{"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/learning-front-end-filter-bank-parameters","title":"Learning Front-end Filter-bank Parameters using Convolutional Neural Networks for Abnormal Heart Sound Detection","arxiv_id":"1806.05892","date":"2018-06-15","proceeding":null,"authors":["Ahmed Imtiaz Humayun","Shabnam Ghaffarzadegan","Zhe Feng","Taufiq Hasan"],"abstract":"Automatic heart sound abnormality detection can play a vital role in the\nearly diagnosis of heart diseases, particularly in low-resource settings. The\nstate-of-the-art algorithms for this task utilize a set of Finite Impulse\nResponse (FIR) band-pass filters as a front-end followed by a Convolutional\nNeural Network (CNN) model. In this work, we propound a novel CNN architecture\nthat integrates the front-end bandpass filters within the network using\ntime-convolution (tConv) layers, which enables the FIR filter-bank parameters\nto become learnable. Different initialization strategies for the learnable\nfilters, including random parameters and a set of predefined FIR filter-bank\ncoefficients, are examined. Using the proposed tConv layers, we add constraints\nto the learnable FIR filters to ensure linear and zero phase responses.\nExperimental evaluations are performed on a balanced 4-fold cross-validation\ntask prepared using the PhysioNet/CinC 2016 dataset. Results demonstrate that\nthe proposed models yield superior performance compared to the state-of-the-art\nsystem, while the linear phase FIR filterbank method provides an absolute\nimprovement of 9.54% over the baseline in terms of an overall accuracy metric.","url_abs":"http://arxiv.org/abs/1806.05892v1","url_pdf":"http://arxiv.org/pdf/1806.05892v1.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":"learning-front-end-filter-bank-parameters","repo_url":"https://github.com/AhmedImtiazPrio/heartnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}