Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment

Indra Hermawan; Muhammad Anwar  Ma'sum; P. Riskyana Dewi Intan; Wisnu Jatmiko; Budi Wiweko; Alfred Boediman; Beno K. Pradekso

doi:10.1109/IWBIS.2019.8935757

Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment

Indra Hermawan, Muhammad Anwar Ma'sum, P. Riskyana Dewi Intan, Wisnu Jatmiko, Budi Wiweko, Alfred Boediman, Beno K. Pradekso

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

6 Citations (Scopus)

Abstract

This study proposes a method for ECG signals quality assessment (SQA) by using temporal feature, and heuristic rule. The ECG signal will be classified as acceptable or unacceptable. Seven types of noise were able to be detected by the prosed method. The noises are: FL, TVN, BW, AB, MA, PLI and AWGN. The proposed method is aimed to have better performance for SQA than classical machine learning method. The experiment is conducted by using 1000 instances ECG signal. The experiment result shows that db8 has the best performance with 0.86, 0.85 and 85.6% on lead-1 signal and 0.69, 0.79, and 74% on lead-5 signal for specificity, sensitivity and accuracy respectively. Compared to the classical machine learning, the proposed heuristic method has same accuracy but has 48% and 31% better specificity for lead-1 and lead-5. It means that the proposed method has far better ability to detect noise.

Original language	English
Title of host publication	2019 International Workshop on Big Data and Information Security, IWBIS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-8
Number of pages	8
ISBN (Electronic)	9781728153476
DOIs	https://doi.org/10.1109/IWBIS.2019.8935757
Publication status	Published - Oct 2019
Event	2019 International Workshop on Big Data and Information Security, IWBIS 2019 - Bali, Indonesia Duration: 11 Oct 2019 → …

Publication series

Name	2019 International Workshop on Big Data and Information Security, IWBIS 2019

Conference

Conference	2019 International Workshop on Big Data and Information Security, IWBIS 2019
Country/Territory	Indonesia
City	Bali
Period	11/10/19 → …

Keywords

classical machine learning
electrocardiogram
heuristic rule
signal quality
temporal features
wavelet

Access to Document

10.1109/IWBIS.2019.8935757

Cite this

Hermawan, I., Ma'sum, M. A., Riskyana Dewi Intan, P., Jatmiko, W., Wiweko, B., Boediman, A., & Pradekso, B. K. (2019). Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment. In 2019 International Workshop on Big Data and Information Security, IWBIS 2019 (pp. 1-8). Article 8935757 (2019 International Workshop on Big Data and Information Security, IWBIS 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IWBIS.2019.8935757

Hermawan, Indra ; Ma'sum, Muhammad Anwar ; Riskyana Dewi Intan, P. et al. / Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment. 2019 International Workshop on Big Data and Information Security, IWBIS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1-8 (2019 International Workshop on Big Data and Information Security, IWBIS 2019).

@inproceedings{8543a32b982d4d87ad951af3df8667f9,

title = "Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment",

abstract = "This study proposes a method for ECG signals quality assessment (SQA) by using temporal feature, and heuristic rule. The ECG signal will be classified as acceptable or unacceptable. Seven types of noise were able to be detected by the prosed method. The noises are: FL, TVN, BW, AB, MA, PLI and AWGN. The proposed method is aimed to have better performance for SQA than classical machine learning method. The experiment is conducted by using 1000 instances ECG signal. The experiment result shows that db8 has the best performance with 0.86, 0.85 and 85.6% on lead-1 signal and 0.69, 0.79, and 74% on lead-5 signal for specificity, sensitivity and accuracy respectively. Compared to the classical machine learning, the proposed heuristic method has same accuracy but has 48% and 31% better specificity for lead-1 and lead-5. It means that the proposed method has far better ability to detect noise.",

keywords = "classical machine learning, electrocardiogram, heuristic rule, signal quality, temporal features, wavelet",

author = "Indra Hermawan and Ma'sum, {Muhammad Anwar} and {Riskyana Dewi Intan}, P. and Wisnu Jatmiko and Budi Wiweko and Alfred Boediman and Pradekso, {Beno K.}",

year = "2019",

month = oct,

doi = "10.1109/IWBIS.2019.8935757",

language = "English",

series = "2019 International Workshop on Big Data and Information Security, IWBIS 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1--8",

booktitle = "2019 International Workshop on Big Data and Information Security, IWBIS 2019",

address = "United States",

note = "2019 International Workshop on Big Data and Information Security, IWBIS 2019 ; Conference date: 11-10-2019",

}

Hermawan, I, Ma'sum, MA, Riskyana Dewi Intan, P, Jatmiko, W , Wiweko, B, Boediman, A & Pradekso, BK 2019, Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment. in 2019 International Workshop on Big Data and Information Security, IWBIS 2019., 8935757, 2019 International Workshop on Big Data and Information Security, IWBIS 2019, Institute of Electrical and Electronics Engineers Inc., pp. 1-8, 2019 International Workshop on Big Data and Information Security, IWBIS 2019, Bali, Indonesia, 11/10/19. https://doi.org/10.1109/IWBIS.2019.8935757

Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment. / Hermawan, Indra; Ma'sum, Muhammad Anwar ; Riskyana Dewi Intan, P. et al.
2019 International Workshop on Big Data and Information Security, IWBIS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1-8 8935757 (2019 International Workshop on Big Data and Information Security, IWBIS 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment

AU - Hermawan, Indra

AU - Ma'sum, Muhammad Anwar

AU - Riskyana Dewi Intan, P.

AU - Jatmiko, Wisnu

AU - Wiweko, Budi

AU - Boediman, Alfred

AU - Pradekso, Beno K.

PY - 2019/10

Y1 - 2019/10

N2 - This study proposes a method for ECG signals quality assessment (SQA) by using temporal feature, and heuristic rule. The ECG signal will be classified as acceptable or unacceptable. Seven types of noise were able to be detected by the prosed method. The noises are: FL, TVN, BW, AB, MA, PLI and AWGN. The proposed method is aimed to have better performance for SQA than classical machine learning method. The experiment is conducted by using 1000 instances ECG signal. The experiment result shows that db8 has the best performance with 0.86, 0.85 and 85.6% on lead-1 signal and 0.69, 0.79, and 74% on lead-5 signal for specificity, sensitivity and accuracy respectively. Compared to the classical machine learning, the proposed heuristic method has same accuracy but has 48% and 31% better specificity for lead-1 and lead-5. It means that the proposed method has far better ability to detect noise.

AB - This study proposes a method for ECG signals quality assessment (SQA) by using temporal feature, and heuristic rule. The ECG signal will be classified as acceptable or unacceptable. Seven types of noise were able to be detected by the prosed method. The noises are: FL, TVN, BW, AB, MA, PLI and AWGN. The proposed method is aimed to have better performance for SQA than classical machine learning method. The experiment is conducted by using 1000 instances ECG signal. The experiment result shows that db8 has the best performance with 0.86, 0.85 and 85.6% on lead-1 signal and 0.69, 0.79, and 74% on lead-5 signal for specificity, sensitivity and accuracy respectively. Compared to the classical machine learning, the proposed heuristic method has same accuracy but has 48% and 31% better specificity for lead-1 and lead-5. It means that the proposed method has far better ability to detect noise.

KW - classical machine learning

KW - electrocardiogram

KW - heuristic rule

KW - signal quality

KW - temporal features

KW - wavelet

UR - http://www.scopus.com/inward/record.url?scp=85077978399&partnerID=8YFLogxK

U2 - 10.1109/IWBIS.2019.8935757

DO - 10.1109/IWBIS.2019.8935757

M3 - Conference contribution

T3 - 2019 International Workshop on Big Data and Information Security, IWBIS 2019

SP - 1

EP - 8

BT - 2019 International Workshop on Big Data and Information Security, IWBIS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 International Workshop on Big Data and Information Security, IWBIS 2019

Y2 - 11 October 2019

ER -

Hermawan I, Ma'sum MA, Riskyana Dewi Intan P, Jatmiko W , Wiweko B, Boediman A et al. Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment. In 2019 International Workshop on Big Data and Information Security, IWBIS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1-8. 8935757. (2019 International Workshop on Big Data and Information Security, IWBIS 2019). doi: 10.1109/IWBIS.2019.8935757

Temporal feature and heuristics-based Noise Detection over Classical Machine Learning for ECG Signal Quality Assessment

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this