2012
DOI: 10.1016/j.measurement.2011.03.022
|View full text |Cite
|
Sign up to set email alerts
|

Empirical Mode Decomposition and Principal Component Analysis implementation in processing non-invasive cardiovascular signals

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

1
36
0

Year Published

2012
2012
2021
2021

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 44 publications
(37 citation statements)
references
References 16 publications
1
36
0
Order By: Relevance
“…Extracting useful information from large amounts of oscillatory data is important for a considerate number of real world applications such as medical electrocardiography (ECG) reading [1,2,3], atomic crystal images in physics [4,5], mechanical engineering [6,7], art investigation [8,9], geology [10,11,12], imaging [13], etc. In order to extract certain features and analyze adaptive components of oscillatory data, it is typical to assume that the signal f (t) consists of several oscillatory modes like…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Extracting useful information from large amounts of oscillatory data is important for a considerate number of real world applications such as medical electrocardiography (ECG) reading [1,2,3], atomic crystal images in physics [4,5], mechanical engineering [6,7], art investigation [8,9], geology [10,11,12], imaging [13], etc. In order to extract certain features and analyze adaptive components of oscillatory data, it is typical to assume that the signal f (t) consists of several oscillatory modes like…”
Section: Introductionmentioning
confidence: 99%
“…In spite of considerable successes of analyzing oscillatory time series in the form of mode decomposition in (1) or GMD in (2), these models conflict with the physical intuition that the oscillation pattern of the time series changes in time. For example, the cardiac and respiratory patterns in Figure 1 vary in time.…”
Section: Introductionmentioning
confidence: 99%
“…In addition, although linear techniques are being increasingly less used in the last years, PCA may be used together with some other nonlinear technique to improve the performance of this latter. An interesting example may be found in [4], where PCA was applied to Empirical Mode Decomposition to isolate the cardiac information in the processing of cardiovascular signals. Therefore, the proposal of new techniques and algorithms based on PCA for dealing with source separation is justifiable, particularly in applications where both speed and memory usage are crucial, e.g.…”
Section: Introductionmentioning
confidence: 99%
“…However, generally only one physiological signal is monitored, often supplemented by accelerometry, and few results are provided regarding the patient's state [7][8][9][10][11][12][13][14][15]. Specifically in chairs or wheelchairs, where physical space is available, and embedding several sensors is possible [16], [17]. Improvements on the state of the art are attainable, as the known implementations on wheelchairs monitor only one cardiac signal, and do not provide a stand alone monitoring solution, or only with limited signal processing data storage and communication capabilities [14,15,26].…”
Section: Introductionmentioning
confidence: 99%