{"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/heartbeat-anomaly-detection-using-adversarial","title":"Heartbeat Anomaly Detection using Adversarial Oversampling","arxiv_id":"1901.09972","date":"2019-01-28","proceeding":null,"authors":["Jefferson L. P. Lima","David Macêdo","Cleber Zanchettin"],"abstract":"Cardiovascular diseases are one of the most common causes of death in the\nworld. Prevention, knowledge of previous cases in the family, and early\ndetection is the best strategy to reduce this fact. Different machine learning\napproaches to automatic diagnostic are being proposed to this task. As in most\nhealth problems, the imbalance between examples and classes is predominant in\nthis problem and affects the performance of the automated solution. In this\npaper, we address the classification of heartbeats images in different\ncardiovascular diseases. We propose a two-dimensional Convolutional Neural\nNetwork for classification after using a InfoGAN architecture for generating\nsynthetic images to unbalanced classes. We call this proposal Adversarial\nOversampling and compare it with the classical oversampling methods as SMOTE,\nADASYN, and RandomOversampling. The results show that the proposed approach\nimproves the classifier performance for the minority classes without harming\nthe performance in the balanced classes.","url_abs":"http://arxiv.org/abs/1901.09972v1","url_pdf":"http://arxiv.org/pdf/1901.09972v1.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":"heartbeat-anomaly-detection-using-adversarial","repo_url":"https://github.com/JeffersonLPLima/adversarial_oversampling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"infogan","method_name":"InfoGAN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"smote","method_name":"SMOTE"},{"method_slug":"softmax","method_name":"Softmax"}],"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}