Heart Rate Variability Analysis for Cardiovascular Disease Detection Using MIDNet 18 Architecture
Dr.P. BalamuruganAssociate Professor, Department of Networking and Communications, SRM Institute of Science and Technology, Kattankulathur, Tamil Nadu, India. balamurp@srmist.edu.in0000-0001-8394-1129
Dr. Sanjay KumarAssistant Professor, Department of Computer Science, Kalinga University, Naya Raipur, Chhattisgarh, India. ku.sanjaykumar@kalingauniversity.ac.in0009-0004-2958-2902
Dr. Kamalraj SubramaniamProfessor and Head, Department of Biomedical Engineering, Faculty of Engineering, Karpagam Academy of Higher Education, India. kamalrajece@gmail.com0000-0002-8517-2578
Dr.M.A.P. ManimekalaiAssistant Professor, Department of ECE, Karunya Institute of Technology and Sciences, Coimbatore, India. manimekalai@karunya.edu0000-0001-8854-4579
Keywords: Cardiac Vascular Disease, Computer-Aided Diagnostic Systems, Deep Learning, MIDNet.
Abstract
Electrocardiogram (ECG) technology has grown as a crucial diagnostic method in the clinical cardiovascular field, helping doctors identify heart conditions and track the heart's electrical activity easily. The ECG identifies CVDs by detecting ventricular hypertrophy, arrhythmia, myocardial infarction, and atrial fibrillation. Recent studies explore transforming wireless patient data through IoT and MEMS devices, designing and integrating small, power-efficient ECG sensors for wearables, and automatically detecting heartbeats. The patient's special heart rhythm can be identified because advanced computers work together with a strong processor to gather health information. The wearable ECG denoising module for the multistage classification system was created by utilizing the Zynq7000 ZedBoard, an advanced and highly regarded platform in this research project. Preprocessing biosignals is essential for analysis because it affects both the data's quality and clinicians' decision-making abilities. It's crucial for how the bio-signals are classified in the system. An efficient digital filter, tailored for resource efficiency, is programmed onto an FPGA to reduce noise from an ECG signal.