Analysis and online realization of the CCA approach for blind source separation

Blind Source Separation Method Based on Neural Network with Bias Term and Maximum Likelihood Estimation Criterion

Convergence speed and steady-state source separation performance are crucial for enable engineering applications of blind source separation methods. The modification of the loss function of the blind source separation algorithm and optimization of the algorithm to improve its performance from the perspective of neural networks (NNs) is a novel concept. In this paper, a blind source separation method, combining the maximum likelihood estimation criterion and an NN with a bias term, is proposed. The method adds L2 regularization terms for weights and biases to the loss function to improve the steady-state performance and designs a novel optimization algorithm with a dual acceleration strategy to improve the convergence speed of the algorithm. The dual acceleration strategy of the proposed optimization algorithm smooths and speeds up the originally steep, slow gradient descent in the parameter space. Compared with competing algorithms, this strategy improves the convergence speed of the algorithm by four times and the steady-state performance index by 96%. In addition, to verify the source separation performance of the algorithm more comprehensively, the simulation data with prior knowledge and the measured data without prior knowledge are used to verify the separation performance. Both simulation results and validation results based on measured data indicate that the new algorithm not only has better convergence and steady-state performance than conventional algorithms, but it is also more suitable for engineering applications.

Detection of Cardiopulmonary Activity and Related Abnormal Events Using Microsoft Kinect Sensor

Monitoring of cardiopulmonary activity is a challenge when attempted under adverse conditions, including different sleeping postures, environmental settings, and an unclear region of interest (ROI). This study proposes an efficient remote imaging system based on a Microsoft Kinect v2 sensor for the observation of cardiopulmonary-signal-and-detection-related abnormal cardiopulmonary events (e.g., tachycardia, bradycardia, tachypnea, bradypnea, and central apnoea) in many possible sleeping postures within varying environmental settings including in total darkness and whether the subject is covered by a blanket or not. The proposed system extracts the signal from the abdominal-thoracic region where cardiopulmonary activity is most pronounced, using a real-time image sequence captured by Kinect v2 sensor. The proposed system shows promising results in any sleep posture, regardless of illumination conditions and unclear ROI even in the presence of a blanket, whilst being reliable, safe, and cost-effective.

Simultaneous Tracking of Cardiorespiratory Signals for Multiple Persons Using a Machine Vision System With Noise Artifact Removal

Most existing non-contact monitoring systems are limited to detecting physiological signs from a single subject at a time. Still, another challenge facing these systems is that they are prone to noise artifacts resulting from motion of subjects, facial expressions, talking, skin tone, and illumination variations. This paper proposes an efficient non-contact system based on a digital camera to track the cardiorespiratory signal from a number of subjects (up to six persons) at the same time with a new method for noise artifact removal. The proposed system relied on the physiological and physical effects as a result of the activity of the cardiovascular and respiratory systems, such as skin color changes and head motion. Since these effects are imperceptible to the human eye and highly affected by the noise variations, we used advanced signal and video processing techniques, including developing video magnification technique, complete ensemble empirical mode decomposition with adaptive noise, and canonical correlation analysis to extract the heart rate and respiratory rate from multiple subjects under the noise artifact assumptions. The experimental results of the proposed system had a significant correlation (Pearson's correlation coefficient = 0.9994, Spearman correlation coefficient = 0.9987, and root mean square error = 0.32) when compared with the conventional contact methods (pulse oximeter and piezorespiratory belt), which makes the proposed system a promising candidate for novel applications.

Remote monitoring of cardiorespiratory signals from a hovering unmanned aerial vehicle

BACKGROUND

Remote physiological measurement might be very useful for biomedical diagnostics and monitoring. This study presents an efficient method for remotely measuring heart rate and respiratory rate from video captured by a hovering unmanned aerial vehicle (UVA). The proposed method estimates heart rate and respiratory rate based on the acquired signals obtained from video-photoplethysmography that are synchronous with cardiorespiratory activity.

METHODS

Since the PPG signal is highly affected by the noise variations (illumination variations, subject's motions and camera movement), we have used advanced signal processing techniques, including complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and canonical correlation analysis (CCA) to remove noise under these assumptions.

RESULTS

To evaluate the performance and effectiveness of the proposed method, a set of experiments were performed on 15 healthy volunteers in a front-facing position involving motion resulting from both the subject and the UAV under different scenarios and different lighting conditions.

CONCLUSION

The experimental results demonstrated that the proposed system with and without the magnification process achieves robust and accurate readings and have significant correlations compared to a standard pulse oximeter and Piezo respiratory belt. Also, the squared correlation coefficient, root mean square error, and mean error rate yielded by the proposed method with and without the magnification process were significantly better than the state-of-the-art methodologies, including independent component analysis (ICA) and principal component analysis (PCA).

Group Component Analysis for Multiblock Data: Common and Individual Feature Extraction

Real-world data are often acquired as a collection of matrices rather than as a single matrix. Such multiblock data are naturally linked and typically share some common features while at the same time exhibiting their own individual features, reflecting the underlying data generation mechanisms. To exploit the linked nature of data, we propose a new framework for common and individual feature extraction (CIFE) which identifies and separates the common and individual features from the multiblock data. Two efficient algorithms termed common orthogonal basis extraction (COBE) are proposed to extract common basis is shared by all data, independent on whether the number of common components is known beforehand. Feature extraction is then performed on the common and individual subspaces separately, by incorporating dimensionality reduction and blind source separation techniques. Comprehensive experimental results on both the synthetic and real-world data demonstrate significant advantages of the proposed CIFE method in comparison with the state-of-the-art.

Removal of eye blink artifacts in wireless EEG sensor networks using reduced-bandwidth canonical correlation analysis

OBJECTIVE

Chronic, 24/7 EEG monitoring requires the use of highly miniaturized EEG modules, which only measure a few EEG channels over a small area. For improved spatial coverage, a wireless EEG sensor network (WESN) can be deployed, consisting of multiple EEG modules, which interact through short-distance wireless communication. In this paper, we aim to remove eye blink artifacts in each EEG channel of a WESN by optimally exploiting the correlation between EEG signals from different modules, under stringent communication bandwidth constraints.

APPROACH

We apply a distributed canonical correlation analysis (CCA-)based algorithm, in which each module only transmits an optimal linear combination of its local EEG channels to the other modules. The method is validated on both synthetic and real EEG data sets, with emulated wireless transmissions.

MAIN RESULTS

While strongly reducing the amount of data that is shared between nodes, we demonstrate that the algorithm achieves the same eye blink artifact removal performance as the equivalent centralized CCA algorithm, which is at least as good as other state-of-the-art multi-channel algorithms that require a transmission of all channels.

SIGNIFICANCE

Due to their potential for extreme miniaturization, WESNs are viewed as an enabling technology for chronic EEG monitoring. However, multi-channel analysis is hampered in WESNs due to the high energy cost for wireless communication. This paper shows that multi-channel eye blink artifact removal is possible with a significantly reduced wireless communication between EEG modules.

Motor Imagery Classification Using Mu and Beta Rhythms of EEG with Strong Uncorrelating Transform Based Complex Common Spatial Patterns

Recent studies have demonstrated the disassociation between the mu and beta rhythms of electroencephalogram (EEG) during motor imagery tasks. The proposed algorithm in this paper uses a fully data-driven multivariate empirical mode decomposition (MEMD) in order to obtain the mu and beta rhythms from the nonlinear EEG signals. Then, the strong uncorrelating transform complex common spatial patterns (SUTCCSP) algorithm is applied to the rhythms so that the complex data, constructed with the mu and beta rhythms, becomes uncorrelated and its pseudocovariance provides supplementary power difference information between the two rhythms. The extracted features using SUTCCSP that maximize the interclass variances are classified using various classification algorithms for the separation of the left- and right-hand motor imagery EEG acquired from the Physionet database. This paper shows that the supplementary information of the power difference between mu and beta rhythms obtained using SUTCCSP provides an important feature for the classification of the left- and right-hand motor imagery tasks. In addition, MEMD is proved to be a preferred preprocessing method for the nonlinear and nonstationary EEG signals compared to the conventional IIR filtering. Finally, the random forest classifier yielded a high performance for the classification of the motor imagery tasks.

Adaptive quasi-Newton algorithm for source extraction via CCA approach

This paper addresses the problem of adaptive source extraction via the canonical correlation analysis (CCA) approach. Based on Liu's analysis of CCA approach, we propose a new criterion for source extraction, which is proved to be equivalent to the CCA criterion. Then, a fast and efficient online algorithm using quasi-Newton iteration is developed. The stability of the algorithm is also analyzed using Lyapunov's method, which shows that the proposed algorithm asymptotically converges to the global minimum of the criterion. Simulation results are presented to prove our theoretical analysis and demonstrate the merits of the proposed algorithm in terms of convergence speed and successful rate for source extraction.

Weighted rule based adaptive algorithm for simultaneously extracting generalized eigenvectors

In this brief, we consider extracting generalized eigenvectors in parallel for the generalized eigendecomposition problem. The problem is formulated as an optimization problem of minimizing an unconstrained quartic cost function based on the weighted rule. It is shown that the proposed weighted cost function has a unique global minimum, which corresponds to the principal generalized eigenvectors. In order to estimate the principal generalized eigenvector matrix efficiently, we simplify the quartic cost function as a quadric one by making an appropriate approximation, and then derive a fast algorithm for extracting the principal generalized eigenvector in parallel. We also show the application of the proposed algorithm in blind source separation. Numerical simulations are performed, and the results demonstrate the performance of the proposed algorithm.

OI and fMRI signal separation using both temporal and spatial autocorrelations

Separating brain imaging signals by maximizing their autocorrelations is an important component of blind source separation (BSS). Canonical correlation analysis (CCA), one of leading BSS techniques, has been widely used for analyzing optical imaging (OI) and functional magnetic resonance imaging (fMRI) data. However, because of the need to reduce dimensionality and ignore spatial autocorrelation, CCA is problematic for separating temporal signal sources. To solve the problems of CCA, "straightforward image projection" (SIP) has been incorporated into temporal BSS. This novel method, termed low-dimensional canonical correlation analysis (LD-CCA), relies on the spatial and temporal autocorrelations of all genuine signals of interest. Incorporating both spatial and temporal information, here we introduce a "generalized timecourse" technique in which data are artificially reorganized prior to separation. The quantity of spatial plus temporal autocorrelations can then be defined. By maximizing temporal and spatial autocorrelations in combination, LD-CCA is able to obtain expected "real" signal sources. Generalized timecourses are low-dimensional, eliminating the need for dimension reduction. This removes the risk of discarding useful information. The new method is compared with temporal CCA and temporal independent component analysis (tICA). Comparison of simulated data showed that LD-CCA was more effective for recovering signal sources. Comparisons using real intrinsic OI and fMRI data also supported the validity of LD-CCA.

Joint Blind Source Separation by Multi-set Canonical Correlation Analysis

In this work, we introduce a simple and effective scheme to achieve joint blind source separation (BSS) of multiple datasets using multi-set canonical correlation analysis (M-CCA) [1]. We first propose a generative model of joint BSS based on the correlation of latent sources within and between datasets. We specify source separability conditions, and show that, when the conditions are satisfied, the group of corresponding sources from each dataset can be jointly extracted by M-CCA through maximization of correlation among the extracted sources. We compare source separation performance of the M-CCA scheme with other joint BSS methods and demonstrate the superior performance of the M-CCA scheme in achieving joint BSS for a large number of datasets, group of corresponding sources with heterogeneous correlation values, and complex-valued sources with circular and non-circular distributions. We apply M-CCA to analysis of functional magnetic resonance imaging (fMRI) data from multiple subjects and show its utility in estimating meaningful brain activations from a visuomotor task.