Heart Sounds Classification for a Medical Diagnostic Assistance

• Main Authors: Abdelhamid Bourouhou, Abdelilah Jilbab, Chafik Nacir, Ahmed Hammouch
• Format: Article
• Language: English
• Published: International Association of Online Engineering (IAOE) 2019-07-01
• Series: International Journal of Online and Biomedical Engineering
• Subjects: Heart disease; PCG; supervised learning classifier; GLM; SVM; Physio-Net/CinC Challenge 2016
• Online Access: https://online-journals.org/index.php/i-joe/article/view/10804

<span lang="EN-US">In order to develop the assessment of phonocardiogram “PCG” signal for discrimination between two of people classes – individuals with heart disease and healthy one- we have adopted the database provided by "The PhysioNet/Computing in Cardilogy Challenge 2016", which contains records of heart sounds 'PCG '. This database is chosen in order to compare and validate our results with those already published. We subsequently extracted 20 features from each provided record. For classification, we used the Generalized Linear Model (GLM), and the Support Vector Machines (SVMs) with its different types of kernels (i.e.; Linear, polynomial and MLP). The best classification accuracy obtained was 88.25%, using the SVM classifier with an MLP kernel.</span>