文档介绍：A Novel Feature Extraction Method for Signal
Quality Assessment of Arterial Blood Pressure for
Monitoring Cerebral Autoregulation
Pandeng Zhang12, Jia Liu12, Xinyu Wu12, Xiaochang Liu12,Qingchun Gao3
1Shenzhen Institute of Advanced Technology, Shenzhen, China,
2Chinese Academy of Sciences/The Chinese University of Hong Kong, HongKong, China
3The Second Affiliated Hospital of Guangzhou Medical College, Guangzhou, China
pd.******@., jia.******@siat., xy.******@siat., xc.******@., qcgao@
Abstract—In this paper, we proposed a novel method of signal ABP. Though the method was effective in terms of
quality assessment of arterial blood pressure for monitoring identification, the structure of it plicated due to nested
Cerebral Autoregulation (CA). This method is based on rules without detailed explanation, and it has six short-time
algorithm of signal abnormality index (SAI). Two simple and averaged features which need a learning time more than 10
effective features-end diastole slope sum (EDSS) and slow seconds to initialize.
ejection slope sum (SESS), were proposed to identify abnormal
beats from ABP as CA input in real-time. The methods of Sun et al proposed an algorithm with a simple structure
cumulative distribution function (CDF) and receiver operating named signal abnormality index (SAI) to assess the quality of
characteristic (R