{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/an-ensemble-of-transfer-semi-supervised-and","title":"An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification","arxiv_id":"1806.06506","date":"2018-06-18","proceeding":null,"authors":["Ahmed Imtiaz Humayun","Md. Tauhiduzzaman Khan","Shabnam Ghaffarzadegan","Zhe Feng","Taufiq Hasan"],"abstract":"In this work, we propose an ensemble of classifiers to distinguish between\nvarious degrees of abnormalities of the heart using Phonocardiogram (PCG)\nsignals acquired using digital stethoscopes in a clinical setting, for the\nINTERSPEECH 2018 Computational Paralinguistics (ComParE) Heart Beats\nSubChallenge. Our primary classification framework constitutes a convolutional\nneural network with 1D-CNN time-convolution (tConv) layers, which uses features\ntransferred from a model trained on the 2016 Physionet Heart Sound Database. We\nalso employ a Representation Learning (RL) approach to generate features in an\nunsupervised manner using Deep Recurrent Autoencoders and use Support Vector\nMachine (SVM) and Linear Discriminant Analysis (LDA) classifiers. Finally, we\nutilize an SVM classifier on a high-dimensional segment-level feature extracted\nusing various functionals on short-term acoustic features, i.e., Low-Level\nDescriptors (LLD). An ensemble of the three different approaches provides a\nrelative improvement of 11.13% compared to our best single sub-system in terms\nof the Unweighted Average Recall (UAR) performance metric on the evaluation\ndataset.","url_abs":"http://arxiv.org/abs/1806.06506v2","url_pdf":"http://arxiv.org/pdf/1806.06506v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"an-ensemble-of-transfer-semi-supervised-and","repo_url":"https://github.com/osnandhu/DS5500_PCG_Classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sound-classification","task_name":"Sound Classification"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}