The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals
This research studies the effects of both Daubechies wavelet basis function (DWBF) and decomposition level (DL) on the performance of detecting atrial fibrillation (AF) based on electrocardiograms (ECGs). ECG signals (consisting of 23 AF data and 18 normal data from MIT-BIH) were decomposed at vario...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/5/3036 |
| _version_ | 1797615730271715328 |
|---|---|
| author | Satria Mandala Annisa Rizki Pratiwi Wibowo Adiwijaya Suyanto Mohd Soperi Mohd Zahid Ardian Rizal |
| author_facet | Satria Mandala Annisa Rizki Pratiwi Wibowo Adiwijaya Suyanto Mohd Soperi Mohd Zahid Ardian Rizal |
| author_sort | Satria Mandala |
| collection | DOAJ |
| description | This research studies the effects of both Daubechies wavelet basis function (DWBF) and decomposition level (DL) on the performance of detecting atrial fibrillation (AF) based on electrocardiograms (ECGs). ECG signals (consisting of 23 AF data and 18 normal data from MIT-BIH) were decomposed at various levels using several types of DWBF to obtain four wavelet coefficient features (WCFs), namely, minimum (min), maximum (max), mean, and standard deviation (stdev). These features were then classified to detect the presence of AF using a support vector machine (SVM) classifier. Distribution of training and testing data for the SVM uses the 5-fold cross-validation (CV) principle to produce optimum detection performance. In this study, AF detection performance is measured and analyzed based on accuracy, sensitivity, and specificity metrics. The results of the analysis show that accuracy tends to decrease with increases in the decomposition level. In addition, it becomes stable in various types of DWBF. For both sensitivity and specificity, the results of the analysis show that increasing the decomposition level also causes a decrease in both sensitivity and specificity. However, unlike the accuracy, changing the DWBF type causes both two metrics to fluctuate over a wider range. The statistical results also indicate that the highest AF accuracy detection (i.e., 94.17%) is obtained at the Daubechies 2 (DB<sub>2</sub>) function with a decomposition level of 4, whereas the highest sensitivity, 97.57%, occurs when the AF detection uses DB<sub>6</sub> with a decomposition level of 2. Finally, DB<sub>2</sub> with decomposition level 4 results in 96.750% for specificity. The finding of this study is that selecting the appropriate DL has a more significant effect than DWBF on AF detection using WCF. |
| first_indexed | 2024-03-11T07:30:49Z |
| format | Article |
| id | doaj.art-815909b3b4f3445d8aabc12202fdec2c |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T07:30:49Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-815909b3b4f3445d8aabc12202fdec2c2023-11-17T07:18:24ZengMDPI AGApplied Sciences2076-34172023-02-01135303610.3390/app13053036The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) SignalsSatria Mandala0Annisa Rizki Pratiwi Wibowo1Adiwijaya2Suyanto3Mohd Soperi Mohd Zahid4Ardian Rizal5Human Centric Engineering & School of Computing, Telkom University, Jl. Telekomunikasi No. 1, Bandung 40257, West Java, IndonesiaHuman Centric Engineering & School of Computing, Telkom University, Jl. Telekomunikasi No. 1, Bandung 40257, West Java, IndonesiaHuman Centric Engineering & School of Computing, Telkom University, Jl. Telekomunikasi No. 1, Bandung 40257, West Java, IndonesiaHuman Centric Engineering & School of Computing, Telkom University, Jl. Telekomunikasi No. 1, Bandung 40257, West Java, IndonesiaDepartment of Computer and Information Sciences, Universiti Teknologi PETRONAS, Seri Iskandar 32610, Perak, MalaysiaDepartment of Cardiology and Vascular Medicine, Faculty of Medicine, Universitas Brawijaya, Jl Veteran, Malang 65145, East Java, IndonesiaThis research studies the effects of both Daubechies wavelet basis function (DWBF) and decomposition level (DL) on the performance of detecting atrial fibrillation (AF) based on electrocardiograms (ECGs). ECG signals (consisting of 23 AF data and 18 normal data from MIT-BIH) were decomposed at various levels using several types of DWBF to obtain four wavelet coefficient features (WCFs), namely, minimum (min), maximum (max), mean, and standard deviation (stdev). These features were then classified to detect the presence of AF using a support vector machine (SVM) classifier. Distribution of training and testing data for the SVM uses the 5-fold cross-validation (CV) principle to produce optimum detection performance. In this study, AF detection performance is measured and analyzed based on accuracy, sensitivity, and specificity metrics. The results of the analysis show that accuracy tends to decrease with increases in the decomposition level. In addition, it becomes stable in various types of DWBF. For both sensitivity and specificity, the results of the analysis show that increasing the decomposition level also causes a decrease in both sensitivity and specificity. However, unlike the accuracy, changing the DWBF type causes both two metrics to fluctuate over a wider range. The statistical results also indicate that the highest AF accuracy detection (i.e., 94.17%) is obtained at the Daubechies 2 (DB<sub>2</sub>) function with a decomposition level of 4, whereas the highest sensitivity, 97.57%, occurs when the AF detection uses DB<sub>6</sub> with a decomposition level of 2. Finally, DB<sub>2</sub> with decomposition level 4 results in 96.750% for specificity. The finding of this study is that selecting the appropriate DL has a more significant effect than DWBF on AF detection using WCF.https://www.mdpi.com/2076-3417/13/5/3036atrial fibrillation detectionfeature extractionwavelet coefficientDaubechies wavelet basis functionartificial intelligence |
| spellingShingle | Satria Mandala Annisa Rizki Pratiwi Wibowo Adiwijaya Suyanto Mohd Soperi Mohd Zahid Ardian Rizal The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals Applied Sciences atrial fibrillation detection feature extraction wavelet coefficient Daubechies wavelet basis function artificial intelligence |
| title | The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals |
| title_full | The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals |
| title_fullStr | The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals |
| title_full_unstemmed | The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals |
| title_short | The Effects of Daubechies Wavelet Basis Function (DWBF) and Decomposition Level on the Performance of Artificial Intelligence-Based Atrial Fibrillation (AF) Detection Based on Electrocardiogram (ECG) Signals |
| title_sort | effects of daubechies wavelet basis function dwbf and decomposition level on the performance of artificial intelligence based atrial fibrillation af detection based on electrocardiogram ecg signals |
| topic | atrial fibrillation detection feature extraction wavelet coefficient Daubechies wavelet basis function artificial intelligence |
| url | https://www.mdpi.com/2076-3417/13/5/3036 |
| work_keys_str_mv | AT satriamandala theeffectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT annisarizkipratiwiwibowo theeffectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT adiwijaya theeffectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT suyanto theeffectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT mohdsoperimohdzahid theeffectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT ardianrizal theeffectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT satriamandala effectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT annisarizkipratiwiwibowo effectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT adiwijaya effectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT suyanto effectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT mohdsoperimohdzahid effectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals AT ardianrizal effectsofdaubechieswaveletbasisfunctiondwbfanddecompositionlevelontheperformanceofartificialintelligencebasedatrialfibrillationafdetectionbasedonelectrocardiogramecgsignals |