Classification of multichannel EEG patterns using parallel hidden Markov models

Similar neural states, but dissimilar decoding patterns for motor control in parietal cortex

Discrete neural states are associated with reaching movements across the fronto-parietal network. Here, the Hidden Markov Model (HMM) applied to spiking activity of the somato-motor parietal area PE revealed a sequence of states similar to those of the contiguous visuomotor areas PEc and V6A. Using a coupled clustering and decoding approach, we proved that these neural states carried spatiotemporal information regarding behaviour in all three posterior parietal areas. However, comparing decoding accuracy, PE was less informative than V6A and PEc. In addition, V6A outperformed PEc in target inference, indicating functional differences among the parietal areas. To check the consistency of these differences, we used both a supervised and an unsupervised variant of the HMM, and compared its performance with two more common classifiers, Support Vector Machine and Long-Short Term Memory. The differences in decoding between areas were invariant to the algorithm used, still showing the dissimilarities found with HMM, thus indicating that these dissimilarities are intrinsic in the information encoded by parietal neurons. These results highlight that, when decoding from the parietal cortex, for example, in brain machine interface implementations, attention should be paid in selecting the most suitable source of neural signals, given the great heterogeneity of this cortical sector.

Dynamics of hidden brain states when people solve verbal puzzles

When people try to solve a problem, they go through distinct steps (encoding, ideation, evaluation, etc.) recurrently and spontaneously. To disentangle different cognitive processes that unfold throughout a trial, we applied an unsupervised machine learning method to electroencephalogram (EEG) data continuously recorded while 39 participants attempted 153 Compound Remote Associates problems (CRA). CRA problems are verbal puzzles that can be solved in either insight-leaning or analysis-leaning manner. We fitted a Hidden Markov Model to the time-frequency transformed EEG signals and decoded each trial as a time-resolved state sequence. The model characterizes hidden brain states with spectrally resolved power topography. Seven states were identified with distinct activation patterns in the theta (4-7 Hz), alpha (8-9 Hz and 10-13 Hz), and gamma (25-50 Hz) bands. Notably, a state featuring widespread activation only in alpha-band frequency emerged, from this data-driven approach, which exhibited dynamic characteristics associated with specific temporal stages and outcomes (whether solved with insight or analysis) of the trials. The state dynamics derived from the model overlap and extend previous literature on the cognitive function of alpha oscillation: the "alpha-state" probability peaks before stimulus onset and decreases before response. In trials solved with insight, relative to solved with analysis, the alpha-state is more likely to be visited and maintained during preparation and solving periods, and its probability declines more sharply immediately preceding a response. This novel paradigm provides a way to extract dynamic features that characterize problem-solving stages and potentially provide a novel window into the nature of the underlying cognitive processes.

Brain-Computer Interface: Advancement and Challenges

Brain-Computer Interface (BCI) is an advanced and multidisciplinary active research domain based on neuroscience, signal processing, biomedical sensors, hardware, etc. Since the last decades, several groundbreaking research has been conducted in this domain. Still, no comprehensive review that covers the BCI domain completely has been conducted yet. Hence, a comprehensive overview of the BCI domain is presented in this study. This study covers several applications of BCI and upholds the significance of this domain. Then, each element of BCI systems, including techniques, datasets, feature extraction methods, evaluation measurement matrices, existing BCI algorithms, and classifiers, are explained concisely. In addition, a brief overview of the technologies or hardware, mostly sensors used in BCI, is appended. Finally, the paper investigates several unsolved challenges of the BCI and explains them with possible solutions.

A hidden Markov model reliably characterizes ketamine-induced spectral dynamics in macaque local field potentials and human electroencephalograms

Ketamine is an NMDA receptor antagonist commonly used to maintain general anesthesia. At anesthetic doses, ketamine causes high power gamma (25-50 Hz) oscillations alternating with slow-delta (0.1-4 Hz) oscillations. These dynamics are readily observed in local field potentials (LFPs) of non-human primates (NHPs) and electroencephalogram (EEG) recordings from human subjects. However, a detailed statistical analysis of these dynamics has not been reported. We characterize ketamine's neural dynamics using a hidden Markov model (HMM). The HMM observations are sequences of spectral power in seven canonical frequency bands between 0 to 50 Hz, where power is averaged within each band and scaled between 0 and 1. We model the observations as realizations of multivariate beta probability distributions that depend on a discrete-valued latent state process whose state transitions obey Markov dynamics. Using an expectation-maximization algorithm, we fit this beta-HMM to LFP recordings from 2 NHPs, and separately, to EEG recordings from 9 human subjects who received anesthetic doses of ketamine. Our beta-HMM framework provides a useful tool for experimental data analysis. Together, the estimated beta-HMM parameters and optimal state trajectory revealed an alternating pattern of states characterized primarily by gamma and slow-delta activities. The mean duration of the gamma activity was 2.2s([1.7,2.8]s) and 1.2s([0.9,1.5]s) for the two NHPs, and 2.5s([1.7,3.6]s) for the human subjects. The mean duration of the slow-delta activity was 1.6s([1.2,2.0]s) and 1.0s([0.8,1.2]s) for the two NHPs, and 1.8s([1.3,2.4]s) for the human subjects. Our characterizations of the alternating gamma slow-delta activities revealed five sub-states that show regular sequential transitions. These quantitative insights can inform the development of rhythm-generating neuronal circuit models that give mechanistic insights into this phenomenon and how ketamine produces altered states of arousal.

Estimating the Memory Order of Electrocorticography Recordings

OBJECTIVE

This paper presents a data-driven method for estimating the memory order (the average length of the statistical dependence of a given sample on previous samples) of a recorded electrocorticography (ECoG) sequence.

METHODS

The proposed inference method is based on the relationship between the loss in predicting the next sample in a time-series and the dependence of this sample on the previous samples. Specifically, the memory order is estimated to be the number of past samples that minimize the least squares error (LSE) in predicting the next sample. To deal with the lack of an analytical model for ECoG recordings, the proposed method combines a collection of different predictors, thereby achieving LSE at least as low as the LSE achieved by each of the different predictors.

RESULTS

ECoG recordings from six patients with epilepsy were analyzed, and the empirical cumulative density functions (ECDFs) of the memory orders estimated from these recordings were generated, for rest as well as pre-ictal time intervals. For pre-ictal time intervals, the electrodes corresponding to the seizure-onset-zone were separately analyzed. The estimated ECDFs were different between patients and between different types of blocks. For all the analyzed patients, the estimated memory orders were on the order of tens of milliseconds (up to 100 ms).

SIGNIFICANCE

The proposed method facilitates the estimation of the causal associations between ECoG recordings, as these associations strongly depend on the recordings' memory. An improved estimation of causal associations can improve the performance of algorithms that use ECoG recordings to localize the epileptogenic zone. Such algorithms can aid doctors in their pre-surgical planning for the surgery of patients with epilepsy.

A Quasi-probabilistic distribution model for EEG Signal classification by using 2-D signal representation

BACKGROUND AND OBJECTIVE

Electroencephalography (EEG) is a method that measures and records the electrical activity of the human brain. These biomedical signals are currently being actively used in many research fields and have a wide range of potential uses in brain-computer interfaces (BCIs). The main aim of the present work is to improve the classification of EEG patterns for EEG-based BCI systems.

METHODS

In this paper, we presented a classification approach for EEG-based BCIs. For this purpose, in the training stage, 2-D representations of signals were extracted and a quasi-probabilistic learning model was built for binary classification. In the testing stage, the estimation of class membership probability was performed with an untrained sub-data set. To confirm the validity of the proposed method, we conducted experiments on the BCI Competition 2003 Data Sets (Ia and Ib). The classification performances were evaluated for accuracy, sensitivity, specificity and F-measure measurements using the five-fold leave-one-out cross-validation technique ten times.

RESULTS

The proposed method yielded an average classification accuracy of 95.54% (with sensitivity and specificity of 100.00% and 91.80% respectively) for Data Set Ia and accuracy of 72.37% (with sensitivity and specificity of 75.76% and 69.77% respectively) for Data Set Ib, which are the highest rates ever reported for both data sets.

CONCLUSIONS

It is apparent from the results that the proposed method has potential and can assist in the development of effective EEG-based BCIs. The advantage of this method lies in its relatively simple algorithm and easy computational implementation. The experimental results also showed that the selection of relevant channels is an important step in developing efficient EEG-based BCI systems.

Extracting duration information in a picture category decoding task using hidden Markov Models

OBJECTIVE

Adapting classifiers for the purpose of brain signal decoding is a major challenge in brain-computer-interface (BCI) research. In a previous study we showed in principle that hidden Markov models (HMM) are a suitable alternative to the well-studied static classifiers. However, since we investigated a rather straightforward task, advantages from modeling of the signal could not be assessed.

APPROACH

Here, we investigate a more complex data set in order to find out to what extent HMMs, as a dynamic classifier, can provide useful additional information. We show for a visual decoding problem that besides category information, HMMs can simultaneously decode picture duration without an additional training required. This decoding is based on a strong correlation that we found between picture duration and the behavior of the Viterbi paths.

MAIN RESULTS

Decoding accuracies of up to 80% could be obtained for category and duration decoding with a single classifier trained on category information only.

SIGNIFICANCE

The extraction of multiple types of information using a single classifier enables the processing of more complex problems, while preserving good training results even on small databases. Therefore, it provides a convenient framework for online real-life BCI utilizations.

Epoch-based Entropy for Early Screening of Alzheimer’s Disease

In this paper, we introduce a novel entropy measure, termed epoch-based entropy. This measure quantifies disorder of EEG signals both at the time level and spatial level, using local density estimation by a Hidden Markov Model on inter-channel stationary epochs. The investigation is led on a multi-centric EEG database recorded from patients at an early stage of Alzheimer’s disease (AD) and age-matched healthy subjects. We investigate the classification performances of this method, its robustness to noise, and its sensitivity to sampling frequency and to variations of hyperparameters. The measure is compared to two alternative complexity measures, Shannon’s entropy and correlation dimension. The classification accuracies for the discrimination of AD patients from healthy subjects were estimated using a linear classifier designed on a development dataset, and subsequently tested on an independent test set. Epoch-based entropy reached a classification accuracy of 83% on the test dataset (specificity = 83.3%, sensitivity = 82.3%), outperforming the two other complexity measures. Furthermore, it was shown to be more stable to hyperparameter variations, and less sensitive to noise and sampling frequency disturbances than the other two complexity measures.

Chow-Liu trees are sufficient predictive models for reproducing key features of functional networks of periictal EEG time-series

Seizure freedom in patients suffering from pharmacoresistant epilepsies is still not achieved in 20-30% of all cases. Hence, current therapies need to be improved, based on a more complete understanding of ictogenesis. In this respect, the analysis of functional networks derived from intracranial electroencephalographic (iEEG) data has recently become a standard tool. Functional networks however are purely descriptive models and thus are conceptually unable to predict fundamental features of iEEG time-series, e.g., in the context of therapeutical brain stimulation. In this paper we present some first steps towards overcoming the limitations of functional network analysis, by showing that its results are implied by a simple predictive model of time-sliced iEEG time-series. More specifically, we learn distinct graphical models (so called Chow-Liu (CL) trees) as models for the spatial dependencies between iEEG signals. Bayesian inference is then applied to the CL trees, allowing for an analytic derivation/prediction of functional networks, based on thresholding of the absolute value Pearson correlation coefficient (CC) matrix. Using various measures, the thus obtained networks are then compared to those which were derived in the classical way from the empirical CC-matrix. In the high threshold limit we find (a) an excellent agreement between the two networks and (b) key features of periictal networks as they have previously been reported in the literature. Apart from functional networks, both matrices are also compared element-wise, showing that the CL approach leads to a sparse representation, by setting small correlations to values close to zero while preserving the larger ones. Overall, this paper shows the validity of CL-trees as simple, spatially predictive models for periictal iEEG data. Moreover, we suggest straightforward generalizations of the CL-approach for modeling also the temporal features of iEEG signals.

Hypovigilance detection for UCAV operators based on a hidden Markov model

With the advance of military technology, the number of unmanned combat aerial vehicles (UCAVs) has rapidly increased. However, it has been reported that the accident rate of UCAVs is much higher than that of manned combat aerial vehicles. One of the main reasons for the high accident rate of UCAVs is the hypovigilance problem which refers to the decrease in vigilance levels of UCAV operators while maneuvering. In this paper, we propose hypovigilance detection models for UCAV operators based on EEG signal to minimize the number of occurrences of hypovigilance. To enable detection, we have applied hidden Markov models (HMMs), two of which are used to indicate the operators' dual states, normal vigilance and hypovigilance, and, for each operator, the HMMs are trained as a detection model. To evaluate the efficacy and effectiveness of the proposed models, we conducted two experiments on the real-world data obtained by using EEG-signal acquisition devices, and they yielded satisfactory results. By utilizing the proposed detection models, the problem of hypovigilance of UCAV operators and the problem of high accident rate of UCAVs can be addressed.

Hidden Markov model and support vector machine based decoding of finger movements using electrocorticography

OBJECTIVE

Support vector machines (SVM) have developed into a gold standard for accurate classification in brain-computer interfaces (BCI). The choice of the most appropriate classifier for a particular application depends on several characteristics in addition to decoding accuracy. Here we investigate the implementation of hidden Markov models (HMM) for online BCIs and discuss strategies to improve their performance.

APPROACH

We compare the SVM, serving as a reference, and HMMs for classifying discrete finger movements obtained from electrocorticograms of four subjects performing a finger tapping experiment. The classifier decisions are based on a subset of low-frequency time domain and high gamma oscillation features.

MAIN RESULTS

We show that decoding optimization between the two approaches is due to the way features are extracted and selected and less dependent on the classifier. An additional gain in HMM performance of up to 6% was obtained by introducing model constraints. Comparable accuracies of up to 90% were achieved with both SVM and HMM with the high gamma cortical response providing the most important decoding information for both techniques.

SIGNIFICANCE

We discuss technical HMM characteristics and adaptations in the context of the presented data as well as for general BCI applications. Our findings suggest that HMMs and their characteristics are promising for efficient online BCIs.