The use of permutation entropy to characterize sleep electroencephalograms

Altered sleep onset transition in depression: Evidence from EEG activity and EEG functional connectivity analyses

OBJECTIVE

Sleep disorders constitute a principal diagnostic criterion for depression, potentially reflecting the abnormal persistence of brain activity during the sleep onset (SO) transition. Here, we sought to explore the differences in the dynamic changes in the EEG activity and the EEG functional connectivity (FC) during the SO transition in depressed patients.

METHODS

Overnight polysomnography recordings were obtained from thirty-two depressed patients and thirty-three healthy controls. The multiscale permutation entropy (MSPE) and EEG relative power were extracted to characterize EEG activity, and weighted phase lag index (WPLI) was calculated to characterize EEG FC.

RESULTS

The intergroup differences in EEG activity of relative power and MSPE were reversed near SO, which attributed to slower rates of change among depressed patients. Regarding the characteristics of the EEG FC network, depressed patients exhibited significantly higher inter-hemispheric and interregional WPLI values in both delta and alpha bands throughout the SO transition, concomitant with different dynamic properties in the delta band FC. During the process after SO, patients exhibited increased inter-hemispheric long-range links, whereas controls showed more intra-hemispheric ones. Finally, we found significant correlations in the dynamic changes between different EEG measures.

CONCLUSIONS

Our research revealed that the abnormal changes during the SO transition in depressed patients were manifested in both homeostatic and dynamic aspects, which were reflected in EEG FC and EEG activity, respectively.

SIGNIFICANCE

These findings may elucidate the mechanism underlying sleep disorders in depression from the perspective of neural activity.

Neural complexity and the spectral slope characterise auditory processing in wakefulness and sleep

Auditory processing and the complexity of neural activity can both indicate residual consciousness levels and differentiate states of arousal. However, how measures of neural signal complexity manifest in neural activity following environmental stimulation and, more generally, how the electrophysiological characteristics of auditory responses change in states of reduced consciousness remain under-explored. Here, we tested the hypothesis that measures of neural complexity and the spectral slope would discriminate stages of sleep and wakefulness not only in baseline electroencephalography (EEG) activity but also in EEG signals following auditory stimulation. High-density EEG was recorded in 21 participants to determine the spatial relationship between these measures and between EEG recorded pre- and post-auditory stimulation. Results showed that the complexity and the spectral slope in the 2-20 Hz range discriminated between sleep stages and had a high correlation in sleep. In wakefulness, complexity was strongly correlated to the 20-40 Hz spectral slope. Auditory stimulation resulted in reduced complexity in sleep compared to the pre-stimulation EEG activity and modulated the spectral slope in wakefulness. These findings confirm our hypothesis that electrophysiological markers of arousal are sensitive to sleep/wake states in EEG activity during baseline and following auditory stimulation. Our results have direct applications to studies using auditory stimulation to probe neural functions in states of reduced consciousness.

Sleep disrupts complex spiking dynamics in the neocortex and hippocampus

Neuronal interactions give rise to complex dynamics in cortical networks, often described in terms of the diversity of activity patterns observed in a neural signal. Interestingly, the complexity of spontaneous electroencephalographic signals decreases during slow-wave sleep (SWS); however, the underlying neural mechanisms remain elusive. Here, we analyse in-vivo recordings from neocortical and hippocampal neuronal populations in rats and show that the complexity decrease is due to the emergence of synchronous neuronal DOWN states. Namely, we find that DOWN states during SWS force the population activity to be more recurrent, deterministic, and less random than during REM sleep or wakefulness, which, in turn, leads to less complex field recordings. Importantly, when we exclude DOWN states from the analysis, the recordings during wakefulness and sleep become indistinguishable: the spiking activity in all the states collapses to a common scaling. We complement these results by implementing a critical branching model of the cortex, which shows that inducing DOWN states to only a percentage of neurons is enough to generate a decrease in complexity that replicates SWS.

Rao-Burbea centroids applied to the statistical characterization of time series and images through ordinal patterns

Divergences or similarity measures between probability distributions have become a very useful tool for studying different aspects of statistical objects, such as time series, networks, and images. Notably, not every divergence provides identical results when applied to the same problem. Therefore, it seems convenient to have the widest possible set of divergences to be applied to the problems under study. Besides this choice, an essential step in the analysis of every statistical object is the mapping of each one of their representing values into an alphabet of symbols conveniently chosen. In this work, we choose the family of divergences known as the Burbea-Rao centroids (BRCs). For the mapping of the original time series into a symbolic sequence, we work with the ordinal pattern scheme. We apply our proposals to analyze simulated and real time series and to real textured images. The main conclusion of our work is that the best BRC, at least in the studied cases, is the Jensen-Shannon divergence, besides the fact that it verifies some interesting formal properties.

Ordinal methods for a characterization of evolving functional brain networks

Ordinal time series analysis is based on the idea to map time series to ordinal patterns, i.e., order relations between the values of a time series and not the values themselves, as introduced in 2002 by C. Bandt and B. Pompe. Despite a resulting loss of information, this approach captures meaningful information about the temporal structure of the underlying system dynamics as well as about properties of interactions between coupled systems. This-together with its conceptual simplicity and robustness against measurement noise-makes ordinal time series analysis well suited to improve characterization of the still poorly understood spatiotemporal dynamics of the human brain. This minireview briefly summarizes the state-of-the-art of uni- and bivariate ordinal time-series-analysis techniques together with applications in the neurosciences. It will highlight current limitations to stimulate further developments, which would be necessary to advance characterization of evolving functional brain networks.

Multiscale two-dimensional permutation entropy to analyze encrypted images

Multiscale versions of weighted (and non-weighted) permutation entropy for two dimensions are considered in order to compare and analyze the results when different experiments are conducted. We propose the application of these measures to analyze encrypted images with different security levels and encryption methods.

Cross-Scale Dynamicity of Entropy and Connectivity in the Sleeping Brain

Introduction: The concept of local sleep refers to the phenomenon of local brain activity that modifies neural networks during unresponsive global sleep. Such network rewiring may differ across spatial scales; however, the global and local alterations in brain systems remain elusive in human sleep. Materials and Methods: We examined cross-scale changes of brain networks in sleep. Functional magnetic resonance imaging data were acquired from 28 healthy participants during nocturnal sleep. We adopted both metrics of connectivity (functional connectivity [FC] and regional homogeneity [ReHo]) and complexity (multiscale entropy) to explore the global and local functionality of the neural assembly across nonrapid eye movement sleep stages. Results: Long-range FC decreased with sleep depth, whereas local ReHo peaked at the N2 stage and reached its lowest level at the N3 stage. Entropy exhibited a general decline at the local scale (Scale 1) as sleep deepened, whereas the coarse-scale entropy (Scale 3) was consistent across stages. Discussion: The negative correlation between Scale-1 entropy and ReHo reflects the enhanced signal regularity and synchronization in sleep, identifying the information exchange at the local scale. The N2 stage showed a distinctive pattern toward local information processing with scrambled long-distance information exchange, indicating a specific time window for network reorganization. Collectively, the multidimensional metrics indicated an imbalanced global-local relationship among brain functional networks across sleep-wake stages.

Are we really unconscious in "unconscious" states? Common assumptions revisited

In the field of consciousness science, there is a tradition to categorize certain states such as slow-wave non-REM sleep and deep general anesthesia as "unconscious". While this categorization seems reasonable at first glance, careful investigations have revealed that it is not so simple. Given that (1) behavioral signs of (un-)consciousness can be unreliable, (2) subjective reports of (un-)consciousness can be unreliable, and, (3) states presumed to be unconscious are not always devoid of reported experience, there are reasons to reexamine our traditional assumptions about "states of unconsciousness". While these issues are not novel, and may be partly semantic, they have implications both for scientific progress and clinical practice. We suggest that focusing on approaches that provide a more pragmatic and nuanced characterization of different experimental conditions may promote clarity in the field going forward, and help us build stronger foundations for future studies.

Complexity of Brain Dynamics as a Correlate of Consciousness in Anaesthetized Monkeys

The use of anaesthesia is a fundamental tool in the investigation of consciousness. Anesthesia procedures allow to investigate different states of consciousness from sedation to deep anesthesia within controlled scenarios. In this study we use information quantifiers to measure the complexity of electrocorticogram recordings in monkeys. We apply these metrics to compare different stages of general anesthesia for evaluating consciousness in several anesthesia protocols. We find that the complexity of brain activity can be used as a correlate of consciousness. For two of the anaesthetics used, propofol and medetomidine, we find that the anaesthetised state is accompanied by a reduction in the complexity of brain activity. On the other hand we observe that use of ketamine produces an increase in complexity measurements. We relate this observation with increase activity within certain brain regions associated with the ketamine used doses. Our measurements indicate that complexity of brain activity is a good indicator for a general evaluation of different levels of consciousness awareness, both in anesthetized and non anesthetizes states.

Beyond randomness: Evaluating measures of information entropy in binary series

The enormous amount of currently available data demands efforts to extract meaningful information. For this purpose, different measurements are applied, including Shannon's entropy, permutation entropy, and the Lempel-Ziv complexity. These methods have been used in many applications, such as pattern recognition, series classification, and several other areas (e.g., physical, financial, and biomedical). Data in these applications are often presented in binary series with temporal correlations. Herein, we compare the measures of information entropy in binary series conveying short- and long-range temporal correlations characterized by the Hurst exponent H. Combining numerical and analytical approaches, we scrutinize different methods that were not efficient in detecting temporal correlations. To surpass this limitation, we propose a measure called the binary permutation index (BPI). We will demonstrate that BPI efficiently discriminates patterns embedded in the series, offering advantages over previous methods. Subsequently, we collect stock market time series and rain precipitation data as well as perform in vivo electrophysiological recordings in the hippocampus of an experimental animal model of temporal lobe epilepsy, in which the BPI application in both public open source and experimental data is demonstrated. An index is proposed to evaluate information entropy, allowing the ability to discriminate randomness and extract meaningful information in binary time series.

Short-Term Impact of Sleep Apnea/Hypopnea on the Interaction Between Various Cortical Areas

INTRODUCTION

Sleep apnea/hypopnea syndrome (SAHS) can change brain structure and function. These alterations are related to respiratory event-induced abnormal sleep, however, how brain activity changes during these events is less well understood.

METHODS

To study information content and interaction among various cortical regions, we analyzed the variations of permutation entropy (PeEn) and symbolic transfer entropy (STE) of electroencephalography (EEG) activity during respiratory events. In this study, 57 patients with moderate SAHS were enrolled, including 2804 respiratory events. The events terminated with cortical arousal were independently researched.

RESULTS

PeEn and STE were lower during apnea/hypopnea, and most of the brain interaction was higher after apnea/hypopnea termination than that before apnea in N2 stage. As indicated by STE, the respiratory events also affected the stability of information transmission mode. In N1, N2, and rapid eye movement (REM) stages, the information flow direction was posterior-to-anterior, but the anterior-to-posterior increased relatively during apnea/hypopnea. The above EEG activity trends maintained in events with cortical arousal.

CONCLUSIONS

These results may be related to the intermittent hypoxia during apnea and the cortical response. Furthermore, increased frontal information outflow, which was related to the compensatory activation of frontal neurons, may associate with cognitive function.

Changes in EEG permutation entropy in the evening and in the transition from wake to sleep

Quantifying the complexity of the EEG signal during prolonged wakefulness and during sleep is gaining interest as an additional mean to characterize the mechanisms associated with sleep and wakefulness regulation. Here, we characterized how EEG complexity, as indexed by Multiscale Permutation Entropy (MSPE), changed progressively in the evening prior to light off and during the transition from wakefulness to sleep. We further explored whether MSPE was able to discriminate between wakefulness and sleep around sleep onset and whether MSPE changes were correlated with spectral measures of the EEG related to sleep need during concomitant wakefulness (theta power-Ptheta: 4-8 Hz). To address these questions, we took advantage of large datasets of several hundred of ambulatory EEG recordings of individual of both sexes aged 25-101 years. Results show that MSPE significantly decreases before light off (i.e. before sleep time) and in the transition from wakefulness to sleep onset. Furthermore, MSPE allows for an excellent discrimination between pre-sleep wakefulness and early sleep. Finally, we show that MSPE is correlated with concomitant Ptheta. Yet, the direction of the latter correlation changed from before light-off to the transition to sleep. Given the association between EEG complexity and consciousness, MSPE may track efficiently putative changes in consciousness preceding sleep onset. An MSPE stands as a comprehensive measure that is not limited to a given frequency band and reflects a progressive change brain state associated with sleep and wakefulness regulation. It may be an effective mean to detect when the brain is in a state close to sleep onset.

An Improved Composite Multiscale Fuzzy Entropy for Feature Extraction of MI-EEG

Motor Imagery Electroencephalography (MI-EEG) has shown good prospects in neurorehabilitation, and the entropy-based nonlinear dynamic methods have been successfully applied to feature extraction of MI-EEG. Especially based on Multiscale Fuzzy Entropy (MFE), the fuzzy entropies of the τ coarse-grained sequences in τ scale are calculated and averaged to develop the Composite MFE (CMFE) with more feature information. However, the coarse-grained process fails to match the nonstationary characteristic of MI-EEG by a mean filtering algorithm. In this paper, CMFE is improved by assigning the different weight factors to the different sample points in the coarse-grained process, i.e., using the weighted mean filters instead of the original mean filters, which is conductive to signal filtering and feature extraction, and the resulting personalized Weighted CMFE (WCMFE) is more suitable to represent the nonstationary MI-EEG for different subjects. All the WCMFEs of multi-channel MI-EEG are fused in serial to construct the feature vector, which is evaluated by a back-propagation neural network. Based on a public dataset, extensive experiments are conducted, yielding a relatively higher classification accuracy by WCMFE, and the statistical significance is examined by two-sample t-test. The results suggest that WCMFE is superior to the other entropy-based and traditional feature extraction methods.

Constructing a Consciousness Meter Based on the Combination of Non-Linear Measurements and Genetic Algorithm-Based Support Vector Machine

OBJECTIVE

Constructing a framework to evaluate consciousness is an important issue in neuroscience research and clinical practice. However, there is still no systematic framework for quantifying altered consciousness along the dimensions of both level and content. This study builds a framework to differentiate the following states: coma, general anesthesia, minimally conscious state (MCS), and normal wakefulness.

METHODS

This study analyzed electroencephalography (EEG) recorded from frontal channels in patients with disorders of consciousness (either coma or MCS), patients under general anesthesia, and healthy participants in normal waking consciousness (NWC). Four non-linear methods-permutation entropy (PE), sample entropy (SampEn), permutation Lempel-Ziv complexity (PLZC), and detrended fluctuation analysis (DFA)-as well as relative power (RP), extracted features from the EEG recordings. A genetic algorithm-based support vector machine (GA-SVM) classified the states of consciousness based on the extracted features. A multivariable linear regression model then built EEG indices for level and content of consciousness.

RESULTS

The PE differentiated all four states of consciousness (p<0.001). Altered contents of consciousness for NWC, MCS, coma, and general anesthesia were best differentiated by the SampEn, and PLZC. In contrast, the levels of consciousness for these four states were best differentiated by RP of Gamma and PE. A multi-dimensional index, combined with the GA-SVM, showed that the integration of PE, PLZC, SampEn, and DFA had the highest classification accuracy (92.3%). The GA-SVM was better than random forest and neural networks at differentiating these four states. The 'coordinate value' in the dimensions of level and content were constructed by the multivariable linear regression model and the non-linear measures PE, PLZC, SampEn, and DFA.

CONCLUSIONS

Multi-dimensional measurements, especially the PE, SampEn, PLZC, and DFA, when combined with GA-SVM, are promising methods for constructing a framework to quantify consciousness.

Decreased electrocortical temporal complexity distinguishes sleep from wakefulness

In most mammals, the sleep-wake cycle is constituted by three behavioral states: wakefulness (W), non-REM (NREM) sleep, and REM sleep. These states are associated with drastic changes in cognitive capacities, mostly determined by the function of the thalamo-cortical system. The intra-cranial electroencephalogram or electocorticogram (ECoG), is an important tool for measuring the changes in the thalamo-cortical activity during W and sleep. In the present study we analyzed broad-band ECoG recordings of the rat by means of a time-series complexity measure that is easy to implement and robust to noise: the Permutation Entropy (PeEn). We found that PeEn is maximal during W and decreases during sleep. These results bring to light the different thalamo-cortical dynamics emerging during sleep-wake states, which are associated with the well-known spectral changes that occur when passing from W to sleep. Moreover, the PeEn analysis allows us to determine behavioral states independently of the electrodes' cortical location, which points to an underlying global pattern in the signal that differs among the cycle states that is missed by classical methods. Consequently, our data suggest that PeEn analysis of a single EEG channel could allow for cheap, easy, and efficient sleep monitoring.

On the development of sleep states in the first weeks of life

Human newborns spend up to 18 hours sleeping. The organization of their sleep differs immensely from adult sleep, and its quick maturation and fundamental changes correspond to the rapid cortical development at this age. Manual sleep classification is specifically challenging in this population given major body movements and frequent shifts between vigilance states; in addition various staging criteria co-exist. In the present study we utilized a machine learning approach and investigated how EEG complexity and sleep stages evolve during the very first weeks of life. We analyzed 42 full-term infants which were recorded twice (at week two and five after birth) with full polysomnography. For sleep classification EEG signal complexity was estimated using multi-scale permutation entropy and fed into a machine learning classifier. Interestingly the baby’s brain signal complexity (and spectral power) revealed developmental changes in sleep in the first 5 weeks of life, and were restricted to NREM (“quiet”) and REM (“active sleep”) states with little to no changes in state wake. Data demonstrate that our classifier performs well over chance (i.e., >33% for 3-class classification) and reaches almost human scoring accuracy (60% at week-2, 73% at week-5). Altogether, these results demonstrate that characteristics of newborn sleep develop rapidly in the first weeks of life and can be efficiently identified by means of machine learning techniques.

A Comparative Study of Multiscale Sample Entropy and Hierarchical Entropy and Its Application in Feature Extraction for Ship-Radiated Noise

The presence of marine ambient noise makes it difficult to extract effective features from ship-radiated noise. Traditional feature extraction methods based on the Fourier transform or wavelets are limited in such a complex ocean environment. Recently, entropy-based methods have been proven to have many advantages compared with traditional methods. In this paper, we propose a novel feature extraction method for ship-radiated noise based on hierarchical entropy (HE). Compared with the traditional entropy, namely multiscale sample entropy (MSE), which only considers information carried in the lower frequency components, HE takes into account both lower and higher frequency components of signals. We illustrate the different properties of HE and MSE by testing them on simulation signals. The results show that HE has better performance than MSE, especially when the difference in signals is mainly focused on higher frequency components. Furthermore, experiments on real-world data of five types of ship-radiated noise are conducted. A probabilistic neural network is employed to evaluate the performance of the obtained features. Results show that HE has a higher classification accuracy for the five types of ship-radiated noise compared with MSE. This indicates that the HE-based feature extraction method could be used to identify ships in the field of underwater acoustic signal processing.

Quantifying interdependence using the missing joint ordinal patterns

In this paper, we develop the concept of forbidden/missing ordinal patterns into the forbidden/missing joint ordinal patterns and propose the ratio of the number of missing joint ordinal patterns (RMJPs) as a sign of interdependence. RMJP in a surrogate analysis can be used to differentiate the forbidden joint ordinal patterns from the missing joint ordinal patterns due to small sample effects. We first apply RMJP to the simulated time series: a two-component autoregressive fractionally integrated moving average process, the Hénon map, and the Rössler system using active control and discuss the effect of the length of the time series, embedding dimension, and noise contamination. RMJP has been proven to be capable of measuring the interdependence in the numerical simulation. Then, RMJP is further used on the electroencephalogram (EEG) time series for empirical analysis to explore the interdependence of brain waves. With results by RMJP obtained from a widely used open dataset of the sleep EEG time series from healthy subjects, we find that RMJP can be used to quantify the brain wave interdependence under different sleep/wake stages, reveal the overall sleep architecture, and indicate a higher level of interdependence as sleep gets deeper. The findings are consistent with existing knowledge in sleep medicine. The proposed RMJP method has shown its validity and applicability and may assist automatic sleep quantification or bring insight into the understanding of the brain activity during sleep. Furthermore, RMJP can be used on sleep EEG under various pathological conditions and in large-scale sleep studies, helping to investigate the mechanisms of the sleep process and neuron synchronization.

Changes in EEG multiscale entropy and power-law frequency scaling during the human sleep cycle

We explored changes in multiscale brain signal complexity and power-law scaling exponents of electroencephalogram (EEG) frequency spectra across several distinct global states of consciousness induced in the natural physiological context of the human sleep cycle. We specifically aimed to link EEG complexity to a statistically unified representation of the neural power spectrum. Further, by utilizing surrogate-based tests of nonlinearity we also examined whether any of the sleep stage-dependent changes in entropy were separable from the linear stochastic effects contained in the power spectrum. Our results indicate that changes of brain signal entropy throughout the sleep cycle are strongly time-scale dependent. Slow wave sleep was characterized by reduced entropy at short time scales and increased entropy at long time scales. Temporal signal complexity (at short time scales) and the slope of EEG power spectra appear, to a large extent, to capture a common phenomenon of neuronal noise, putatively reflecting cortical balance between excitation and inhibition. Nonlinear dynamical properties of brain signals accounted for a smaller portion of entropy changes, especially in stage 2 sleep.

Fusion of Motif- and Spectrum-Related Features for Improved EEG-Based Emotion Recognition

Emotion recognition is a burgeoning field allowing for more natural human-machine interactions and interfaces. Electroencephalography (EEG) has shown to be a useful modality with which user emotional states can be measured and monitored, particularly primitives such as valence and arousal. In this paper, we propose the use of ordinal pattern analysis, also called motifs, for improved EEG-based emotion recognition. Motifs capture recurring structures in time series and are inherently robust to noise, thus are well suited for the task at hand. Several connectivity, asymmetry, and graph-theoretic features are proposed and extracted from the motifs to be used for affective state recognition. Experiments with a widely used public database are conducted, and results show the proposed features outperforming benchmark spectrum-based features, as well as other more recent nonmotif-based graph-theoretic features and amplitude modulation-based connectivity/asymmetry measures. Feature and score-level fusion suggest complementarity between the proposed and benchmark spectrum-based measures. When combined, the fused models can provide up to 9% improvement relative to benchmark features alone and up to 16% to nonmotif-based graph-theoretic features.

Application of Permutation Entropy and Permutation Min-Entropy in Multiple Emotional States Analysis of RRI Time Series

This study’s aim was to apply permutation entropy (PE) and permutation min-entropy (PME) over an RR interval time series to quantify the changes in cardiac activity among multiple emotional states. Electrocardiogram (ECG) signals were recorded under six emotional states (neutral, happiness, sadness, anger, fear, and disgust) in 60 healthy subjects at a rate of 1000 Hz. For each emotional state, ECGs were recorded for 5 min and the RR interval time series was extracted from these ECGs. The obtained results confirm that PE and PME increase significantly during the emotional states of happiness, sadness, anger, and disgust. Both symbolic quantifiers also increase but not in a significant way for the emotional state of fear. Moreover, it is found that PME is more sensitive than PE for discriminating non-neutral from neutral emotional states.

Measures of entropy and complexity in altered states of consciousness

Quantification of complexity in neurophysiological signals has been studied using different methods, especially those from information or dynamical system theory. These studies have revealed a dependence on different states of consciousness, and in particular that wakefulness is characterized by a greater complexity of brain signals, perhaps due to the necessity for the brain to handle varied sensorimotor information. Thus, these frameworks are very useful in attempts to quantify cognitive states. We set out to analyze different types of signals obtained from scalp electroencephalography (EEG), intracranial EEG and magnetoencephalography recording in subjects during different states of consciousness: resting wakefulness, different sleep stages and epileptic seizures. The signals were analyzed using a statistical (permutation entropy) and a deterministic (permutation Lempel-Ziv complexity) analytical method. The results are presented in complexity versus entropy graphs, showing that the values of entropy and complexity of the signals tend to be greatest when the subjects are in fully alert states, falling in states with loss of awareness or consciousness. These findings were robust for all three types of recordings. We propose that the investigation of the structure of cognition using the frameworks of complexity will reveal mechanistic aspects of brain dynamics associated not only with altered states of consciousness but also with normal and pathological conditions.

Analysis of the sleep EEG in the complexity domain

Conventional sleep analysis relies primarily on electroencephalogram (EEG) waveform features assessed in concert with eye movements, respiration and muscle tone. We explore a complementary "complexity domain" approach based on multiscale entropy (MSE) analysis of EEG signals and discuss its relationships to standard sleep analysis and to that based on electrocardiogram (ECG)-derived cardiopulmonary coupling (CPC). We observe a progressive decrease in complexity associated with decreased arousability, as measured by both conventional sleep scoring and CPC analysis. Furthermore, complexity analysis supports the contention that stage 2 non-REM sleep has distinct sub-phases that map to CPC high- and low-frequency coupled dynamics.

Enhancing the performance of motor imagery EEG classification using phase features

An electroencephalogram recognition system considering phase features is proposed to enhance the performance of motor imagery classification in this study. It mainly consists of feature extraction, feature selection and classification. Surface Laplacian filter is used for background removal. Several potential features, including phase features, are then extracted to enhance the classification accuracy. Next, genetic algorithm is used to select sub-features from feature combination. Finally, selected features are classified by extreme learning machine. Compared with "without phase features" and linear discriminant analysis on motor imagery data from 2 data sets, the results denote that the proposed system achieves enhanced performance, which is suitable for the brain-computer interface applications.

Artificial bee colony algorithm for single-trial electroencephalogram analysis

In this study, we propose an analysis system combined with feature selection to further improve the classification accuracy of single-trial electroencephalogram (EEG) data. Acquiring event-related brain potential data from the sensorimotor cortices, the system comprises artifact and background noise removal, feature extraction, feature selection, and feature classification. First, the artifacts and background noise are removed automatically by means of independent component analysis and surface Laplacian filter, respectively. Several potential features, such as band power, autoregressive model, and coherence and phase-locking value, are then extracted for subsequent classification. Next, artificial bee colony (ABC) algorithm is used to select features from the aforementioned feature combination. Finally, selected subfeatures are classified by support vector machine. Comparing with and without artifact removal and feature selection, using a genetic algorithm on single-trial EEG data for 6 subjects, the results indicate that the proposed system is promising and suitable for brain-computer interface applications.

Ordinal symbolic analysis and its application to biomedical recordings

Ordinal symbolic analysis opens an interesting and powerful perspective on time-series analysis. Here, we review this relatively new approach and highlight its relation to symbolic dynamics and representations. Our exposition reaches from the general ideas up to recent developments, with special emphasis on its applications to biomedical recordings. The latter will be illustrated with epilepsy data.

Permutation entropy analysis of vital signs data for outcome prediction of patients with severe traumatic brain injury

Permutation entropy is computationally efficient, robust to outliers, and effective to measure complexity of time series. We used this technique to quantify the complexity of continuous vital signs recorded from patients with traumatic brain injury (TBI). Using permutation entropy calculated from early vital signs (initial 10-20% of patient hospital stay time), we built classifiers to predict in-hospital mortality and mobility, measured by 3-month Extended Glasgow Outcome Score (GOSE). Sixty patients with severe TBI produced a skewed dataset that we evaluated for accuracy, sensitivity and specificity. The overall prediction accuracy achieved 91.67% for mortality, and 76.67% for 3-month GOSE in testing datasets, using the leave-one-out cross validation. We also applied Receiver Operating Characteristic analysis to compare classifiers built from different learning methods. Those results support the applicability of permutation entropy in analyzing the dynamic behavior of TBI vital signs for early prediction of mortality and long-term patient outcomes.

Improving classification accuracy of motor imagery EEG using genetic feature selection

In this study, an electroencephalogram (EEG) analysis system combined with feature selection, is proposed to enhance the classification of motor imagery (MI) data. It principally comprises feature extraction, feature selection, and classification. First, several features, including adaptive autoregressive (AAR) parameters, spectral power, asymmetry ratio, coherence and phase-locking value are extracted for subsequent classification. A genetic algorithm is then used to select features from the combination of the aforementioned features. Finally, the selected features are classified by support vector machine (SVM). Compared with "without feature selection" and back-propagation neural network (BPNN) on MI data from 2 data sets, the proposed system achieves better classification accuracy and is suitable for the applications of brain-computer interface (BCI).

Embedded grey relation theory in Hopfield neural network: application to motor imagery EEG recognition

In this study, grey-based Hopfield neural network (GHNN), is proposed for the unsupervised analysis of motor imagery (MI) electroencephalogram (EEG) data. Combined with segment selection and feature extraction, GHNN is used for the recognition of left and right MI data. A Gaussian-like filter is proposed to reduce noise, to further enhance performance of active segment selection. Features are extracted by coherence from wavelet data, and then discriminated by GHNN, which is an unsupervised approach suitable for the online classification of nonstationary biomedical signals. Compared to EEG data without segment selection, several usual features, and classifiers, the proposed system is potentially an analytic approach in brain-computer interface (BCI) applications.

Independent component analysis and multiresolution asymmetry ratio for brain-computer interface

This study proposes a brain-computer interface (BCI) system for the recognition of single-trial electroencephalogram (EEG) data. With the combination of independent component analysis (ICA) and multiresolution asymmetry ratio, a support vector machine (SVM) is used to classify left and right finger lifting or motor imagery. First, ICA and similarity measures are proposed to eliminate the electrooculography (EOG) artifacts automatically. The features are then extracted from the wavelet data by means of an asymmetry ratio. Finally, the SVM classifier is used to discriminate between the features. Compared to the EEG data without EOG artifact removal, band power, and adoptive autoregressive (AAR) parameter features, the proposed system achieves promising results in BCI applications.

Embedded prediction in feature extraction: application to single-trial EEG discrimination

In this study, an analysis system embedding neuron-fuzzy prediction in feature extraction is proposed for brain-computer interface (BCI) applications. Wavelet-fractal features combined with neuro-fuzzy predictions are applied for feature extraction in motor imagery (MI) discrimination. The features are extracted from the electroencephalography (EEG) signals recorded from participants performing left and right MI. Time-series predictions are performed by training 2 adaptive neuro-fuzzy inference systems (ANFIS) for respective left and right MI data. Features are then calculated from the difference in multi-resolution fractal feature vector (MFFV) between the predicted and actual signals through a window of EEG signals. Finally, the support vector machine is used for classification. The proposed method estimates its performance in comparison with the linear adaptive autoregressive (AAR) model and the AAR time-series prediction of 6 participants from 2 data sets. The results indicate that the proposed method is promising in MI classification.

Dynamic characteristics of absence EEG recordings with multiscale permutation entropy analysis

Understanding the transition of brain activities towards an absence seizure, called pre-epileptic seizure, is a challenge. In this study, multiscale permutation entropy (MPE) is proposed to describe dynamical characteristics of electroencephalograph (EEG) recordings on different absence seizure states. The classification ability of the MPE measures using linear discriminant analysis is evaluated by a series of experiments. Compared to a traditional multiscale entropy method with 86.1% as its classification accuracy, the classification rate of MPE is 90.6%. Experimental results demonstrate there is a reduction of permutation entropy of EEG from the seizure-free state to the seizure state. Moreover, it is indicated that the dynamical characteristics of EEG data with MPE can identify the differences among seizure-free, pre-seizure and seizure states. This also supports the view that EEG has a detectable change prior to an absence seizure.

ANALYSIS OF ABSENCE SEIZURE GENERATION USING EEG SPATIAL-TEMPORAL REGULARITY MEASURES

Epileptic seizures are thought to be generated and to evolve through an underlying anomaly of synchronization in the activity of groups of neuronal populations. The related dynamic scenario of state transitions is revealed by detecting changes in the dynamical properties of Electroencephalography (EEG) signals. The recruitment procedure ending with the crisis can be explored through a spatial-temporal plot from which to extract suitable descriptors that are able to monitor and quantify the evolving synchronization level from the EEG tracings. In this paper, a spatial-temporal analysis of EEG recordings based on the concept of permutation entropy (PE) is proposed. The performance of PE are tested on a database of 24 patients affected by absence (generalized) seizures. The results achieved are compared to the dynamical behavior of the EEG of 40 healthy subjects. Being PE a feature which is dependent on two parameters, an extensive study of the sensitivity of the performance of PE with respect to the parameters' setting was carried out on scalp EEG. Once the optimal PE configuration was determined, its ability to detect the different brain states was evaluated. According to the results here presented, it seems that the widely accepted model of "jump" transition to absence seizure should be in some cases coupled (or substituted) by a gradual transition model characteristic of self-organizing networks. Indeed, it appears that the transition to the epileptic status is heralded before the preictal state, ever since the interictal stages. As a matter of fact, within the limits of the analyzed database, the frontal-temporal scalp areas appear constantly associated to PE levels higher compared to the remaining electrodes, whereas the parieto-occipital areas appear associated to lower PE values. The EEG of healthy subjects neither shows any similar dynamic behavior nor exhibits any recurrent portrait in PE topography.

Complexity-entropy causality plane as a complexity measure for two-dimensional patterns

Complexity measures are essential to understand complex systems and there are numerous definitions to analyze one-dimensional data. However, extensions of these approaches to two or higher-dimensional data, such as images, are much less common. Here, we reduce this gap by applying the ideas of the permutation entropy combined with a relative entropic index. We build up a numerical procedure that can be easily implemented to evaluate the complexity of two or higher-dimensional patterns. We work out this method in different scenarios where numerical experiments and empirical data were taken into account. Specifically, we have applied the method to fractal landscapes generated numerically where we compare our measures with the Hurst exponent; liquid crystal textures where nematic-isotropic-nematic phase transitions were properly identified; 12 characteristic textures of liquid crystals where the different values show that the method can distinguish different phases; and Ising surfaces where our method identified the critical temperature and also proved to be stable.

Efficient feature selection for sleep staging based on maximal overlap discrete wavelet transform and SVM

In this paper, a novel algorithm is proposed with application in sleep/awake detection and in multiclass sleep stage classification (awake, non rapid eye movement (NREM) sleep and REM sleep). In turn, NREM is further divided into three stages denoted here by S1, S2, and S3. Six electroencephalographic (EEG) and two electro-oculographic (EOG) channels were used in this study. The maximum overlap discrete wavelet transform (MODWT) with the multi-resolution Analysis is applied to extract relevant features from EEG and EOG signals. The extracted feature set is transformed and normalized to reduce the effect of extreme values of features. A set of significant features are selected by mRMR which is a powerful feature selection method. Finally the selected feature set is classified using support vector machines (SVMs). The system achieved 95.0% of average accuracy for sleep/awake detection. As concerns the multiclass case, the average accuracy of sleep stages classification was 93.0%.

Enhanced active segment selection for single-trial EEG classification

In this study, an electroencephalogram (EEG) analysis system is proposed for single-trial classification of both motor imagery (MI) and finger-lifting EEG data. Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system mainly consists of three procedures; enhanced active segment selection, feature extraction, and classification. In addition to the original use of continuous wavelet transform (CWT) and Student 2-sample t statistics, the two-dimensional (2D) anisotropic Gaussian filter further refines the selection of active segments. The multiresolution fractal features are then extracted from wavelet data by using proposed modified fractal dimension. Finally, the support vector machine (SVM) is used for classification. Compared to original active segment selection, with several popular features and classifier on both the MI and finger-lifting data from 2 data sets, the results indicate that the proposed method is promising in EEG classification.

Application of multiscale amplitude modulation features and fuzzy C-means to brain-computer interface

This study proposed a recognized system for electroencephalogram (EEG) data classification. In addition to the wavelet-based amplitude modulation (AM) features, the fuzzy c-means (FCM) clustering is used for the discriminant of left finger lifting and resting. The features are extracted from discrete wavelet transform (DWT) data with the AM method. The FCM is then applied to recognize extracted features. Compared with band power features, k-means clustering, and linear discriminant analysis (LDA) classifier, the results indicate that the proposed method is satisfactory in applications of brain-computer interface (BCI).