Scholarlink

<p>This study proposes a novel approach utilizing a recently developed empirical statistical method to address redundancy in source imaging problems. This methodology integrates time and frequency domain analyses, leveraging a 3D tensor-based Canonical Polyadic Decomposition with wavelet transform. The approach is validated using epileptic EEG data, with hyperparameters optimized through K-fold cross-validation. The proposed method is benchmarked against state-of-the-art techniques across three test cases. It also improves the interpretability of epileptic EEG data and delivers robust, explainable results.</p>

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

Tensor and machine learning based reduced algorithm using wavelet transform for EEG source localization

  • 期刊论文

  • 发表日期：

    2025年5月5日

查看全文
  • Teja Mannepalli,
  • Aurobinda Routray

摘要

This study proposes a novel approach utilizing a recently developed empirical statistical method to address redundancy in source imaging problems. This methodology integrates time and frequency domain analyses, leveraging a 3D tensor-based Canonical Polyadic Decomposition with wavelet transform. The approach is validated using epileptic EEG data, with hyperparameters optimized through K-fold cross-validation. The proposed method is benchmarked against state-of-the-art techniques across three test cases. It also improves the interpretability of epileptic EEG data and delivers robust, explainable results.