| Title |
Modified block compressed sensing for extraction of fetal electrocardiogram from mother electrocardiogram using block compressed sensing based guided FOCUSS and FAST-independent component / |
| Authors |
Tayyib, Muhammad ; Amir, Muhammad ; Yousufi, Musyyab ; Abdullah, Suheel ; Maqsood, Sarmad ; Irfan, Muhammad |
| DOI |
10.5755/j01.itc.50.1.24145 |
| Full Text |
|
| Is Part of |
Information technology and control = Informacinės technologijos ir valdymas.. Kaunas : Technologija. 2021, vol. 50, no. 1, p. 123-137.. ISSN 1392-124X. eISSN 2335-884X |
| Keywords [eng] |
Fetal ECG ; Compressed Sensing ; BCS-GFOCUSS ; Source separation ; Classification |
| Abstract [eng] |
Fetal electrocardiogram extraction from abdominal electrocardiogram is perilous task for tele-monitoring of fetus which require in-depth understanding. Conventional source separation methods are not efficient enough to separate fetal electrocardiogram from huge multi-channel electrocardiogram signals. Due to huge amount of data, source separation techniques along with compression methods are used, however, the use of compressed sensing depends on the sparsity of signal. Electrocardiogram signal is not sparse in original form; therefore, it is made co-sparse for processing. This paper proposes block compresses sensing based reconstruction of fetal electrocardiogram from abdominal electrocardiogram, the novelty of this paper is in the form of using guided frequency filter for removing interdependency between multichannel electrocardiogram signals. The use of Walsh sensing matrix made it possible to achieve high compression ratio. Experimental results prove that even at very high compression ratio, successful fetal electrocardiogram reconstruction from raw electrocardiogram is possible. These results are validated using peak signal to noise ratio, signal to interference and noise ratio, and mean square error. This shows the framework, compared to other algorithms such as current blocking compressed sensing algorithms, Rakness based compressed sensing algorithm and wavelet algorithms, can greatly reduce code execution time during data compression stage and achieve better reconstruction. |
| Published |
Kaunas : Technologija |
| Type |
Journal article |
| Language |
English |
| Publication date |
2021 |
| CC license |
|
