Scholarlink

By contrasting its performance with that of the normalized least mean square (NLMS) algorithm, this study investigates the use of the Error Normalized Least Mean Square (ENLMS) algorithm in adaptive signal processing for denoising phonocardiograms (PCGs). The study emphasizes the value of adaptive filtering in reducing noise and improving signal quality, especially for cardiac diagnostic PCG signals. The approach outperforms NLMS in terms of noise attenuation and convergence speed under a range of noise situations by utilizing ENLMS’s error normalization capabilities. Significant improvements in mean square error (MSE) and signal-to-noise ratio (SNR) metrics are revealed by simulation results, demonstrating ENLMS’s promise for reliable real-time flexibility in medical diagnostics. ENLMS is highlighted in this comparative research as an economical and effective option for noise reduction in crucial signal processing applications.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Error Normalized LMS-Based Low-Complexity Noise Removal Technique for Acoustic Signal

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Tanmay Umesh Pawar,
  • Sanskruti Gopinath More,
  • Krishna Jhanwar,
  • S. Hannah Pauline,
  • R. Senthil Kumaran

摘要

By contrasting its performance with that of the normalized least mean square (NLMS) algorithm, this study investigates the use of the Error Normalized Least Mean Square (ENLMS) algorithm in adaptive signal processing for denoising phonocardiograms (PCGs). The study emphasizes the value of adaptive filtering in reducing noise and improving signal quality, especially for cardiac diagnostic PCG signals. The approach outperforms NLMS in terms of noise attenuation and convergence speed under a range of noise situations by utilizing ENLMS’s error normalization capabilities. Significant improvements in mean square error (MSE) and signal-to-noise ratio (SNR) metrics are revealed by simulation results, demonstrating ENLMS’s promise for reliable real-time flexibility in medical diagnostics. ENLMS is highlighted in this comparative research as an economical and effective option for noise reduction in crucial signal processing applications.