计算机科学
特征选择
滤波器(信号处理)
人工智能
模式识别(心理学)
光容积图
血压
选择(遗传算法)
Lasso(编程语言)
特征(语言学)
特征提取
计算机视觉
医学
内科学
万维网
哲学
语言学
作者
Dingliang Wang,Xiu Yang,Xuenan Liu,Shaolin Mao,Longwei Li,Wenjin Wang
出处
期刊:IEEE Transactions on Instrumentation and Measurement
[Institute of Electrical and Electronics Engineers]
日期:2021-01-01
卷期号:70: 1-14
被引量:19
标识
DOI:10.1109/tim.2021.3109986
摘要
Objective: Currently, BP measurement devices are mainly cuff-based which are not portable or convenient for users. To simplify the measurement of BP, this paper proposed a new framework for noninvasive BP estimation using single-channel photoplethysmography (PPG) signal. Methods: Various PPG features that may be related to BP were extracted and a filter-wrapper collaborated feature selection method was used for rejecting irrelevant and redundant features. The features that maximize the correlation with BP were finally selected as the BP-oriented improved feature subset (IFS), and a new LASSO-LSTM model was designed to estimate BP from the IFS. Results: Experiments were conducted on a public dataset and a self-collected clinical dataset, respectively. Results demonstrated that the proposed method is superior to previously reported methods in the literature, giving a mean absolute error of 4.95 mmHg for systolic blood pressure (SBP) and 3.15 mmHg for diastolic blood pressure (DBP) which complies with the standard of AAMI. Conclusion: The proposed filter-wrapper collaborated feature selection method could effectively reject weak correlation and redundant features, and the designed LASSO-LSTM model is capable of learning complicated nonlinear relations between the selected IFS and BP. The proposed method shows improved accuracy of noninvasive BP estimation.
科研通智能强力驱动
Strongly Powered by AbleSci AI