PMID- 34450724
OWN - NLM
STAT- MEDLINE
DCOM- 20210831
LR  - 20240403
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 21
IP  - 16
DP  - 2021 Aug 5
TI  - A Dictionary Optimization Method for Reconstruction of ECG Signals after 
      Compressed Sensing.
LID - 10.3390/s21165282 [doi]
LID - 5282
AB  - This paper presents a new approach for the optimization of a dictionary used in 
      ECG signal compression and reconstruction systems, based on Compressed Sensing 
      (CS). Alternatively to fully data driven methods, which learn the dictionary from 
      the training data, the proposed approach uses an over complete wavelet 
      dictionary, which is then reduced by means of a training phase. Moreover, the 
      alignment of the frames according to the position of the R-peak is proposed, such 
      that the dictionary optimization can exploit the different scaling features of 
      the ECG waves. Therefore, at first, a training phase is performed in order to 
      optimize the overcomplete dictionary matrix by reducing its number of columns. 
      Then, the optimized matrix is used in combination with a dynamic sensing matrix 
      to compress and reconstruct the ECG waveform. In this paper, the mathematical 
      formulation of the patient-specific optimization is presented and three 
      optimization algorithms have been evaluated. For each of them, an experimental 
      tuning of the convergence parameter is carried out, in order to ensure that the 
      algorithm can work in its most suitable conditions. The performance of each 
      considered algorithm is evaluated by assessing the Percentage of 
      Root-mean-squared Difference (PRD) and compared with the state of the art 
      techniques. The obtained experimental results demonstrate that: (i) the 
      utilization of an optimized dictionary matrix allows a better performance to be 
      reached in the reconstruction quality of the ECG signals when compared with other 
      methods, (ii) the regularization parameters of the optimization algorithms should 
      be properly tuned to achieve the best reconstruction results, and (iii) the 
      Multiple Orthogonal Matching Pursuit (M-OMP) algorithm is the better suited 
      algorithm among those examined.
FAU - De Vito, Luca
AU  - De Vito L
AUID- ORCID: 0000-0003-1896-2614
AD  - Department of Engineering, University of Sannio, 82100 Benevento, Italy.
FAU - Picariello, Enrico
AU  - Picariello E
AD  - Department of Engineering, University of Sannio, 82100 Benevento, Italy.
FAU - Picariello, Francesco
AU  - Picariello F
AUID- ORCID: 0000-0001-6854-3026
AD  - Department of Engineering, University of Sannio, 82100 Benevento, Italy.
FAU - Rapuano, Sergio
AU  - Rapuano S
AD  - Department of Engineering, University of Sannio, 82100 Benevento, Italy.
FAU - Tudosa, Ioan
AU  - Tudosa I
AUID- ORCID: 0000-0002-5127-578X
AD  - Department of Engineering, University of Sannio, 82100 Benevento, Italy.
LA  - eng
GR  - ARS01_00860/Italian Ministry of Research/
PT  - Journal Article
DEP - 20210805
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - Algorithms
MH  - *Data Compression
MH  - *Electrocardiography
MH  - Humans
PMC - PMC8398887
OTO - NOTNLM
OT  - ECG
OT  - OMP
OT  - compressed sensing
OT  - dictionary learning
COIS- The authors declare no conflict of interest.
EDAT- 2021/08/29 06:00
MHDA- 2021/09/01 06:00
PMCR- 2021/08/05
CRDT- 2021/08/28 01:01
PHST- 2021/06/22 00:00 [received]
PHST- 2021/07/30 00:00 [revised]
PHST- 2021/08/01 00:00 [accepted]
PHST- 2021/08/28 01:01 [entrez]
PHST- 2021/08/29 06:00 [pubmed]
PHST- 2021/09/01 06:00 [medline]
PHST- 2021/08/05 00:00 [pmc-release]
AID - s21165282 [pii]
AID - sensors-21-05282 [pii]
AID - 10.3390/s21165282 [doi]
PST - epublish
SO  - Sensors (Basel). 2021 Aug 5;21(16):5282. doi: 10.3390/s21165282.