Computer-aided Phonocardiogram Classification using Multidomain Time and Frequency Features
| Autor: | Jehan Dastagir, Kaleem Nawaz Khan, Muhammad Salman Khan, Faiq Ahmad Khan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
0209 industrial biotechnology
Phonocardiogram Signal processing business.industry Computer science Decision tree Pattern recognition 02 engineering and technology Time–frequency analysis Support vector machine Statistical classification ComputingMethodologies_PATTERNRECOGNITION 020901 industrial engineering & automation Classifier (linguistics) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Sensitivity (control systems) business |
| Zdroj: | 2021 International Conference on Artificial Intelligence (ICAI). |
| DOI: | 10.1109/icai52203.2021.9445235 |
| Popis: | This paper presents an improved classification technique for automated classification of phonocardiogram (PCG) signals. In the light of presented literature study, a number of representative multidomain time and frequency features are suggested for the heart signal analysis and classification with comparatively large and imbalanced dataset. Machine learning algorithms such as support vector machines (SVM), k-nearest neighbor (KNN), Decision Tree (DT) and TreeBagger (TB) are tested for heart sound (HS) classification. For the performance evaluation metrics such as, accuracy, final score, sensitivity and specificity are computed for each classifier. Overall, all the classification algorithms performed well by achieving final scores greater than 85% but with the designed setup and dataset SVM outperformed others by achieving final score of 94.20% (Accuracy 95.31%, Sensitivity 92.30%, Specificity 96.08%). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|