Including Independent Component Analysis Research Articles

Tracking gaze position from EEG: Exploring the possibility of an EEG-based virtual eye-tracker.

Ocular artifact has long been viewed as an impediment to the interpretation of electroencephalogram (EEG) signals in basic and applied research. Today, the use of blind source separation (BSS) methods, including independent component analysis (ICA) and second-order blind identification (SOBI), is considered an essential step in improving the quality of neural signals. Recently, we introduced a method consisting of SOBI and a discriminant and similarity (DANS)-based identification method, capable of identifying and extracting eye movement-related components. These recovered components can be localized within ocular structures with a high goodness of fit (>95%). This raised the possibility that such EEG-derived SOBI components may be used to build predictive models for tracking gaze position. As proof of this new concept, we designed an EEG-based virtual eye-tracker (EEG-VET) for tracking eye movement from EEG alone. The EEG-VET is composed of a SOBI algorithm for separating EEG signals into different components, a DANS algorithm for automatically identifying ocular components, and a linear model to transfer ocular components into gaze positions. The prototype of EEG-VET achieved an accuracy of 0.920° and precision of 1.510° of a visual angle in the best participant, whereas an average accuracy of 1.008°±0.357° and a precision of 2.348°±0.580° of a visual angle across all participants (N=18). This work offers a novel approach that readily co-registers eye movement and neural signals from a single-EEG recording, thus increasing the ease of studying neural mechanisms underlying natural cognition in the context of free eye movement.

Less is more: balancing noise reduction and data retention in fMRI with data-driven scrubbing

Functional MRI (fMRI) data may be contaminated by artifacts arising from a myriad of sources, including subject head motion, respiration, heartbeat, scanner drift, and thermal noise. These artifacts cause deviations from common distributional assumptions, introduce spatial and temporal outliers, and reduce the signal-to-noise ratio of the data—all of which can have negative consequences for the accuracy and power of downstream statistical analysis. Scrubbing is a technique for excluding fMRI volumes thought to be contaminated by artifacts and generally comes in two flavors. Motion scrubbing based on subject head motion-derived measures is popular but suffers from a number of drawbacks, among them the need to choose a threshold, a lack of generalizability to multiband acquisitions, and high rates of censoring of individual volumes and entire subjects. Alternatively, data-driven scrubbing methods like DVARS are based on observed noise in the processed fMRI timeseries and may avoid some of these issues. Here we propose “projection scrubbing”, a novel data-driven scrubbing method based on a statistical outlier detection framework and strategic dimension reduction, including independent component analysis (ICA), to isolate artifactual variation. We undertake a comprehensive comparison of motion scrubbing with data-driven projection scrubbing and DVARS. We argue that an appropriate metric for the success of scrubbing is maximal data retention subject to reasonable performance on typical benchmarks such as the validity, reliability, and identifiability of functional connectivity. We find that stringent motion scrubbing yields worsened validity, worsened reliability, and produced small improvements to fingerprinting. Meanwhile, data-driven scrubbing methods tend to yield greater improvements to fingerprinting while not generally worsening validity or reliability. Importantly, however, data-driven scrubbing excludes a fraction of the number of volumes or entire sessions compared to motion scrubbing. The ability of data-driven fMRI scrubbing to improve data retention without negatively impacting the quality of downstream analysis has major implications for sample sizes in population neuroscience research.

Dynamic Brain Connectivity in Resting-State FMRI Using Spectral ICA and Graph Approach: Application to Healthy Controls and Multiple Sclerosis.

Multiple sclerosis (MS) is a neuroinflammatory disease that involves structural and functional damage to the brain. It changes the functional connectivity of the brain between and within networks. Resting-state functional magnetic resonance imaging (fMRI) enables us to measure functional correlation and independence between different brain regions. In recent years, statistical methods, including independent component analysis (ICA) and graph-based analysis, have been widely used in fMRI studies. Furthermore, topological properties of the brain have been appeared as significant features of neuroscience studies. Most studies are focused on graph analysis and ICA methods, rather than considering spectral approaches. Here, we developed a new framework to measure brain connectivity (in static and dynamic formats) and incorporate it to study fMRI data from MS patients and healthy controls (HCs). For this purpose, a spectral ICA method is proposed to extract the nodes of the brain graph. Spectral ICA extracts more reliable components and decreases the processing time in calculation of the static brain connectivity. Compared to Infomax ICA, dynamic range and low-frequency to high-frequency power ratio (fALFF) show better results using the proposed ICA. It is also helpful in selection of the states for dynamic connectivity. Furthermore, the dynamic connectivity-based extracted components from spectral ICA are estimated using a mutual information method and based on correlation of sliding time-windowed on selected IC time courses. First-level and second-level connectivity states are calculated using correlations of connectivity strength between graph nodes (spectral ICA components). Finally, static and dynamic connectivity are analyzed based on correlation nodes percolated by an anatomical automatic labeling (AAL) atlas. Despite static and dynamic connectivity results of AAL correlations not showing any significant changes between MS and HC, our results based on spectral ICA in static and dynamic connectivity showed significantly decreased connectivity in MS patients in the anterior cingulate cortex, whereas it was significantly weaker in the core but stronger at the periphery of the posterior cingulate cortex.

A Novel Method Based on Combination of Independent Component Analysis and Ensemble Empirical Mode Decomposition for Removing Electrooculogram Artifacts From Multichannel Electroencephalogram Signals

Electrooculogram (EOG) is one of common artifacts in recorded electroencephalogram (EEG) signals. Many existing methods including independent component analysis (ICA) and wavelet transform were applied to eliminate EOG artifacts but ignored the possible impact of the nature of EEG signal. Therefore, the removal of EOG artifacts still faces a major challenge in EEG research. In this paper, the ensemble empirical mode decomposition (EEMD) and ICA algorithms were combined to propose a novel EEMD-based ICA method (EICA) for removing EOG artifacts from multichannel EEG signals. First, the ICA method was used to decompose original EEG signals into multiple independent components (ICs), and the EOG-related ICs were automatically identified through the kurtosis method. Then, by performing the EEMD algorithm on EOG-related ICs, the intrinsic mode functions (IMFs) linked to EOG were discriminated and eliminated. Finally, artifact-free IMFs were projected to obtain the ICs without EOG artifacts, and the clean EEG signals were ultimately reconstructed by the inversion of ICA. Both EOGs correction from simulated EEG signals and real EEG data were studied, which verified that the proposed method could achieve an improved performance in EOG artifacts rejection. By comparing with other existing approaches, the EICA obtained the optimal performance with the highest increase in signal-to-noise ratio and decrease in root mean square error and correlation coefficient after EOG artifacts removal, which demonstrated that the proposed method could more effectively eliminate blink artifacts from multichannel EEG signals with less error influence. This study provided a novel promising method to eliminate EOG artifacts with high performance, which is of great importance for EEG signals processing and analysis.

Lie Group Methods in Blind Signal Processing.

This paper deals with the use of Lie group methods to solve optimization problems in blind signal processing (BSP), including Independent Component Analysis (ICA) and Independent Subspace Analysis (ISA). The paper presents the theoretical fundamentals of Lie groups and Lie algebra, the geometry of problems in BSP as well as the basic ideas of optimization techniques based on Lie groups. Optimization algorithms based on the properties of Lie groups are characterized by the fact that during optimization motion, they ensure permanent bonding with a search space. This property is extremely significant in terms of the stability and dynamics of optimization algorithms. The specific geometry of problems such as ICA and ISA along with the search space homogeneity enable the use of optimization techniques based on the properties of the Lie groups and . An interesting idea is that of optimization motion in one-parameter commutative subalgebras and toral subalgebras that ensure low computational complexity and high-speed algorithms.

Object-Based Tree Species Classification Using Airborne Hyperspectral Images and LiDAR Data

The identification of tree species is one of the most basic and key indicators in forest resource monitoring with great significance in the actual forest resource survey and it can comprehensively improve the efficiency of forest resource monitoring. The related research has mainly focused on single tree species without considering multiple tree species, and therefore the ability to classify forest tree species in complex stand is not clear, especially in the subtropical monsoon climate region of southern China. This study combined airborne hyperspectral data with simultaneously acquired LiDAR data, to evaluate the capability of feature combinations and k-nearest neighbor (KNN) and support vector machine (SVM) classifiers to identify tree species, in southern China. First, the stratified classification method was used to remove non-forest land. Second, the feature variables were extracted from airborne hyperspectral image and LiDAR data, including independent component analysis (ICA) transformation images, spectral indices, texture features, and canopy height model (CHM). Third, random forest and recursion feature elimination methods were adopted for feature selection. Finally, we selected different feature combinations and used KNN and SVM classifiers to classify tree species. The results showed that the SVM classifier has a higher classification accuracy as compared with KNN classifier, with the highest classification accuracy of 94.68% and a Kappa coefficient of 0.937. Through feature elimination, the classification accuracy and performance of SVM classifier was further improved. Recursive feature elimination method based on SVM is better than random forest. In the spectral indices, the new constructed slope spectral index, SL2, has a certain effect on improving the classification accuracy of tree species. Texture features and CHM height information can effectively distinguish tree species with similar spectral features. The height information plays an important role in improving the classification accuracy of other broad-leaved species. In general, the combination of different features can improve the classification accuracy, and the proposed strategies and methods are effective for the identification of tree species at complex forest type in southern China.

Automatic extraction and integration of behavioural indicators of malware for protection of cyber–physical networks

Abstract Conventional isolated cyber–physical systems (CPS) based industrial networks are increasingly being integrated with modern corporate information technology (IT) network. Therefore, cyber-attacks on CPS are increasing enormously and this could result in a massive damage to the machines themselves or the humans who interact with them. Malware has been one of the major source of attacks and threats to the CPS networks and computer systems. The high growth and the variety of malware variants such as Internet worms, Trojan horses and computer viruses requires periodic update of the database. Traditional malware system fulfil this requirement by manual effort from the experts though signature generation. However manual update could result into potential drawback for integrity and availability of services provided by CPS systems and protection in real-time. Machine learning technique is a natural choice to address the malware challenge for CPSs, since it can easily model and discover the underlying patterns from large-scale data sets. This paper introduces intelligent models and algorithms that can extract behavioural features and inherent attack patterns from the existing malware data, then integrates the behavioural indicators into the detection system. The main contribution of the paper is that the proposed models do not require periodic manual effort to update the database of the detection engine. We have introduced semi-supervised models using unsupervised learning including independent component analysis (ICA), global K-means clustering and multivariate exponentially weighted moving average (MEWMA) for extracting behavioural indicators which clusters the malware. Then the extracted geometric information of the clusters and hoteling T 2 of the behavioural indicators from MEWMA are incorporated into the database of existing detection system which are used with support vector machine (SVM) based supervised system. This enables the detection system to update the dynamic behavioural patterns of new malware automatically. The performances of developed semi-supervised models have been verified using malware data for both static and dynamic characteristics of malware. The summary of our experimental results demonstrate that the combination of unsupervised and supervised learning can successfully extracts behavioural indicators automatically from new malware. Performance comparison from experimental results summarize that the semi-supervised models can detect more accurately than the existing supervised models where accuracies are increased up to 100% for SVM and random forest based semi-supervised models.

Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics.

In recent years, analyzing task-based fMRI (tfMRI) data has become an essential tool for understanding brain function and networks. However, due to the sheer size of tfMRI data, its intrinsic complex structure, and lack of ground truth of underlying neural activities, modeling tfMRI data is hard and challenging. Previously proposed data modeling methods including Independent Component Analysis (ICA) and Sparse Dictionary Learning only provided shallow models based on blind source separation under the strong assumption that original fMRI signals could be linearly decomposed into time series components with corresponding spatial maps. Given the Convolutional Neural Network (CNN) successes in learning hierarchical abstractions from low-level data such as tfMRI time series, in this work we propose a novel scalable distributed deep CNN autoencoder model and apply it for fMRI big data analysis. This model aims to both learn the complex hierarchical structures of the tfMRI big data and to leverage the processing power of multiple GPUs in a distributed fashion. To deploy such a model, we have created an enhanced processing pipeline on the top of Apache Spark and Tensorflow, leveraging from a large cluster of GPU nodes over cloud. Experimental results from applying the model on the Human Connectome Project (HCP) data show that the proposed model is efficient and scalable toward tfMRI big data modeling and analytics, thus enabling data-driven extraction of hierarchical neuroscientific information from massive fMRI big data.

Remote monitoring of cardiorespiratory signals from a hovering unmanned aerial vehicle

BackgroundRemote 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.MethodsSince 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.ResultsTo 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.ConclusionThe 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).

Mobile Brain/Body Imaging (MoBI) of Physical Interaction with Dynamically Moving Objects.

The non-invasive recording and analysis of human brain activity during active movements in natural working conditions is a central challenge in Neuroergonomics research. Existing brain imaging approaches do not allow for an investigation of brain dynamics during active behavior because their sensors cannot follow the movement of the signal source. However, movements that require the operator to react fast and to adapt to a dynamically changing environment occur frequently in working environments like assembly-line work, construction trade, health care, but also outside the working environment like in team sports. Overcoming the restrictions of existing imaging methods would allow for deeper insights into neurocognitive processes at workplaces that require physical interactions and thus could help to adapt work settings to the user. To investigate the brain dynamics accompanying rapid volatile movements we used a visual oddball paradigm where participants had to react to color changes either with a simple button press or by physically pointing towards a moving target. Using a mobile brain/body imaging approach (MoBI) including independent component analysis (ICA) with subsequent backprojection of cluster activity allowed for systematically describing the contribution of brain and non-brain sources to the sensor signal. The results demonstrate that visual event-related potentials (ERPs) can be analyzed for simple button presses and physical pointing responses and that it is possible to quantify the contribution of brain processes, muscle activity and eye movements to the signal recorded at the sensor level even for fast volatile arm movements with strong jerks. Using MoBI in naturalistic working environments can thus help to analyze brain dynamics in natural working conditions and help improving unhealthy or inefficient work settings.

Feature extraction of wound infection data for electronic nose based on a novel weighted KPCA

When an electronic nose (E-nose) is used to predict the classes of wound infection, its result is not ideal if the original feature matrix extracted from the response of sensors is put into the classifier directly. To acquire more useful information which can improve E-nose's classification accuracy, we present a novel weighted kernel principal component analysis (KPCA) method to process this matrix. In addition, we have also compared it with other existing methods including independent component analysis (ICA), orthogonal signal correction (OSC), locality preserving projections (LPP), principal component analysis (PCA), KPCA and the traditional weighted KPCA. The odors of four different classes of wounds (uninfected and infected with Staphylococcus aureus, Escherichia coli, and Pseudomonas aeruginosa) are used as the original response of E-nose. Experimental results have demonstrated that the proposed weighted KPCA method outperforms other feature extraction methods.

Metabolomics coupled with pattern recognition and pathway analysis on potential biomarkers in liver injury and hepatoprotective effects of yinchenhao.

Metabolomics can provide an opportunity to develop the systematic analysis of the metabolites in biological samples and has been increasingly applied to discovering and identifying biomarkers and perturbed pathways. It enables us to better understand the metabolic pathways which can clarify the mechanism of traditional Chinese medicines (TCM). Yinchenhao (YCH, Artemisia annua L), a famous TCM plant, has been used clinically for more than a thousand years to relieve liver diseases in Asia, and its mechanisms are not still completely clear. Here, metabolomic techniques may provide additional insight, and our investigation was designed to assess the effects and possible mechanisms of YCH on α-naphthylisothiocyanate (ANIT)-induced liver injury. Metabolite profiling was performed by ultra-performance liquid chromatography/electrospray ionization quadruple time-of-flight mass spectrometry (UPLC/ESI-Q-TOF/MS) combined with pathway analysis and pattern recognition approaches including independent component analysis (ICA) and partial least squares-discriminant analysis (PLS-DA). Biochemistry test was also performed for the liver tissue and plasma samples. The changes in metabolic profiling were restored to their baseline values after YCH treatment according to the ICA score plots. Of note, YCH has a potential pharmacological effect through regulating multiple perturbed pathways to normal state, correlating well to the assessment of biochemistry test. Five different potential biomarkers in the positive mode contributing to the treatment of YCH were discovered. Pathway analysis showed that these metabolites were associated with perturbations in pyrimidine metabolism, primary bile acid biosynthesis, and propanoate metabolism, which may be helpful to further understand the action mechanisms of YCH. It showed that changed biomarkers and pathways may provide evidence to insight into drug action mechanisms and drug discovery.

Tumor segmentation from breast magnetic resonance images using independent component texture analysis

A new spectral signature analysis method for tumor segmentation in breast magnetic resonance images is presented. The proposed method is called an independent component texture analysis (ICTA), which consists of three techniques including independent component analysis (ICA), entropy-based thresholding, and texture feature registration (TFR). ICTA was mainly developed to resolve the inconsistency in the results of independent components (ICs) due to the random initial projection vector of ICA and then accordingly determine the most likely IC. A series of experiments were conducted to compare and evaluate ICTA with principal component texture analysis, traditional ICA, traditional principal component analysis (PCA), fuzzy c-means, constrained energy minimization, and orthogonal subspace projection methods. The experimental results showed that ICTA had higher efficiency than existing methods.

MEG-SIM: A Web Portal for Testing MEG Analysis Methods using Realistic Simulated and Empirical Data

MEG and EEG measure electrophysiological activity in the brain with exquisite temporal resolution. Because of this unique strength relative to noninvasive hemodynamic-based measures (fMRI, PET), the complementary nature of hemodynamic and electrophysiological techniques is becoming more widely recognized (e.g., Human Connectome Project). However, the available analysis methods for solving the inverse problem for MEG and EEG have not been compared and standardized to the extent that they have for fMRI/PET. A number of factors, including the non-uniqueness of the solution to the inverse problem for MEG/EEG, have led to multiple analysis techniques which have not been tested on consistent datasets, making direct comparisons of techniques challenging (or impossible). Since each of the methods is known to have their own set of strengths and weaknesses, it would be beneficial to quantify them. Toward this end, we are announcing the establishment of a website containing an extensive series of realistic simulated data for testing purposes ( http://cobre.mrn.org/megsim/ ). Here, we present: 1) a brief overview of the basic types of inverse procedures; 2) the rationale and description of the testbed created; and 3) cases emphasizing functional connectivity (e.g., oscillatory activity) suitable for a wide assortment of analyses including independent component analysis (ICA), Granger Causality/Directed transfer function, and single-trial analysis.