Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition Frameworks

Electroencephalography (EEG) signals are frequently compromised by missing data due to electrode contact issues or subject movement. Tensor decomposition has emerged as a powerful technique for analyzing multidimensional EEG data. This study evaluates various tensor-based methods for reconstructing...

Full description

Saved in:
Bibliographic Details
Main Authors: Yue Zhang, Huanmin Ge, Chencheng Huang, Xinhua Su
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11087549/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849245896219295744
author Yue Zhang
Huanmin Ge
Chencheng Huang
Xinhua Su
author_facet Yue Zhang
Huanmin Ge
Chencheng Huang
Xinhua Su
author_sort Yue Zhang
collection DOAJ
description Electroencephalography (EEG) signals are frequently compromised by missing data due to electrode contact issues or subject movement. Tensor decomposition has emerged as a powerful technique for analyzing multidimensional EEG data. This study evaluates various tensor-based methods for reconstructing structured and unstructured missing EEG signals, including recovery methods based on canonical polyadic (CP) decomposition, tensor singular value decomposition (t-SVD), and tucker decomposition. Notably, this research represents the first application of t-SVD-based recovery to missing EEG data. To rigorously assess the efficacy of our proposed method, we implement a dual evaluation framework encompassing: a) signal recovery indices and b) classification performance metrics. In the most challenging structured missing data scenario (missing segments <inline-formula> <tex-math notation="LaTeX">$N=80$ </tex-math></inline-formula>, duration <inline-formula> <tex-math notation="LaTeX">$d=1.8s$ </tex-math></inline-formula>), the t-SVD-based method demonstrate superior performance based on signal recovery indices, followed by the tucker-based method, while CP-based approaches exhibited inferior results. We further evaluate the impact of signal recovery on classification accuracy by comparing performance on complete, missing, and recovered data using six classifiers and five metrics. In the most severe structured-missing case, employing a Linear Discriminant Analysis classifier, the t-SVD method enhance accuracy from 46.36% (missing data) to 56.50%, surpassing the tucker-based method (54.29%) and both CP-based methods (48.21% and 49.07%), approaching the accuracy achieved with the original data (58.57%). These results demonstrate the superior capability of t-SVD-based recovery method in preserving discriminative features within EEG signals. This research offers promising solutions for enhancing EEG signals quality and subsequent analysis in challenging real-world scenarios.
format Article
id doaj-art-e4932e3ba87f4fc4822b2cc73cec4819
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-e4932e3ba87f4fc4822b2cc73cec48192025-08-20T03:58:40ZengIEEEIEEE Access2169-35362025-01-011313018513020010.1109/ACCESS.2025.359127811087549Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition FrameworksYue Zhang0Huanmin Ge1https://orcid.org/0009-0005-8843-5221Chencheng Huang2Xinhua Su3School of Sports Engineering, Beijing Sport University, Beijing, ChinaSchool of Sports Engineering, Beijing Sport University, Beijing, ChinaSchool of Sports Engineering, Beijing Sport University, Beijing, ChinaSchool of Sports Engineering, Beijing Sport University, Beijing, ChinaElectroencephalography (EEG) signals are frequently compromised by missing data due to electrode contact issues or subject movement. Tensor decomposition has emerged as a powerful technique for analyzing multidimensional EEG data. This study evaluates various tensor-based methods for reconstructing structured and unstructured missing EEG signals, including recovery methods based on canonical polyadic (CP) decomposition, tensor singular value decomposition (t-SVD), and tucker decomposition. Notably, this research represents the first application of t-SVD-based recovery to missing EEG data. To rigorously assess the efficacy of our proposed method, we implement a dual evaluation framework encompassing: a) signal recovery indices and b) classification performance metrics. In the most challenging structured missing data scenario (missing segments <inline-formula> <tex-math notation="LaTeX">$N=80$ </tex-math></inline-formula>, duration <inline-formula> <tex-math notation="LaTeX">$d=1.8s$ </tex-math></inline-formula>), the t-SVD-based method demonstrate superior performance based on signal recovery indices, followed by the tucker-based method, while CP-based approaches exhibited inferior results. We further evaluate the impact of signal recovery on classification accuracy by comparing performance on complete, missing, and recovered data using six classifiers and five metrics. In the most severe structured-missing case, employing a Linear Discriminant Analysis classifier, the t-SVD method enhance accuracy from 46.36% (missing data) to 56.50%, surpassing the tucker-based method (54.29%) and both CP-based methods (48.21% and 49.07%), approaching the accuracy achieved with the original data (58.57%). These results demonstrate the superior capability of t-SVD-based recovery method in preserving discriminative features within EEG signals. This research offers promising solutions for enhancing EEG signals quality and subsequent analysis in challenging real-world scenarios.https://ieeexplore.ieee.org/document/11087549/Electroencephalogrammissing datatensor recoveryclassification
spellingShingle Yue Zhang
Huanmin Ge
Chencheng Huang
Xinhua Su
Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition Frameworks
IEEE Access
Electroencephalogram
missing data
tensor recovery
classification
title Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition Frameworks
title_full Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition Frameworks
title_fullStr Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition Frameworks
title_full_unstemmed Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition Frameworks
title_short Exploring Tensor-Based Optimization for Missing EEG Signal Recovery: A Comparative Study of Optimization Methods Across Different Tensor Decomposition Frameworks
title_sort exploring tensor based optimization for missing eeg signal recovery a comparative study of optimization methods across different tensor decomposition frameworks
topic Electroencephalogram
missing data
tensor recovery
classification
url https://ieeexplore.ieee.org/document/11087549/
work_keys_str_mv AT yuezhang exploringtensorbasedoptimizationformissingeegsignalrecoveryacomparativestudyofoptimizationmethodsacrossdifferenttensordecompositionframeworks
AT huanminge exploringtensorbasedoptimizationformissingeegsignalrecoveryacomparativestudyofoptimizationmethodsacrossdifferenttensordecompositionframeworks
AT chenchenghuang exploringtensorbasedoptimizationformissingeegsignalrecoveryacomparativestudyofoptimizationmethodsacrossdifferenttensordecompositionframeworks
AT xinhuasu exploringtensorbasedoptimizationformissingeegsignalrecoveryacomparativestudyofoptimizationmethodsacrossdifferenttensordecompositionframeworks