,副教授.
基金资助:
国家自然科学基金项目（61370222）；黑龙江省自然科学基金重点项目（ZD2019F003）；黑龙江省属高等学校基本科研业务费基础研究项目（KJCX201815，KJCX201917）

A Method of Detecting Sleep Apnea Using Random Forest

Lü Xing-feng¹, LI Jin-bao²

1. School of Computer Science and Technology, Heilongjiang University, Harbin 150080, China;
2. Qilu University of Technology(Shandong Academy of Sciences), Shandong Artificial Intelligence Institute, Jinan 250353, China

Received:2019-12-12 Published:2021-03-11

摘要/Abstract

摘要： 多导睡眠仪中的多种呼吸信号使睡眠呼吸暂停检测过程变得复杂，影响患者睡眠，对此，提出一种利用随机森林方法进行自动睡眠呼吸暂停检测的方法.腹部呼吸信号经过希尔伯特-黄变换后，呼吸暂停与正常睡眠时的能量和边际谱分布显著不同，通过提取相关频域特征，结合时域特征，利用机器学习中的随机森林方法进行呼吸暂停的检测，有效地降低了检测复杂性，提高了检测准确性.实验结果表明，此方法在检测的便捷性和准确性上优于已有方法，更适用于家庭环境，具有广泛的应用前景.

关键词: 机器学习, 睡眠呼吸暂停, 希尔伯特-黄变换, 随机森林

Abstract: To solve the problem that various respiratory signals in polysomnography make the detection of sleep apnea complicated and affect patients' sleep, a method of automatic sleep apnea detection using random forest is proposed. The energy and marginal spectrum distribution of sleep apnea is significantly different from that of normal sleep after Hilbert-Huang transform. By extracting the relevant frequency domain features, combining with the time domain features, the random forest method in machine learning method is used to detect sleep apnea, which effectively reduces the detection complexity and improve the accuracy. Experiments show that this method is more convenient and accurate than the existing method, more suitable for home environment,and has a wide range of application prospects.

Key words: machine learning, sleep apnea, Hilbert-Huang transform, random forest

中图分类号:

TP391

吕兴凤, 李金宝. 一种利用随机森林方法检测睡眠呼吸暂停的研究[J]. 北京邮电大学学报, 2020, 43(5): 64-70.

Lü Xing-feng, LI Jin-bao. A Method of Detecting Sleep Apnea Using Random Forest[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(5): 64-70.

参考文献

[1] Wu H, Stone W S, Hsi X, et al. Effects of different sleep restriction protocols on sleep architecture and daytime vigilance in healthy men[J]. Physiological Research, 2010, 59(5):821-829.
[2] Cafer A, Ahmet A, Feng L, et al. Sleep apnea classification based on respiration signals by using ensemble methods[J]. Bio-Medical Materials and Engineering, 2015, 26(1):1703-1710.
[3] Haidar R, McCloskey S, Koprinska I, et al. Convolutional neural networks on multiple respiratory channels to detect hypopnea and obstructive apnea events[C]//International Joint Conference on Neural Networks.[S.l.]:IEEE Press, 2018:1-7.
[4] Kagawa M, Tojima H, Matsui T. Non-contact diagnostic system for sleep apnea-hypopnea syndrome based on amplitude and phase analysis of thoracic and abdominal Doppler radars[J]. Medical & Biological Engineering & Computing, 2016, 54(5):789-798.
[5] Chen Y C, Hsiao T C. Instantaneous phase difference analysis between thoracic and abdominal movement signals based on complementary ensemble empirical mode decomposition[J]. BioMedical Engineering OnLine, 2016, 15(1):1-21.
[6] Maali Y, Al-Jumaily A. Automated detecting sleep apnea syndrome:a novel system based on genetic SVM[C]//International Conference on Hybrid Intelligent Systems. Melacca:IEEE Press, 2011:590-594.
[7] Koley B L, Dey D. Automated detection of apnea and hypopnea events[C]//Third International Conference on Emerging Applications of Information Technology. Kolkata:IEEE Press, 2013:85-88.
[8] Gutiérrez-Tobal G, Alvarez D, Del Campo F, et al. Utility of adaBoost to detect sleep apnea-hypopnea syndrome from single-channel airflow[J]. IEEE Transactions on Biomedical Engineering, 2016, 63(3):636-647.
[9] Bianchi M T, Lipoma T, Darling C, et al. Automated sleep apnea quantification based on respiratory movement[J]. International Journal of Medical Sciences, 2014, 11(8):796-802.
[10] Koley B L, Dey D. Real-time adaptive apnea and hypopnea event detection methodology for portable sleep apnea monitoring devices[J]. IEEE Transactions on Biomedical Engineering, 2013, 60(12):3354-3363.
[11] Barroso-García V, Gutiérrez-Tobal G, Leila K G, et al. Irregularity and variability analysis of airflow recordings to facilitate the diagnosis of paediatric sleep apnoea-hypopnoea syndrome[J]. Entropy, 2017, 19(9):447-463.
[12] Minu P, Amithab M. SAHS detection based on ANFIS using single channel airflow signal[J]. International Journal of Innovative Research in Science, Engineering and Technology, 2016, 5(7):13053-13061.

[1]	常霄, 黄智濒, 禹旻, 杨武兵. 一种适用于航天大数据的深度决策树算法[J]. 北京邮电大学学报, 2023, 46(3): 1-6.
[2]	欧阳莫微, 康桂霞, 王开亮, 王亚明. 一种放射组学分析的海马硬化自动诊断方法[J]. 北京邮电大学学报, 2022, 45(4): 51-57.
[3]	牟晓惠, 李丽香. Dropout回声状态网络的网络流量预测[J]. 北京邮电大学学报, 2021, 44(5): 10-13,20.
[4]	易茜, 黎伟, 易树平, 谢俊东. 基于鼠标行为时频联合分析的用户可信认证[J]. 北京邮电大学学报, 2021, 44(4): 121-128.
[5]	汤永利, 李星宇, 赵宗渠, 李运峰. 面向Android支付破解应用的检测方法[J]. 北京邮电大学学报, 2021, 44(4): 95-101.
[6]	彭雨荷, 陈翔, 陈双武, 杨坚. 基于迁移学习的跨域异常流量检测[J]. 北京邮电大学学报, 2021, 44(2): 33-39.
[7]	谢晓燕, 赵欢, 蒋林. 基于视频数据特性的动态手势识别[J]. 北京邮电大学学报, 2020, 43(5): 91-97.
[8]	张德干, 陈露, 陈晨, 张婷, 崔玉亚. 一种面向边缘计算节点能量优化的QoS约束路由算法[J]. 北京邮电大学学报, 2020, 43(4): 101-105.
[9]	周怡琳, 杨璐, 鲁文睿. 尘土颗粒影响下电路板电化学迁移失效寿命建模探索[J]. 北京邮电大学学报, 2020, 43(3): 11-18,31.
[10]	张国栋, 应欢, 杨寿国, 石志强, 李霁远. 嵌入式固件脆弱哈希函数自动识别与破解方法[J]. 北京邮电大学学报, 2020, 43(1): 46-53.
[11]	余凯祥, 陈振豪, 张四海. 一种多变量制造过程中的关键变量检测算法[J]. 北京邮电大学学报, 2019, 42(6): 98-104.
[12]	孟浩, 霍如, 郭倩影, 黄韬, 刘韵洁. 基于机器学习的MEC随机任务迁移算法[J]. 北京邮电大学学报, 2019, 42(2): 25-30.
[13]	崔鸿雁, 徐帅, 张利锋, Roy E. Welsch, Berthold K. P. Horn. 机器学习中的特征选择方法研究及展望[J]. 北京邮电大学学报, 2018, 41(1): 1-12.
[14]	董枫, 刘天铭, 徐国爱, 郭燕慧, 李承泽. 面向Android二进制代码的缺陷预测方法[J]. 北京邮电大学学报, 2018, 41(1): 13-23.
[15]	郑康锋,王秀娟. 利用边际谱Hurst参数检测DDoS攻击[J]. 北京邮电大学学报, 2011, 34(5): 128-132.

一种利用随机森林方法检测睡眠呼吸暂停的研究

A Method of Detecting Sleep Apnea Using Random Forest

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价