| 基于DTW的贝叶斯方法在睡眠和唤醒分类中的应用 |
| |
| 引用本文： | 马科,符春晓,刘建,孙海胜.基于DTW的贝叶斯方法在睡眠和唤醒分类中的应用[J].计算机系统应用,2018,27(1):195-200. |
| |
| 作者姓名： | 马科 符春晓 刘建 孙海胜 |
| |
| 作者单位： | 中国科学技术大学 管理学院学院, 合肥 230026,中国人民解放军 65113部队, 葫芦岛 125000,淮河流域水资源保护局, 蚌埠 230000,中国科学技术大学 计算机科学与技术学院, 合肥 230026 |
| |
| 基金项目： | 国家自然科学基金（71671168）；国家科技重大专项（2014ZX07204006） |
| |
| 摘 要： | 许多方便的可穿戴设备被用于医疗用途，如测量心率（HR）、血压和其他信号. 随着睡眠质量监测问题的出现，如何从这些信号中区分睡眠和唤醒状态成为关键问题. 提出了一种基于动态时间规整（DTW）的贝叶斯方法用于睡眠和唤醒分类. 利用心率和血氧饱和度（SpO2）的信号去分析睡眠状态和一些睡眠相关问题. 利用DTW从原始的心率、血氧饱和度信号中提取特征，然后贝叶斯分类方法用于区别睡眠和唤醒状态. 最后，从睡眠心脏健康研究网站收集数据的一个真实案例研究验证了基于DTW的贝叶斯方法的可行性和优势.
|
| 关 键 词： | 睡眠和唤醒分类问题 动态时间规划 贝叶斯分类 贝叶斯网络模型 |
| 收稿时间： | 2017/3/24 0:00:00 |
| 修稿时间： | 2017/4/13 0:00:00 |
Application of Bayesian Method Based on DTW in Classification of Sleep and Wake |
| |
| MA Ke,FU Chun-Xiao,LIU Jian and SUN Hai-Sheng.Application of Bayesian Method Based on DTW in Classification of Sleep and Wake[J].Computer Systems& Applications,2018,27(1):195-200. |
| |
| Authors: | MA Ke FU Chun-Xiao LIU Jian and SUN Hai-Sheng |
| |
| Affiliation: | School of Management, University of Science and Technology of China, Hefei 230026, China,65113 Troops, People''s Liberation Army of China, Huludao 125000, China,Huaihe Water Resources Protection Science Research Institute, Bengbu 230000, China and School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China |
| |
| Abstract: | Many convenient wearable devices are being used for medical purposes, like measuring the heart rate (HR), blood pressure. With the sleep quality monitor problem, the key point is how to discriminate the sleeping state from waking one out of these signals. This paper proposes a Bayesian approach based on dynamic time warping (DTW) method for sleeping and waking classification. It uses HR and surplus pulse O2 (SpO2) signals to analyze the sleeping states and the occurrence of some sleep-related problems. The DTW is used to extract features from the original HR and SpO2 signals. Then a Bayesian classification method is introduced for the discrimination of sleeping and waking states. Finally, a case study from a real-world applications, collected from the website of the Sleep Heart Health Study, is presented to show the feasibility and advantages of the DTW-based Bayesian approach. |
| |
| Keywords: | sleep and wake classification problem dynamic time warping Bayesian classfication Bayesian network model |
|
| 点击此处可从《计算机系统应用》浏览原始摘要信息 |
|
点击此处可从《计算机系统应用》下载全文 |
|
