Paper Info
Title
Assessment Of Photoplethysmogram Signal Quality Based On Frequency Domain And Time Series Parameters
Abstract
In this work, we describe a new method for assessing the photoplethysmogram (PPG) signal quality. In this algorithm, two types of characteristic parameters are used, including frequency domain characteristics and time series characteristics. In the frequency domain, we use the signal power spectrum characteristics, and in terms of time series, we use the correlation dimension, box-counting dimension, fuzzy entropy and LempeiZiv complexity. The quality evaluation of the signal is carried out with each characteristic parameter, and the support vector machine (SVM) model is used to fuse these parameters to determine the signal quality. An expert-labeled database was used to train and test our algorithms. The results show that our algorithm has an accuracy rate of 96.6% on the test set and 99.0% on the training set. The new algorithm is accurate and reliable, showing strong potential to be applied in practice.
Year
DOI
Venue
2017
10.1109/CISP-BMEI.2017.8302279
2017 10TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI)
Keywords
Field
DocType
support vector machine, photoplethysmogram, signal quality assessment, power spectrum, time series characteristics, principal component analysis
Frequency domain,Time series,Pattern recognition,Computer science,Photoplethysmogram,Support vector machine,Correlation dimension,Spectral density,Artificial intelligence,Fuse (electrical),Test set
Conference
Volume
ISBN
Citations 
2018-January
9781538619377
0
PageRank 
References 
Authors
0.34
0
2
Name
Order
Citations
PageRank
Yue Zhang1205.10
Junjun Pan231.44