Compressed Sensing Framework Applying Independent Component Analysis after Undersampling for Reconstructing Electroencephalogram Signals

Abstract

This paper proposes a novel compressed sensing (CS) framework for reconstructing electroencephalogram (EEG) signals. A feature of this framework is the application of independent component analysis (ICA) to remove the interference from artifacts after undersampling in a data processing unit. Therefore, we can remove the ICA processing block from the sensing unit. In this framework, we used a random undersampling measurement matrix to suppress the Gaussian. The developed framework, in which the discrete cosine transform basis and orthogonal matching pursuit were used, was evaluated using raw EEG signals with a pseudo-model of an eye-blink artifact. The normalized mean square error (NMSE) and correlation coefficient (CC), obtained as the average of 2,000 results, were compared to quantitatively demonstrate the effectiveness of the proposed framework. The evaluation results of the NMSE and CC showed that the proposed framework could remove the interference from the artifacts under a high compression ratio.

Compressed Sensing Approach for Physiological Signals: A Review

“…Several random matrices have been proposed in the literature for sampling EEG signals, such as Random Gaussian Matrices (RGM) with entries representing absolute values, Bernoulli matrices with entries representing 1's, and random binary matrices (RBMs) containing 0's and 1's. The RGM is commonly used [51][58] [59] since it meets the RIP and incoherence criteria with high probability. Due to a large amount of on-chip memory used to store random floating-point matrix elements.…”

“…Various sensing matrix structures have been investigated on the basis of correlations between distinct channels and employed to spontaneous (un-evoked) EEG data, and it showed low spatial correlation, and rakeness-based CS has good performance at a high compression ratio. A novel framework is proposed by K. Daisuke et al [59] for analyzing EEG recordings containing artifacts. This framework eliminates the need for independent component analysis in the sensing unit, allowing the ICA block to be shifted to the data processing unit.…”

Applying K-SVD Dictionary Learning for EEG Compressed Sensing Framework with Outlier Detection and Independent Component Analysis

“…We created a dictionary matrix using the K-SVD dictionary learning algorithm with EEG signals based on the CHB-MIT scalp EEG database [12]. The sampling rate of the EEG signals was changed from 256 Hz/sample to 200 Hz/sample to be the same as that used in [6], [7], [9] When using the K-SVD dictionary for a CS framework with OD-ICA, it is necessary to reveal the optimal sparse parameters during training and reconstruction, as well as the suitable number of the dictionary matrix size. Considering the relationship with the sparse parameter r when using the OMP algorithm in the reconstruction, we determined the optimal s parameter.…”

“…For comparison purposes, the region containing pseudoeye-blink artifact was not considered when calculating the NMSE to realize same evaluation as [6], [7], and [9]. At first, suitable sparse parameters are evaluated.…”

“…Especially, it is a critical problem that reconstruction accuracy of signals achieved by CS reconstructed algorithm become worse by impulse-like disturbance called eye-blink artifacts [5]. Thus, remove eyeblink artifacts before reconstruction is desirable [6], [7]. Recently, a framework was proposed to efficiently remove the eye-blink artifacts before reconstruction by applying outlier detection and independent component analysis (OD-ICA) [8] to compressed EEG signals [9].…”