Epilepsy seizure prediction with few-shot learning method.

Epileptic seizures prediction and timely alarms allow the patient to take effective and preventive actions. In this paper, a convolutional neural network (CNN) is proposed to diagnose the preictal period. Our goal is for those epileptic patients in whom seizures occur late and it is very challenging to record the preictal signal for them. In the previous works, generalized methods were inevitably used for this group of patients which were not very accurate. Our approach to solve this problem is to provide a few-shot learning method. This method, having the previous knowledge, is trained with only a small number of samples, learns new tasks and reduces the efforts to collect more data. Evaluation results for three patients from the CHB-MIT database, for a 10-min seizure prediction horizon (SPH) and a 20-min seizure occurrence period (SOP), averaged sensitivity of 95.70% and a false prediction rate (FPR) of 0.057/h and for the 5-min prediction horizon and the 25-min seizure occurrence period averaged sensitivity of 98.52% and a false prediction rate of (FPR) of 0.045/h. The proposed few-shot learning method, based on previous knowledge gained from the generalizable method, is regulated with a few new patient samples for the patient. Our results show that the accuracy obtained in this method is higher than the generalizable methods.

An EEG-Based Neuromarketing Approach for Analyzing the Preference of an Electric Car.

This study evaluates consumer preference from the perspective of neuroscience when a choice is made among a number of cars, one of which is an electric car. Consumer neuroscience contributes to a systematic understanding of the underlying information processing and cognitions involved in choosing or preferring a product. This study aims to evaluate whether neural measures, which were implicitly extracted from brain activities, can be reliable or consistent with self-reported measures such as preference or liking. In an EEG-based experiment, the participants viewed images of automobiles and their specifications. Emotional and attentional stimuli and the participants' responses, in the form of decisions made, were meticulously distinguished and analyzed via signal processing techniques, statistical tests, and brain mapping tools. Long-range temporal correlations (LRTCs) were also calculated to investigate whether the preference of a product could affect the dynamic of neuronal fluctuations. Statistically significant spatiotemporal dynamical differences were then evaluated between those who select an electric car (which seemingly demands specific memory and long-term attention) and participants who choose other cars. The results showed increased PSD and central-parietal and central-frontal coherences at the alpha frequency band for those who selected the electric car. In addition, the findings showed the emergence of LRTCs or the ability of this group to integrate information over extended periods. Furthermore, the result of clustering subjects into two groups, using statistically significant discriminative EEG measures, was associated with the self-report data. The obtained results highlighted the promising role of intrinsically extracted measures on consumers' buying behavior.

Automated sleep staging of OSAs based on ICA preprocessing and consolidation of temporal correlations.

An automated sleep staging based on analyzing long-range time correlations in EEG is proposed. These correlations, indicating time-scale invariant property or self-similarity at different time scales, are known to be salient dynamical characteristics of stage succession for a sleeping brain even when the subject suffers a destructive disorder such as Obstructive Sleep Apnea (OSA). The goal is to extract a set of complementary features from cerebral sources mapped onto the scalp electrodes or from a number of denoised EEG channels. For this purpose, source localization/extraction and noise reduction approaches based on Independent Component Analysis were used prior to correlation analysis. Feature extracted segments were then classified in one of the five classes including WAKE, STAGE1, STAGE2, SWS and REM via an ensemble neuro-fuzzy classifier. Some techniques were employed to improve the classifier's performance including Scaled Conjugate Gradient Method to speed up learning the ANFIS classifiers, a pruning algorithm to eliminate irrelevant fuzzy rules and the 10-fold cross-validation technique to train and test the system more efficiently. The performance of classification for two strategies including (1) feature extraction from effective cerebral sources and (2) feature extraction from selected channels of denoised EEG signals was compared and contrasted in terms of training errors and test accuracies. The first and second strategies achieved 92.23 and 88.74% agreement with human expert respectively which indicates the effectiveness of the staging system based on cerebral sources of activity. Our results further indicate that the misclassification rates were almost below 10%. The proposed automated sleep staging system is reliable due to the fact that it is based on the underlying dynamics of sleep staging which is less likely to be affected by sleep fragmentations occurred repeatedly in OSA.

Modeling the interaction of navigational systems in a reward-based virtual navigation task.

Existence of allocentric and egocentric systems for human navigation, mediating spatial, and response learning, respectively, has so far been discussed. It is controversial whether navigational strategies and their underlying learning systems and, accordingly, the activation of their associated brain areas are independent/parallel or whether they functionally/causally interact in a competitive or in a cooperative manner to solve navigational tasks. The insights provided by neural networks involved in reward-based navigation attributed to individual involvement or interactions of learning systems have been surveyed. This paper characterizes the interactions of neural networks by constructing generative neural models and investigating their functional and effective connectivity patterns. A single-subject computer-based virtual reality environment was constructed to simulate a navigation task within a naturalistic large-scale space wherein participants were rewarded for using either a place, response, or mixed strategy at different navigational stages. First, functional analyses were undertaken to evaluate neural activities via mapping brain activation and making statistical inference. Effects of interest, spatial and response learning/retrieval, and their competition and cooperation were investigated. The optimal generative model was then estimated using dynamic casual modeling to quantify effective connectivities within the network. This analysis revealed how experimental conditions supported competition and cooperation strategies and how they modulated the underlying network. Results suggest that when navigational strategies cooperated, there were statistically significant, functional, and effective connectivities between hippocampus and striatum. However, when the strategies competed, effective connections were not established among these regions. Instead, connections between hippocampus/striatum and prefrontal cortex were strengthened. It can be inferred that a type of dynamical reconfiguration occurs within a network responsible for navigation when strategies interact either cooperatively or competitively. This supports adaptive causal organization of the brain when it is engaged with goal directed behavior.

Quantifying the dynamic of OSA brain using multifractal formalism: A novel measure for sleep fragmentation.

It is thought that the critical brain dynamics in sleep is modulated during frequent periods of wakefulness. This paper utilizes the capacity of EEG based scaling analysis to quantify sleep fragmentation in patients with obstructive sleep apnea. The scale-free (fractal) behavior refers to a state where no characteristic scale dominates the dynamics of the underlying process which is evident as long range correlations in a time series. Here, Multiscaling (multifractal) spectrum is utilized to quantify the disturbed dynamic of an OSA brain with fragmented sleep. The whole night multichannel sleep EEG recordings of 18 subjects were employed to compute and quantify variable power-law long-range correlations and singularity spectra. Based on this characteristic, a new marker for sleep fragmentation named ``scaling based sleep fragmentation'' was introduced. This measure takes into account the sleep run length and stage transition quality within a fuzzy inference system to improve decisions made on sleep fragmentation. The proposed index was implemented, validated with sleepiness parameters and compared to some common indexes including sleep fragmentation index, arousal index, sleep diversity index, and sleep efficiency index. Correlations were almost significant suggesting that the sleep characterizing measure, based on singularity spectra range, could properly detect fragmentations and quantify their rate. This method can be an alternative for quantifying the sleep fragmentation in clinical practice after being approved experimentally. Control of sleep fragmentation and, subsequently, suppression of excessive daytime sleepiness will be a promising outlook of this kind of researches.

Pre-control characterization of hippocampal epileptic models.

This paper presents a dynamical characterization of epileptic seizures in animal models. Inter-hippocampal recordings of two animal models of seizures, kindling and pilocarpine, were analyzed by nonlinear analytic tools. The aim is to assess and differentiate pathophysiological states and behavioral phases of a status epilepticus. The achieved results indicates that stage V of Racine classification could be identified as the transition of dynamical indicators exhibit a monotonic decline up to this stage and an increase after that. Furthermore, concentration of data points on a small region of state space, achieved by our analysis, promises that a local nonlinear control may cause neuromodulation. This feasibility gets more strengthen by achievements of this paper on successful tracking of drifts of unstable periodic orbits at seizure onset. Nonlinear control algorithms could afterwards be designed to find suitable instances for inserting perturbations and steer the dynamics of system toward a desired dynamical operating mode.

On the discrimination of patho-physiological states in epilepsy by means of dynamical measures.

In the present paper a number of techniques were applied to determine the effects of epileptic seizure on spontaneous ongoing EEG. The idea is that seizure represents transitions of an epileptic brain from its normal (chaotic) state to an abnormal (more ordered) state. Some nonlinear measures including correlation dimension, maximum Lyapunov exponent and wavelet entropy and a graphical tool, named recurrence plot, as well as a novel technique that collects some statistics of the state space organization were used to characterize interictal, preictal and ictal states and derivate a phase transition. The novelty of this work includes of introducing new types of indicators base upon some nonlinear features besides of proposing a new feature of point distribution in phase space. Our results show that (1) these three states are separable in 3-D feature space of nonlinear measures with a gradual decrease of their quantity in seizure evolution, (2) strong rhythmicity, which manifests in recurrence plots and recurrence quantification analysis measures, appears in dynamic while having entered into seizure and (3) different volumes of state space are occupied during each phase of epileptic disorder. The significance of the work is that this information is a step into the detection of a preictal state and consequently is helpful in the prediction and control of epileptic seizures.

Complexity evolution in epileptic seizure.

The present paper concentrates on neural complexity generated during the phase transition in epileptic seizure. Epileptic seizures represent a sudden and transient change in the synchronized firing of neuronal brain ensembles. The proposed model treats the brain as an excitable medium for the propagation of waves of electrical activity with a level of abstraction encompassing underlying variables into a number of discrete states. The analysis presented here provides support for the notion of dynamical phase transition in the sequence of chaos --> complexity --> order during the progress of epilepsy. Evolving cellular automata and quantifying it using Langton parameter shows critical value or highest complexity at the onset of seizure phenomenon.

Wavelet packet decomposition of a new filter -- based on underlying neural activity -- for ERP classification.

This paper introduces a wavelet packet algorithm based on a new wavelet like filter created by a neural mass model in place of wavelet. The hypothesis is that the performance of an ERP based BCI system can be improved by choosing an optimal wavelet derived from underlying mechanism of ERPs. The wavelet packet transform has been chosen for its generalization in comparison to wavelet. We compared the performance of proposed algorithm with existing standard wavelets as Db4, Bior4.4 and Coif3 in wavelet packet platform. The results showed a lowest cross validation error for the new filter in classification of two different kinds of ERP datasets via a SVM classifier.