Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction

Szymon Sieciński; Muhammad Tausif Irshad; Md Abid Hasan; Ewaryst Tkacz; Marcin Grzegorzek

doi:10.1145/3615834.3615855

Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction

Szymon Sieciński^*, Muhammad Tausif Irshad, Md Abid Hasan, Ewaryst Tkacz, Marcin Grzegorzek

^*Corresponding author for this work

Silesian University of Technology

1 Citation (Scopus)

Abstract

Signal quality assessment is essential for biomedical signal processing, analysis, and interpretation. Various methods exist, including averaged numerical values, thresholding, time- or frequency-domain analysis, and nonlinear approaches. This study evaluated the quality of gyrocardiographic signals (GCG) using symmetric projection attractor reconstruction (SPAR) analysis. Two classifiers, random forest and bagged trees, were used to assess the performance of the SPAR-based approach. Eleven features were extracted from the variables v and w, calculated on the basis of the signal delay. These features included minimum and maximum values, mean, standard deviation (SD), median, and Euclidean distance. The results showed that the SPAR-based approach achieved high accuracy, precision, and recall. The random forest classifier achieved 0.729 accuracy, 0.726 precision, and 0.729 recall, while the bagged trees classifier achieved 0.792 accuracy, 0.804 precision, and 0.792 recall. These findings suggest that the SPAR-based approach is a promising method to accurately assess the quality of GCG signals.

Original language	English
Pages	15:1-15:5
Number of pages	5
DOIs	https://doi.org/10.1145/3615834.3615855
Publication status	Published - 10.2023
Event	iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence - Fraunhofer IMTE, Lübeck, Germany Duration: 21.09.2023 → 22.09.2023 https://doi.org/10.1145/3615834.3615855

Conference

Conference	iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence
Abbreviated title	iWOAR'23
Country/Territory	Germany
City	Lübeck
Period	21.09.23 → 22.09.23
Internet address	https://doi.org/10.1145/3615834.3615855

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being
SDG 4 Quality Education
SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities
SDG 12 Responsible Consumption and Production
SDG 14 Life Below Water
SDG 15 Life on Land

Research Areas and Centers

Centers: Center for Artificial Intelligence Luebeck (ZKIL)

DFG Research Classification Scheme

2.22-07 Medical Informatics and Medical Bioinformatics

Access to Document

10.1145/3615834.3615855Licence: Unspecified

Cite this

Sieciński, S., Irshad, M. T., Hasan, M. A., Tkacz, E., & Grzegorzek, M. (2023). Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction. 15:1-15:5. Paper presented at iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence, Lübeck, Germany. https://doi.org/10.1145/3615834.3615855

@conference{38a255ceef0a4db682f474cb2c416ca2,

title = "Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction",

abstract = "Signal quality assessment is essential for biomedical signal processing, analysis, and interpretation. Various methods exist, including averaged numerical values, thresholding, time- or frequency-domain analysis, and nonlinear approaches. This study evaluated the quality of gyrocardiographic signals (GCG) using symmetric projection attractor reconstruction (SPAR) analysis. Two classifiers, random forest and bagged trees, were used to assess the performance of the SPAR-based approach. Eleven features were extracted from the variables v and w, calculated on the basis of the signal delay. These features included minimum and maximum values, mean, standard deviation (SD), median, and Euclidean distance. The results showed that the SPAR-based approach achieved high accuracy, precision, and recall. The random forest classifier achieved 0.729 accuracy, 0.726 precision, and 0.729 recall, while the bagged trees classifier achieved 0.792 accuracy, 0.804 precision, and 0.792 recall. These findings suggest that the SPAR-based approach is a promising method to accurately assess the quality of GCG signals.",

author = "Szymon Sieci{\'n}ski and Irshad, \{Muhammad Tausif\} and Hasan, \{Md Abid\} and Ewaryst Tkacz and Marcin Grzegorzek",

note = "DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.; iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence, iWOAR'23 ; Conference date: 21-09-2023 Through 22-09-2023",

year = "2023",

month = oct,

doi = "10.1145/3615834.3615855",

language = "English",

pages = "15:1--15:5",

url = "https://doi.org/10.1145/3615834.3615855",

}

Sieciński, S, Irshad, MT, Hasan, MA, Tkacz, E & Grzegorzek, M 2023, 'Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction', Paper presented at iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence, Lübeck, Germany, 21.09.23 - 22.09.23 pp. 15:1-15:5. https://doi.org/10.1145/3615834.3615855

Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction. / Sieciński, Szymon; Irshad, Muhammad Tausif; Hasan, Md Abid et al.
2023. 15:1-15:5 Paper presented at iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence, Lübeck, Germany.

Research output: Contribution to conference › Conference Papers › peer-review

TY - CONF

T1 - Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction

AU - Sieciński, Szymon

AU - Irshad, Muhammad Tausif

AU - Hasan, Md Abid

AU - Tkacz, Ewaryst

AU - Grzegorzek, Marcin

N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2023/10

Y1 - 2023/10

N2 - Signal quality assessment is essential for biomedical signal processing, analysis, and interpretation. Various methods exist, including averaged numerical values, thresholding, time- or frequency-domain analysis, and nonlinear approaches. This study evaluated the quality of gyrocardiographic signals (GCG) using symmetric projection attractor reconstruction (SPAR) analysis. Two classifiers, random forest and bagged trees, were used to assess the performance of the SPAR-based approach. Eleven features were extracted from the variables v and w, calculated on the basis of the signal delay. These features included minimum and maximum values, mean, standard deviation (SD), median, and Euclidean distance. The results showed that the SPAR-based approach achieved high accuracy, precision, and recall. The random forest classifier achieved 0.729 accuracy, 0.726 precision, and 0.729 recall, while the bagged trees classifier achieved 0.792 accuracy, 0.804 precision, and 0.792 recall. These findings suggest that the SPAR-based approach is a promising method to accurately assess the quality of GCG signals.

AB - Signal quality assessment is essential for biomedical signal processing, analysis, and interpretation. Various methods exist, including averaged numerical values, thresholding, time- or frequency-domain analysis, and nonlinear approaches. This study evaluated the quality of gyrocardiographic signals (GCG) using symmetric projection attractor reconstruction (SPAR) analysis. Two classifiers, random forest and bagged trees, were used to assess the performance of the SPAR-based approach. Eleven features were extracted from the variables v and w, calculated on the basis of the signal delay. These features included minimum and maximum values, mean, standard deviation (SD), median, and Euclidean distance. The results showed that the SPAR-based approach achieved high accuracy, precision, and recall. The random forest classifier achieved 0.729 accuracy, 0.726 precision, and 0.729 recall, while the bagged trees classifier achieved 0.792 accuracy, 0.804 precision, and 0.792 recall. These findings suggest that the SPAR-based approach is a promising method to accurately assess the quality of GCG signals.

UR - https://www.mendeley.com/catalogue/b9355a95-87f4-3732-acbc-de2062cd1cb0/

U2 - 10.1145/3615834.3615855

DO - 10.1145/3615834.3615855

M3 - Conference Papers

SP - 15:1-15:5

T2 - iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence

Y2 - 21 September 2023 through 22 September 2023

ER -

Sieciński S, Irshad MT, Hasan MA, Tkacz E, Grzegorzek M. Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction. 2023. Paper presented at iWOAR '23: Proceedings of the 8th international Workshop on Sensor-Based Activity Recognition and Artificial Intelligence, Lübeck, Germany. doi: 10.1145/3615834.3615855

Assessment of Quality of Gyrocardiograms Based on Features Derived from Symmetric Projection Attractor Reconstruction

Abstract

Conference

UN SDGs

Research Areas and Centers

DFG Research Classification Scheme

Access to Document

Other files and links

Fingerprint

Cite this