ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2020, Vol. 57 ›› Issue (12): 2547-2555.doi: 10.7544/issn1000-1239.2020.20190583

• 人工智能 • 上一篇    下一篇

多特征信息融合LSTM-RNN检测OSA方法

朱兆坤1,2,3,李金宝1   

  1. 1(齐鲁工业大学(山东省科学院)山东省人工智能研究院 济南 250014);2(黑龙江大学计算机科学技术学院 哈尔滨 150080);3(黑龙江大学软件学院 哈尔滨 150080) (zzklove3344@hotmail.com)
  • 出版日期: 2020-12-01
  • 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)

Multi-Feature Information Fusion LSTM-RNN Detection for OSA

Zhu Zhaokun1,2,3, Li Jinbao1   

  1. 1(Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Science), Jinan 250014);2(School of Computer Science and Tecnology, Heilongjiang University, Harbin 150080);3(Software Technology Institute, Heilongjiang University, Harbin 150080)
  • Online: 2020-12-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (61370222) and the Key Program of the Natural Science Foundation of Heilongjiang Province of China (ZD2019F003).

摘要: 阻塞性睡眠呼吸暂停(obstructive sleep apnea, OSA)是最常见的睡眠呼吸疾病,它对人体的很多生理系统尤其对心血管系统是一个潜在的威胁.现有使用心电信号(electrocardiograph, ECG)提取浅层特征检测OSA的方法在长片段、高噪声的ECG信号和大数据集上表现较差.针对上述问题,提出一种多特征心电信号融合的长短期记忆循环神经网络,融合从ECG信号中提取的多种浅层特征信号,通过在融合信号上学习深层特征来检测OSA,提升模型在长片段ECG上的检测准确率和大数据集上的泛化能力.同时还针对浅层特征信号提出一种有效的数据预处理方法,用以突出OSA的时序变化,提高神经网络训练的收敛性,并降低由异常值噪声带来的影响,进一步提升模型在高噪声ECG片段上的检测准确率.实验证明:提出的方法在片段OSA检测准确率上优于已有的方法.

关键词: 阻塞性睡眠呼吸暂停, 心电信号, 预处理, 长短时记忆, 循环神经网络

Abstract: Obstructive sleep apnea (OSA) is the most common sleep respiratory disorder, and it is a potential threat to many physiological systems, especially the cardiovascular system. Most of the previous methods for OSA detection extracted the shallow features from electrocardiograph (ECG) which would be used in classifiers, and they failed to achieve excellent performances on the ECG signal with high noise and large datasets. To solve this kind of problem, this paper proposes a long short-term memory recurrent neural network (LSTM-RNN) based on combination of multiple kinds of feature signals. The method fuses multiple kinds of shallow feature signals that are extracted from ECG signals and learns the deep feature from the fused signals. The accuracy of OSA detection model in long ECG segments is increased and the generalization ability on large datasets is improved. An effective preprocessing method is propesed for shallow feature signals to highlight the variation of OSA time sequences. The preprocessing method may improve the convergence of training neural networks, reduce the impact of outlier noise, and further improve the detection accuracy of the model for the ECG segments with high noise. The experimental results indicate that our method is superior to the existing methods in the accuracy of per-segment OSA detection.

Key words: obstructive sleep apnea, electrocardiograph, preprocessing, long short-term memory, recurrent neural network

中图分类号: