Differentiating Epileptic and Psychogenic Non-Epileptic Seizures Using Machine Learning Analysis of EEG Plot Images

The treatment of epilepsy, the second most common chronic neurological disorder, is often complicated by the failure of patients to respond to medication. Treatment failure with anti-seizure medications is often due to the presence of non-epileptic seizures. Distinguishing non-epileptic from epileptic seizures requires an expensive and time-consuming analysis of electroencephalograms (EEGs) recorded in an epilepsy monitoring unit. Machine learning algorithms have been used to detect seizures from EEG, typically using EEG waveform analysis. We employed an alternative approach, using a convolutional neural network (CNN) with transfer learning using MobileNetV2 to emulate the real-world visual analysis of EEG images by epileptologists. A total of 5359 EEG waveform plot images from 107 adult subjects across two epilepsy monitoring units in separate medical facilities were divided into epileptic and non-epileptic groups for training and cross-validation of the CNN. The model achieved an accuracy of 86.9% (Area Under the Curve, AUC 0.92) at the site where training data were extracted and an accuracy of 87.3% (AUC 0.94) at the other site whose data were only used for validation. This investigation demonstrates the high accuracy achievable with CNN analysis of EEG plot images and the robustness of this approach across EEG visualization software, laying the groundwork for further subclassification of seizures using similar approaches in a clinical setting.

A self-attention model for cross-subject seizure detection

Epilepsy is a neurological disorder characterized by recurring seizures, detected by electroencephalography (EEG). EEG signals can be detected by manual time-consuming analysis and recently by automatic detection. The latter poses a significant challenge due to the high dimensional and non-stationary nature of EEG signals. Recently, deep learning (DL) techniques have emerged as valuable tools for seizure detection. In this study, a novel data-driven model based on DL, incorporating a self-attention mechanism (SAT), is proposed. One notable advantage of the proposed method is its simplicity in application, as the raw signal data is directly fed into the suggested network without requiring expertise in signal processing. The model leverages a one-dimensional convolutional neural network (CNN) to extract relevant features from EEG signals. These features are then passed through a long short-term memory (LSTM) module to benefit from its memory capabilities, along with a SAT mechanism. The key contribution of this paper lies in the addition of the SAT layer to the LSTM encoder, enabling enhanced exploration of the latent mapping during the encoding step. Cross-subject experiments revealed good performance of this approach with F1-score of 97.8% and 92.7% for binary and five-class epileptic seizure recognition tasks, respectively, on the public UCI dataset, and 97.9% on the CHB-MIT database, surpassing state-of-the-art DL performance. Besides, the proposed method exhibits robustness to inter-subject variability.

Visibility graph for time series prediction and image classification: a review

The analysis of time series and images is significant across different fields due to their widespread applications. In the past few decades, many approaches have been developed, including data-driven artificial intelligence methods, mechanism-driven physical methods, and hybrid mechanism and data-driven models. Complex networks have been used to model numerous complex systems due to its characteristics, including time series prediction and image classification. In order to map time series and images into complex networks, many visibility graph algorithms have been developed, such as horizontal visibility graph, limited penetrable visibility graph, multiplex visibility graph, and image visibility graph. The family of visibility graph algorithms will construct different types of complex networks, including (un-) weighted, (un-) directed, and (single-) multi-layered networks, thereby focusing on different kinds of properties. Different types of visibility graph algorithms will be reviewed in this paper. Through exploring the topological structure and information in the network based on statistical physics, the property of time series and images can be discovered. In order to forecast (multivariate) time series, several variations of local random walk algorithms and different information fusion approaches are applied to measure the similarity between nodes in the network. Different forecasting frameworks are also proposed to consider the information in the time series based on the similarity. In order to classify the image, several machine learning models (such as support vector machine and linear discriminant) are used to classify images based on global features, local features, and multiplex features. Through various simulations on a variety of datasets, researchers have found that the visibility graph algorithm outperformed existing algorithms, both in time series prediction and image classification. Clearly, complex networks are closely connected with time series and images by visibility graph algorithms, rendering complex networks to be an important tool for understanding the characteristics of time series and images. Finally, we conclude in the last section with future outlooks for the visibility graph.

Network Analysis of Time Series: Novel Approaches to Network Neuroscience

In the last two decades, there has been an explosion of interest in modeling the brain as a network, where nodes correspond variously to brain regions or neurons, and edges correspond to structural or statistical dependencies between them. This kind of network construction, which preserves spatial, or structural, information while collapsing across time, has become broadly known as "network neuroscience." In this work, we provide an alternative application of network science to neural data: network-based analysis of non-linear time series and review applications of these methods to neural data. Instead of preserving spatial information and collapsing across time, network analysis of time series does the reverse: it collapses spatial information, instead preserving temporally extended dynamics, typically corresponding to evolution through some kind of phase/state-space. This allows researchers to infer a, possibly low-dimensional, "intrinsic manifold" from empirical brain data. We will discuss three methods of constructing networks from nonlinear time series, and how to interpret them in the context of neural data: recurrence networks, visibility networks, and ordinal partition networks. By capturing typically continuous, non-linear dynamics in the form of discrete networks, we show how techniques from network science, non-linear dynamics, and information theory can extract meaningful information distinct from what is normally accessible in standard network neuroscience approaches.

EMD-WOG-2DCNN based EEG signal processing for Rolandic seizure classification

Objective Approximately 65 million people have epilepsy around the world. Recognition of epilepsy types is the basis to determine the treatment method and predict the prognosis in epilepsy patients. Childhood benign epilepsy with centrotemporal spikes (BECTS) or benign Rolandic epilepsy is the most common focal epilepsy in children, accounting for 15-20% of childhood epilepsies. These EEG patterns of individuals usually predict good treatment responses and prognosis. Until now, the interpretation of EEG still depends entirely on experienced neurologists, which may be a lengthy and tedious task. Method In this article, we proposed a novel machine learning model that efficiently distinguished Rolandic seizures from normal EEG signals. The proposed machine learning model processes the identification procedure in the following order (1) creating preliminary EEG features using signal empirical mode decomposition, (2) applying weighted overlook graph (WOG) to represent the decomposed EMD of IMF, and (3) classifying the results through a two Dimensional Convolutional Neural Network (2DCNN). The performance of our classification model is compared with other representative machine learning models. Results The model offered in this article gains an accuracy performance exceeding 97.6% in the Rolandic dataset, which is higher than other classification models. The effect of the model on the Bonn public dataset is also comparable to existing methods and even performs better in some subsets. Conclusion The purpose of this study is to introduce the most common childhood benign epilepsy type and propose a model that meets the real clinical needs to distinguish this Rolandic EEG pattern from normal signals accurately. Significance Future research will optimize the model to categorize other types of epilepsies beyond BECTS and finally implement them in the hospital system.

A fuzzy sensitivity analysis approach to estimate brain effective connectivity and its application to epileptic seizure detection

The brain is considered to be the most complicated organ in human body. Inferring and quantification of effective (causal) connectivity among regions of the brain is an important step in characterization of its complicated functions. The proposed method is comprised of modeling multivariate time series with Adaptive Neurofuzzy Inference System (ANFIS) and carrying out a sensitivity analysis using Fuzzy network parameters as a new approach to introduce a connectivity measure for detecting causal interactions between interactive input time series. The results of simulations indicate that this method is successful in detecting causal connectivity. After validating the performance of the proposed method on synthetic linear and nonlinear interconnected time series, it is applied to epileptic intracranial Electroencephalography (EEG) signals. The result of applying the proposed method on Freiburg epileptic intracranial EEG data recorded during seizure shows that the proposed method is capable of discriminating between the seizure and non-seizure states of the brain.

Cuff-less Blood Pressure Estimation from Photoplethysmography via Visibility Graph and Transfer Learning

This paper presents a new solution that enables the use of transfer learning for cuff-less blood pressure (BP) monitoring via short duration of photoplethysmogram (PPG). The proposed method estimates BP with low computational budget by 1) creating images from segments of PPG via visibility graph (VG) that preserves the temporal information of the PPG waveform, 2) using pre-trained deep convolutional neural network (CNN) to extract feature vectors from VG images, and 3) solving for the weights and bias between the feature vectors and the reference BPs with ridge regression. Using the University of California Irvine (UCI) database consisting of 348 records, the proposed method achieves a best error performance of 0.008.46 mmHg for systolic blood pressure (SBP), and -0.045.36 mmHg for diastolic blood pressure (DBP), respectively, in terms of the mean error (ME) and the standard deviation (SD) of error, ranking grade B for SBP and grade A for DBP under the British Hypertension Society (BHS) protocol. Our novel data-driven method offers a computationally-efficient end-to-end solution for rapid and user-friendly cuff-less PPG-based BP estimation.

Complex networks and deep learning for EEG signal analysis

Electroencephalogram (EEG) signals acquired from brain can provide an effective representation of the human's physiological and pathological states. Up to now, much work has been conducted to study and analyze the EEG signals, aiming at spying the current states or the evolution characteristics of the complex brain system. Considering the complex interactions between different structural and functional brain regions, brain network has received a lot of attention and has made great progress in brain mechanism research. In addition, characterized by autonomous, multi-layer and diversified feature extraction, deep learning has provided an effective and feasible solution for solving complex classification problems in many fields, including brain state research. Both of them show strong ability in EEG signal analysis, but the combination of these two theories to solve the difficult classification problems based on EEG signals is still in its infancy. We here review the application of these two theories in EEG signal research, mainly involving brain-computer interface, neurological disorders and cognitive analysis. Furthermore, we also develop a framework combining recurrence plots and convolutional neural network to achieve fatigue driving recognition. The results demonstrate that complex networks and deep learning can effectively implement functional complementarity for better feature extraction and classification, especially in EEG signal analysis.

Negative Effects of Mobile Phone Addiction Tendency on Spontaneous Brain Microstates: Evidence From Resting-State EEG

The prevalence of mobile phone addiction (MPA) has increased rapidly in recent years, and it has had a certain negative impact on emotions (e.g., anxiety and depression) and cognitive capacities (e.g., executive control and working memory). At the level of neural circuits, the continued increase in activity in the brain regions associated with addiction leads to neural adaptations and structural changes. At present, the spontaneous brain microstates that could be negatively influenced by MPA are unclear. In this study, the temporal characteristics of four resting-state electroencephalogram (RS-EEG) microstates (MS1, MS2, MS3, and MS4) related to mobile phone addiction tendency (MPAT) were investigated using the Mobile Phone Addiction Tendency Scale (MPATS). We attempted to analyze the correlation between MPAT and corresponding microstates and provide evidence to explain the brain and behavioral changes caused by MPA. The results showed that the total score of the MPATS was positively correlated with the duration of MS1, related to phonological processing and negatively correlated with the duration of MS2, related to visual or imagery processing, and MS4, related to the attentional network; the score of the withdrawal symptoms subscale was additionally associated with duration of MS3, related to the cingulo-opercular emotional network. Based on these results, we believe that MPAT may have some negative effects on attentional networks and sensory brain networks; moreover, withdrawal symptoms may induce some negative emotions.

Visibility-graphlet approach to the output series of a Hodgkin-Huxley neuron

The output signals of neurons that are exposed to external stimuli are of great importance for brain functionality. Traditional time-series analysis methods have provided encouraging results; however, the associated patterns and their correlations in the output signals of neurons are masked by statistical procedures. Here, graphlets are employed to extract the local temporal patterns and the transitions between them from the output signals when neurons are exposed to external stimuli with selected stimulating periods. A transition network is defined where the node is the graphlet and the direct link is the transition between two successive graphlets. The transition-network structure is affected by the simulating periods. When the stimulating period moves close to an integer multiple of the neuronal intrinsic period, only the backbone or core survives, while the other linkages disappear. Interestingly, the size of the backbone (number of nodes) equals the multiple. The transition-network structure is conservative within each stimulating region, which is defined as the range between two successive integer multiples. Nevertheless, the backbone or detailed structure is significantly altered between different stimulating regions. This alternation is induced primarily from a total of 12 active linkages. Hence, the transition network shows the structure of cross correlations in the output time-series for a single neuron.

Analysis of magnetohydrodynamic channel flow through complex network analysis

Velocity time series of hydrodynamic and magnetohydrodynamic (MHD) turbulent flow are analyzed by means of complex network analysis in order to understand the mechanism of fluid patterns modification due to the external magnetic field. Direct numerical simulations of two cases are used, one for the plane hydrodynamic turbulent channel flow at the low Reynolds number of 180, based on the friction velocity, and the corresponding MHD flow with an external streamwise magnetic field with a magnetic interaction number of 0.1. By applying the visibility graph algorithm, we first transformed the time series into networks and then we evaluated the network topological properties. Results show that the proposed network analysis is not only able to identify and detect dynamical transitions in the system's behavior that identifies three distinct fluid areas in accordance with turbulent flow theory but also can quantify the effect of the magnetic field on the time series transitions. Moreover, we find that the topological measures of networks without a magnetic field and as compared to the one with a magnetic field are statistically different within a 95% confidence interval. These results provide a way to discriminate and characterize the influence of the magnetic field on the turbulent flows.

EEG-Based Emotion Recognition Using an Improved Weighted Horizontal Visibility Graph

Emotion recognition, as a challenging and active research area, has received considerable awareness in recent years. In this study, an attempt was made to extract complex network features from electroencephalogram (EEG) signals for emotion recognition. We proposed a novel method of constructing forward weighted horizontal visibility graphs (FWHVG) and backward weighted horizontal visibility graphs (BWHVG) based on angle measurement. The two types of complex networks were used to extract network features. Then, the two feature matrices were fused into a single feature matrix to classify EEG signals. The average emotion recognition accuracies based on complex network features of proposed method in the valence and arousal dimension were 97.53% and 97.75%. The proposed method achieved classification accuracies of 98.12% and 98.06% for valence and arousal when combined with time-domain features.

A multiplex visibility graph motif‐based convolutional neural network for characterizing sleep stages using EEG signals

Sleep is an essential integrant in everyone’s daily life; therefore, it is an important but challenging problem to characterize sleep stages from electroencephalogram (EEG) signals. The network motif has been developed as a useful tool to investigate complex networks. In this study, we developed a multiplex visibility graph motif‐based convolutional neural network (CNN) for characterizing sleep stages using EEG signals and then introduced the multiplex motif entropy as the quantitative index to distinguish the six sleep stages. The independent samples t‐test shows that the multiplex motif entropy values have significant differences among the six sleep stages. Furthermore, we developed a CNN model and employed the multiplex motif sequence as the input of the model to classify the six sleep stages. Notably, the classification accuracy of the six‐state stage detection was 85.27%. Results demonstrated the effectiveness of the multiplex motif in characterizing the dynamic features underlying different sleep stages, whereby they further provide an essential strategy for future sleep‐stage detection research.

The Automatic Detection of Seizure Based on Tensor Distance And Bayesian Linear Discriminant Analysis

Electroencephalogram (EEG) plays an important role in recording brain activity to diagnose epilepsy. However, it is not only laborious, but also not very cost effective for medical experts to manually identify the features on EEG. Therefore, automatic seizure detection in accordance with the EEG recordings is significant for the diagnosis and treatment of epilepsy. Here, a new method for detecting seizures using tensor distance (TD) is proposed. First, the time-frequency characteristics of EEG signals are obtained by wavelet transformation, and the tensor representation of EEG signals is then obtained. Tucker decomposition is used to obtain the principal components of the EEG tensor. After, the distances between different categories of EEG tensors are calculated as the EEG features. Finally, the TD features are classified through the Bayesian Linear Discriminant Analysis (Bayesian LDA) classifier. The performance of this method is measured by the sensitivity, specificity, and recognition accuracy. Results indicate 95.12% sensitivity, 97.60% specificity, 97.60% recognition accuracy, and a false detection rate of 0.76 per hour in the invasive EEG dataset, which included 566.57[Formula: see text]h of EEG recording data from 21 patients. Taken together, the results show that TD has a good detection effect for seizure classification and that this method has high computational speed and great potential for real-time diagnosis.

The Relationships Between Trait Creativity and Resting-State EEG Microstates Were Modulated by Self-Esteem

Numerous studies find that creativity is not only associated with low effort and flexible processes but also associated with high effort and persistent processes especially when defensive behavior is induced by negative emotions. The important role of self-esteem is to buffer negative emotions, and individuals with low self-esteem are prone to instigating various forms of defensive behaviors. Thus, we thought that the relationships between trait creativity and executive control brain networks might be modulated by self-esteem. The resting-state electroencephalogram (RS-EEG) microstates can be divided into four classical types (MS1, MS2, MS3, and MS4), which can reflect the brain networks as well as their dynamic characteristic. Thus, the Williams Creative Tendency Scale (WCTS) and Rosenberg Self-esteem Scale (RSES) were used to investigate the modulating role of self-esteem on the relationships between trait creativity and the RS-EEG microstates. As our results showed, self-esteem consistently modulated the relationships between creativity and the duration and contribution of MS2 related to visual or imagery processing, the occurrence of MS3 related to cingulo-opercular networks, and transitions between MS2 and MS4, which were related to frontoparietal control networks. Based on these results, we thought that trait creativity was related to the executive control of bottom-up processing for individuals with low self-esteem, while the bottom-up information from vision or visual imagery might be related to trait creativity for individuals with high self-esteem.

Construction of Multiplex Muscle Network for Precision Pinch Force Control

Muscle synergy is a fundamental mechanism of motor control. Despite a number of studies focusing on muscle synergy during power grip and pinch at high-level force, relatively less is known about the functional interactions between muscles within low-level force production during precision pinch. Traditional analytical tools such as nonnegative matrix factorization or principal component analysis have limitations in processing nonlinear dynamic electromyographic signals and have confined sensitivity particularly for the low-level force production. In this study, we developed a novel method - multiplex muscle networks, to investigate the dynamical coordination of muscle activities at low-level force production during precision pinch. The multiplex muscle network was constructed based on multiplex limited penetrable horizontal visibility graph (MLPHVG). Seven forearm and hand muscles, including brachioradialis (BR), flexor carpi ulnaris (FCU), flexor carpi radialis (FCR), flexor digitorum superficialis (FDS), extensor digitorum communis (EDC), abductor pollicis brevis (APB) and first dorsal interosseous (FDI), were examined using surface electromyography (sEMG). Eight healthy subjects were instructed to perform a visuomotor force tracking task by producing higher (10% MVC) and lower (1% MVC) precision pinch. Interlayer mutual information I, average edge overlap ω weighted clustering coefficient C^W, weighted characteristic path length L^W were selected as network metrics. We assessed the undirected weighted network generated from multiplex muscle network after taking the I between paired muscle network layers as edge. There are significant differences between higher and lower force level with higher I, ω, C^W and lower L^W at higher force level. Advanced efficiency of information processing in the regional and global perspective indicated dynamical alterations when human faces the higher force tracking task. It suggested that ω may be an important characteristic to classify different force control states with the average classification accuracy of 82.21%. These findings reveal related alterations of functional interactions between muscles involved in precision pinch. The novel method for constructing multiplex muscle network may provide insights into muscle synergies during precision pinch force control.

GRP-DNet: A gray recurrence plot-based densely connected convolutional network for classification of epileptiform EEG

BACKGROUND

The classification of epileptiform electroencephalogram (EEG) signals has been treated as an important but challenging issue for realizing epileptic seizure detection. In this work, combing gray recurrence plot (GRP) and densely connected convolutional network (DenseNet), we developed a novel classification system named GRP-DNet to identify seizures and epilepsy from single-channel, long-term EEG signals.

NEW METHODS

The proposed GRP-DNet classification system includes three main modules: 1) input module takes an input long-term EEG signal and divides it into multiple short segments using a fixed-size non-overlapping sliding window (FNSW); 2) conversion module transforms short segments into GRPs and passes them to the DenseNet; 3) fusion and decision, the predicted label of each GRP is fused using a majority voting strategy to make the final decision.

RESULTS

Six different classification experiments were designed based on a publicly available benchmark database to evaluate the effectiveness of our system. Experimental results showed that the proposed GRP-DNet achieved an excellent classification accuracy of 100 % in each classification experiment, Furthermore, GRP-DNet gave excellent computational efficiency, which indicates its tremendous potential for developing an EEG-based online epilepsy diagnosis system.

COMPARISON WITH EXISTING METHODS

Our GRP-DNet system was superior to the existing competitive classification systems using the same database.

CONCLUSIONS

The GRP-DNet is a potentially powerful system for identifying and classifying EEG signals recorded from different brain states.

Spontaneous microstates related to effects of low socioeconomic status on neuroticism

Individuals with high neuroticism had the decreased control functions of anterior cingulate cortex (ACC) over amygdala (emotion regions) and low socioeconomic status (SES) had negative effects on the functions of ACC. Based on these, we hypothesized that the decreased functions of ACC might make individuals with low SES had high level of neuroticism. According to the score of objective SES (OSES) and subjective SES (SSES) scales, subjects were divided into four groups (low SSES, high SSES, low OSES and high OSES) to investigate the roles of dynamic characteristics related to the ACC in the relationships between SES and neuroticism using resting-state EEG (RS-EEG) microstates analysis. It had been found that RS-EEG microstates can be divided into four types (MS1, MS2, MS3 and MS4) and the MS3 was related cingulo-opercular brain networks (including ACC and anterior insular). As our prediction, SSES had direct effects on neuroticism relative to OSES. Moreover, the neuroticism for low SSES was positively related to the occurrence and contribution of MS3, as well as the possibilities of transitions between MS3 and MS1. Based on these, we thought that low-SSES individuals might be more difficult to inhibit the negative emotions, especially inhibit the spontaneous thoughts related to these emotions.

False alarms reduction in non-convulsive status epilepticus detection via continuous EEG analysis

OBJECTIVE

Frequent false alarms from computer-assisted monitoring systems may harm the safety of patients with non-convulsive status epilepticus (NCSE). In this study, we aimed at reducing false alarms in the NCSE detection based on preventing from three common errors: over-interpretation of abnormal background activity, dense short ictal discharges and continuous interictal discharges as ictal discharges.

APPROACH

We analyzed 10 participants' hospital-archived 127-hour electroencephalography (EEG) recordings with 310 ictal discharges. To reduce the false alarms caused by abnormal background activity, we used morphological features extracted by visibility graph methods in addition to time-frequency features. To reduce the false alarms caused by over-interpreting short ictal discharges and interictal discharges, we created two synthetic classes-'Suspected Non-ictal' and 'Suspected Ictal'-based on the misclassified categories and constructed a synthetic 4-class dataset combining the standard two classes-'Non-ictal' and 'Ictal'-to train a 4-class classifier. Precision-recall curves were used to compare our proposed 4-class classification model and the standard 2-class classification model with or without the morphological features in the leave-one-out cross validation stage. The sensitivity and precision were primarily used as performance metrics for the detection of a seizure event.

MAIN RESULTS

The 4-class classification model improved the performance of the standard 2-class model, in particular increasing the precision by 15% at an 80% sensitivity level when only time-frequency features were used. Using the morphological features, the 4-class classification model achieved the best performances: a sensitivity of 93% ± 12% and a precision of 55% ± 30% in the group level. 100% accuracy was reached in a participant's 4.3-hour recording with 5 ictal discharges.

SIGNIFICANCE

False alarms in the NCSE detection were remarkably reduced using the morphological features and the proposed 4-class classification model.

Cross-Subject Seizure Detection in EEGs Using Deep Transfer Learning

Electroencephalography (EEG) plays an import role in monitoring the brain activities of patients with epilepsy and has been extensively used to diagnose epilepsy. Clinically reading tens or even hundreds of hours of EEG recordings is very time consuming. Therefore, automatic detection of seizure is of great importance. But the huge diversity of EEG signals belonging to different patients makes the task of seizure detection much challenging, for both human experts and automation methods. We propose three deep transfer convolutional neural networks (CNN) for automatic cross-subject seizure detection, based on VGG16, VGG19, and ResNet50, respectively. The original dataset is the CHB-MIT scalp EEG dataset. We use short time Fourier transform to generate time-frequency spectrum images as the input dataset, while positive samples are augmented due to the infrequent nature of seizure. The model parameters pretrained on ImageNet are transferred to our models. And the fine-tuned top layers, with an output layer of two neurons for binary classification (seizure or nonseizure), are trained from scratch. Then, the input dataset are randomly shuffled and divided into three partitions for training, validating, and testing the deep transfer CNNs, respectively. The average accuracies achieved by the deep transfer CNNs based on VGG16, VGG19, and ResNet50 are 97.75%, 98.26%, and 96.17% correspondingly. On those results of experiments, our method could prove to be an effective method for cross-subject seizure detection.

Disrupted Time-Dependent and Functional Connectivity Brain Network in Alzheimer's Disease: A Resting-State fMRI Study Based on Visibility Graph

Background:

Alzheimer's Disease (AD) is a progressive neurodegenerative disease with insidious onset, which is difficult to be reversed and cured. Therefore, discovering more precise biological information from neuroimaging biomarkers is crucial for accurate and automatic detection of AD.

Methods:

We innovatively used a Visibility Graph (VG) to construct the time-dependent brain networks as well as functional connectivity network to investigate the underlying dynamics of AD brain based on functional magnetic resonance imaging. There were 32 AD patients and 29 Normal Controls (NCs) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. First, the VG method mapped the time series of single brain region into networks. By extracting topological properties of the networks, the most significant features were selected as discriminant features into a supporting vector machine for classification. Furthermore, in order to detect abnormalities of these brain regions in the whole AD brain, functional connectivity among different brain regions was calculated based on the correlation of regional degree sequences.

Results:

According to the topology abnormalities exploration of local complex networks, we found several abnormal brain regions, including left insular, right posterior cingulate gyrus and other cortical regions. The accuracy of characteristics of the brain regions extracted from local complex networks was 88.52%. Association analysis demonstrated that the left inferior opercular part of frontal gyrus, right middle occipital gyrus, right superior parietal gyrus and right precuneus played a tremendous role in AD.

Conclusion:

These results would be helpful in revealing the underlying pathological mechanism of the disease.

Automatic Seizure Detection using Fully Convolutional Nested LSTM

The automatic seizure detection system can effectively help doctors to monitor and diagnose epilepsy thus reducing their workload. Many outstanding studies have given good results in the two-class seizure detection problems, but most of them are based on hand-wrought feature extraction. This study proposes an end-to-end automatic seizure detection system based on deep learning, which does not require heavy preprocessing on the EEG data or feature engineering. The fully convolutional network with three convolution blocks is first used to learn the expressive seizure characteristics from EEG data. Then these robust EEG features pertinent to seizures are presented as an input to the Nested Long Short-Term Memory (NLSTM) model to explore the inherent temporal dependencies in EEG signals. Lastly, the high-level features obtained from the NLSTM model are fed into the softmax layer to output predicted labels. The proposed method yields an accuracy range of 98.44–100% in 10 different experiments based on the Bonn University database. A larger EEG database is then used to evaluate the performance of the proposed method in real-life situations. The average sensitivity of 97.47%, specificity of 96.17%, and false detection rate of 0.487 per hour are yielded. For CHB–MIT Scalp EEG database, the proposed model also achieves a segment-level sensitivity of 94.07% with a false detection rate of 0.66 per hour. The excellent results obtained on three different EEG databases demonstrate that the proposed method has good robustness and generalization power under ideal and real-life conditions.

A TrAdaBoost Method for Detecting Multiple Subjects' N200 and P300 Potentials Based on Cross-Validation and an Adaptive Threshold

Traditional training methods need to collect a large amount of data for every subject to train a subject-specific classifier, which causes subjects fatigue and training burden. This study proposes a novel training method, TrAdaBoost based on cross-validation and an adaptive threshold (CV-T-TAB), to reduce the amount of data required for training by selecting and combining multiple subjects' classifiers that perform well on a new subject to train a classifier. This method adopts cross-validation to extend the amount of the new subject's training data and sets an adaptive threshold to select the optimal combination of the classifiers. Twenty-five subjects participated in the N200- and P300-based brain-computer interface. The study compares CV-T-TAB to five traditional training methods by testing them on the training of a support vector machine. The accuracy, information transfer rate, area under the curve, recall and precision are used to evaluate the performances under nine conditions with different amounts of data. CV-T-TAB outperforms the other methods and retains a high accuracy even when the amount of data is reduced to one-third of the original amount. The results imply that CV-T-TAB is effective in improving the performance of a subject-specific classifier with a small amount of data by adopting multiple subjects' classifiers, which reduces the training cost.

A New Methodology Based on EMD and Nonlinear Measurements for Sudden Cardiac Death Detection

Heart diseases are among the most common death causes in the population. Particularly, sudden cardiac death (SCD) is the cause of 10% of the deaths around the world. For this reason, it is necessary to develop new methodologies that can predict this event in the earliest possible stage. This work presents a novel methodology to predict when a person can develop an SCD episode before it occurs. It is based on the adroit combination of the empirical mode decomposition, nonlinear measurements, such as the Higuchi fractal and permutation entropy, and a neural network. The obtained results show that the proposed methodology is capable of detecting an SCD episode 25 min before it appears with a 94% accuracy. The main benefits of the proposal are: (1) an improved detection time of 25% compared with previously published works, (2) moderate computational complexity since only two features are used, and (3) it uses the raw ECG without any preprocessing stage, unlike recent previous works.

A recurrence network-based convolutional neural network for fatigue driving detection from EEG

Driver fatigue is an important cause of traffic accidents, which has triggered great concern for detecting drivers' fatigue. Numerous methods have been proposed to fulfill this challenging task, including feature methods and machine learning methods. Recently, with the development of deep learning techniques, many studies achieved better results than traditional feature methods, and the combination of traditional methods and deep learning techniques gradually received attention. In this paper, we propose a recurrence network-based convolutional neural network (RN-CNN) method to detect fatigue driving. To be specific, we first conduct a simulated driving experiment to collect electroencephalogram (EEG) signals of subjects under alert state and fatigue state. Then, we construct the multiplex recurrence network (RN) from EEG signals to fuse information from the original time series. Finally, CNN is employed to extract and learn the features of a multiplex RN for realizing a classification task. The results indicate that the proposed RN-CNN method can achieve an average accuracy of 92.95%. To verify the effectiveness of our method, some existing competitive methods are compared with ours. The results show that our method outperforms the existing methods, which demonstrate the effect of the RN-CNN method.

Crash dynamics of interdependent networks

The emergence and evolution of real-world systems have been extensively studied in the last few years. However, equally important phenomena are related to the dynamics of systems' collapse, which has been less explored, especially when they can be cast into interdependent systems. In this paper, we develop a dynamical model that allows scrutinizing the collapse of systems composed of two interdependent networks. Specifically, we explore the dynamics of the system's collapse under two scenarios: in the first one, the condition for failure should be satisfied for the focal node as well as for its corresponding node in the other network; while in the second one, it is enough that failure of one of the nodes occurs in either of the two networks. We report extensive numerical simulations of the dynamics performed in different setups of interdependent networks, and analyze how the system behavior depends on the previous scenarios as well as on the topology of the interdependent system. Our results can provide valuable insights into the crashing dynamics and evolutionary properties of interdependent complex systems.

EEG-Based Spatio-Temporal Convolutional Neural Network for Driver Fatigue Evaluation

Driver fatigue evaluation is of great importance for traffic safety and many intricate factors would exacerbate the difficulty. In this paper, based on the spatial-temporal structure of multichannel electroencephalogram (EEG) signals, we develop a novel EEG-based spatial-temporal convolutional neural network (ESTCNN) to detect driver fatigue. First, we introduce the core block to extract temporal dependencies from EEG signals. Then, we employ dense layers to fuse spatial features and realize classification. The developed network could automatically learn valid features from EEG signals, which outperforms the classical two-step machine learning algorithms. Importantly, we carry out fatigue driving experiments to collect EEG signals from eight subjects being alert and fatigue states. Using 2800 samples under within-subject splitting, we compare the effectiveness of ESTCNN with eight competitive methods. The results indicate that ESTCNN fulfills a better classification accuracy of 97.37% than these compared methods. Furthermore, the spatial-temporal structure of this framework advantages in computational efficiency and reference time, which allows further implementations in the brain-computer interface online systems.

Segmentation and clustering in brain MRI imaging

Clustering is a vital task in magnetic resonance imaging (MRI) brain imaging and plays an important role in the reliability of brain disease detection, diagnosis, and effectiveness of the treatment. Clustering is used in processing and analysis of brain images for different tasks, including segmentation of brain regions and tissues (grey matter, white matter, and cerebrospinal fluid) and clustering of the atrophy in different parts of the brain. This paper presents a state-of-the-art review of brain MRI studies that use clustering techniques for different tasks.

Characterization of SSMVEP-based EEG signals using multiplex limited penetrable horizontal visibility graph

The steady state motion visual evoked potential (SSMVEP)-based brain computer interface (BCI), which incorporates the motion perception capabilities of the human visual system to alleviate the negative effects caused by strong visual stimulation from steady-state VEP, has attracted a great deal of attention. In this paper, we design a SSMVEP-based experiment by Newton's ring paradigm. Then, we use the canonical correlation analysis and Support Vector Machines to classify SSMVEP signals for the SSMVEP-based electroencephalography (EEG) signal detection. We find that the classification accuracy of different subjects under fatigue state is much lower than that in the normal state. To probe into this, we develop a multiplex limited penetrable horizontal visibility graph method, which enables to infer a brain network from 62-channel EEG signals. Subsequently, we analyze the variation of the average weighted clustering coefficient and the weighted global efficiency corresponding to these two brain states and find that both network measures are lower under fatigue state. The results suggest that the associations and information transfer efficiency among different brain regions become weaker when the brain state changes from normal to fatigue, which provide new insights into the explanations for the reduced classification accuracy. The promising classification results and the findings render the proposed methods particularly useful for analyzing EEG recordings from SSMVEP-based BCI system.

Multiplex Limited Penetrable Horizontal Visibility Graph from EEG Signals for Driver Fatigue Detection

Driver fatigue is an important contributor to road accidents, and driver fatigue detection has attracted a great deal of attention on account of its significant importance. Numerous methods have been proposed to fulfill this challenging task, though, the characterization of the fatigue mechanism still, to a large extent, remains to be investigated. To address this problem, we, in this work, develop a novel Multiplex Limited Penetrable Horizontal Visibility Graph (Multiplex LPHVG) method, which allows in not only detecting fatigue driving but also probing into the brain fatigue behavior. Importantly, we use the method to construct brain networks from EEG signals recorded from different subjects performing simulated driving tasks under alert and fatigue driving states. We then employ clustering coefficient, global efficiency and characteristic path length to characterize the topological structure of the networks generated from different brain states. In addition, we combine average edge overlap with the network measures to distinguish alert and mental fatigue states. The high-accurate classification results clearly demonstrate and validate the efficacy of our multiplex LPHVG method for the fatigue detection from EEG signals. Furthermore, our findings show a significant increase of the clustering coefficient as the brain evolves from alert state to mental fatigue state, which yields novel insights into the brain behavior associated with fatigue driving.

Strong-Weak Pruning for Brain Network Identification in Connectome-Wide Neuroimaging: Application to Amyotrophic Lateral Sclerosis Disease Stage Characterization

Magnetic resonance imaging allows acquiring functional and structural connectivity data from which high-density whole-brain networks can be derived to carry out connectome-wide analyses in normal and clinical populations. Graph theory has been widely applied to investigate the modular structure of brain connections by using centrality measures to identify the "hub" of human connectomes, and community detection methods to delineate subnetworks associated with diverse cognitive and sensorimotor functions. These analyses typically rely on a preprocessing step (pruning) to reduce computational complexity and remove the weakest edges that are most likely affected by experimental noise. However, weak links may contain relevant information about brain connectivity, therefore, the identification of the optimal trade-off between retained and discarded edges is a subject of active research. We introduce a pruning algorithm to identify edges that carry the highest information content. The algorithm selects both strong edges (i.e. edges belonging to shortest paths) and weak edges that are topologically relevant in weakly connected subnetworks. The newly developed "strong-weak" pruning (SWP) algorithm was validated on simulated networks that mimic the structure of human brain networks. It was then applied for the analysis of a real dataset of subjects affected by amyotrophic lateral sclerosis (ALS), both at the early (ALS2) and late (ALS3) stage of the disease, and of healthy control subjects. SWP preprocessing allowed identifying statistically significant differences in the path length of networks between patients and healthy subjects. ALS patients showed a decrease of connectivity between frontal cortex to temporal cortex and parietal cortex and between temporal and occipital cortex. Moreover, degree of centrality measures revealed significantly different hub and centrality scores between patient subgroups. These findings suggest a widespread alteration of network topology in ALS associated with disease progression.

Visibility graph analysis of temporal irreversibility in sleep electroencephalograms

The study of sleep has continued to garner increased attention. However, most studies assume stationarity of sleep electroencephalogram (EEG) signals, whereas they are typically nonlinear and nonstationary. Little work has focused on the time irreversibility of sleep EEG signals. Hence, the aim of this work is to reveal the temporally irreversible structures of rapid-eye-movement (REM) and non-REM sleep using a visibility algorithm, which is robust to nonstationarity and finite-size effect. Results show that the temporal structure of non-REM sleep is more irreversible than that of REM sleep. The degree of irreversibility is highest in slow-wave sleep. Moreover, statistical analysis suggests that aging is the major factor that affects the irreversibility of sleep signals, while gender and body mass index contribute insignificantly. The dominant role of slow oscillations on the irreversible structures of the sleep signals is also indicated.

Empirical Functional PCA for 3D Image Feature Extraction Through Fractal Sampling

Medical image classification is currently a challenging task that can be used to aid the diagnosis of different brain diseases. Thus, exploratory and discriminative analysis techniques aiming to obtain representative features from the images play a decisive role in the design of effective Computer Aided Diagnosis (CAD) systems, which is especially important in the early diagnosis of dementia. In this work, we present a technique that allows using specific time series analysis techniques with 3D images. This is achieved by sampling the image using a fractal-based method which preserves the spatial relationship among voxels. In addition, a method called Empirical functional PCA (EfPCA) is presented, which combines Empirical Mode Decomposition (EMD) with functional PCA to express an image in the space spanned by a basis of empirical functions, instead of using components computed by a predefined basis as in Fourier or Wavelet analysis. The devised technique has been used to classify images from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and the Parkinson Progression Markers Initiative (PPMI), achieving accuracies up to 93% and 92% differential diagnosis tasks (AD versus controls and PD versus Controls, respectively). The results obtained validate the method, proving that the information retrieved by our methodology is significantly linked to the diseases.

Alternative Diagnosis of Epilepsy in Children Without Epileptiform Discharges Using Deep Convolutional Neural Networks

Numerous nonepileptic paroxysmal events, such as syncope and psychogenic nonepileptic seizures, may imitate seizures and impede diagnosis. Misdiagnosis can lead to mistreatment, affecting patients’ lives considerably. Electroencephalography is commonly used for diagnosing epilepsy. Although on electroencephalograms (EEGs), epileptiform discharges (ED) specifically indicate epilepsy, only approximately 50% of patients with epilepsy have ED in their first EEG. In this study, we developed a deep convolutional neural network (ConvNet)-based classifier to distinguish EEG between patients with epilepsy without ED and controls. Overall, 25 patients with epilepsy without ED in their EEGs and 25 age-matched patients with Tourette syndrome or syncope were enrolled. Their EEGs were classified using the deep ConvNet. When the EEG data without overlapping were used, the accuracy, sensitivity, and specificity were 65.00%, 48.00%, and 82.00%, respectively. The performance measures improved when the input EEG data were augmented through overlapping. With 95% EEG data overlapping, the accuracy, sensitivity, and specificity increased to 80.00%, 70.00%, and 90.00%, respectively. The proposed method could be regarded as a pilot study to demonstrate a proof of concept of a potential diagnostic value of deep ConvNet in patients with epilepsy without ED. Further studies are needed to assist neurologists in distinguishing nonepileptic paroxysmal events from epilepsy.

Seizure detection by convolutional neural network-based analysis of scalp electroencephalography plot images

We hypothesized that expert epileptologists can detect seizures directly by visually analyzing EEG plot images, unlike automated methods that analyze spectro-temporal features or complex, non-stationary features of EEG signals. If so, seizure detection could benefit from convolutional neural networks because their visual recognition ability is comparable to that of humans. We explored image-based seizure detection by applying convolutional neural networks to long-term EEG that included epileptic seizures. After filtering, EEG data were divided into short segments based on a given time window and converted into plot EEG images, each of which was classified by convolutional neural networks as ‘seizure’ or ‘non-seizure’. These resultant labels were then used to design a clinically practical index for seizure detection. The best true positive rate was obtained using a 1-s time window. The median true positive rate of convolutional neural networks labelling by seconds was 74%, which was higher than that of commercially available seizure detection software (20% by BESA and 31% by Persyst). For practical use, the median of detected seizure rate by minutes was 100% by convolutional neural networks, which was higher than the 73.3% by BESA and 81.7% by Persyst. The false alarm of convolutional neural networks' seizure detection was issued at 0.2 per hour, which appears acceptable for clinical practice. Moreover, we demonstrated that seizure detection improved when training was performed using EEG patterns similar to those of testing data, suggesting that adding a variety of seizure patterns to the training dataset will improve our method. Thus, artificial visual recognition by convolutional neural networks allows for seizure detection, which otherwise currently relies on skillful visual inspection by expert epileptologists during clinical diagnosis.

•

Artificial visual recognition of scalp EEG plot images successfully detects seizures.

•

CNN-based automatic detection performed better than commercial software.

•

Customized CNN learning using large datasets improves detection.

The Dynamic Brain Networks of Motor Imagery: Time-Varying Causality Analysis of Scalp EEG

Motor imagery (MI) requires subjects to visualize the requested motor behaviors, which involves a large-scale network that spans multiple brain areas. The corresponding cortical activity reflected on the scalp is characterized by event-related desynchronization (ERD) and then by event-related synchronization (ERS). However, the network mechanisms that account for the dynamic information processing of MI during the ERD and ERS periods remain unknown. Here, we combined ERD/ERS analysis with the dynamic networks in different MI stages (i.e. motor preparation, ERD and ERS) to probe the dynamic processing of MI information. Our results show that specific dynamic network structures correspond to the ERD/ERS evolution patterns. Specifically, ERD mainly shows the contralateral networks, while ERS has the symmetric networks. Moreover, different dynamic network patterns are also revealed between the two types of MIs, in which the left-hand MIs exhibit a relatively less sustained contralateral network, which may be the network mechanism that accounts for the bilateral ERD/ERS observed for the left-hand MIs. Similar to the network topologies, the three MI stages also appear to be characterized by different network properties. The above findings all demonstrate that different MI stages that involve specific brain networks for dynamically processing the MI information.

Transition of brain networks from an interictal to a preictal state preceding a seizure revealed by scalp EEG network analysis

Epilepsy is a neurological disorder in the brain that is characterized by unprovoked seizures. Epileptic seizures are attributed to abnormal synchronous neuronal activity in the brain. To detect the seizure as early as possible, the identification of specific electroencephalogram (EEG) dynamics is of great importance in investigating the transition of brain activity as the epileptic seizure approaches. In this study, we investigated the transition of brain activity from interictal to preictal states preceding a seizure by combining EEG network and clustering analyses together in different frequency bands. The findings of this study demonstrated the best clustering performance of k-medoids in the beta band; in addition, compared to the interictal state, the preictal state experienced increased synchronization of EEG network connectivity, characterized by relatively higher network properties. These findings can provide helpful insight into the mechanism of epilepsy, which can also be used in the prediction of epileptic seizures and subsequent intervention.

Automatic seizure detection using three-dimensional CNN based on multi-channel EEG

BACKGROUND

Automated seizure detection from clinical EEG data can reduce the diagnosis time and facilitate targeting treatment for epileptic patients. However, current detection approaches mainly rely on limited features manually designed by domain experts, which are inflexible for the detection of a variety of patterns in a large amount of patients' EEG data. Moreover, conventional machine learning algorithms for seizure detection cannot accommodate multi-channel Electroencephalogram (EEG) data effectively, which contains both temporal and spatial information. Recently, deep learning technology has been widely applied to perform image processing tasks, which could learns useful features from data and process multi-channel data automatically. To provide an effective system for automatic seizure detection, we proposed a new three-dimensional (3D) convolutional neural network (CNN) structure, whose inputs are multi-channel EEG signals.

METHODS

EEG data of 13 patients were collected from one center hospital, which has already been inspected by experts. To represent EEG data in CNN, firstly time series of each channel of EEG data was converted into the two-dimensional image. Then all channel images were combined into 3D images according to the mutual correlation intensity between different electrodes. Finally, a CNN was constructed using 3D kernels to predict different stages of EEG data, including inter-ictal, pre-ictal, and ictal stages. The system performance was evaluated and compared with the traditional feature-based classifier and the two-dimensional (2D) deep learning method.

RESULTS

It demonstrated that multi-channel EEG data could provide more information for increasing the specificity and sensitivity in cpmparison result between the single and multi-channel. And the 3D CNN based on multi-channel outperformed the 2D CNN and traditional signal processing methods with an accuracy of more than 90%, an sensitivity of 88.90% and an specificity of 93.78%.

CONCLUSIONS

This is the first effort to apply 3D CNN in detecting seizures from EEG. It provides a new way of learning patterns simultaneously from multi-channel EEG signals, and demonstrates that deep neural networks in combination with 3D kernels can establish an effective system for seizure detection.

Visibility Graph Feature Model of Vibration Signals: A Novel Bearing Fault Diagnosis Approach

Reliable fault diagnosis of rolling bearings is an important issue for the normal operation of many rotating machines. Information about the structure dynamics is always hidden in the vibration response of the bearings, and it is often very difficult to extract them correctly due to the nonlinear/chaotic nature of the vibration signal. This paper proposes a new feature extraction model of vibration signals for bearing fault diagnosis by employing a recently-developed concept in graph theory, the visibility graph (VG). The VG approach is used to convert the vibration signals into a binary matrix. We extract 15 VG features from the binary matrix by using the network analysis and image processing methods. The three global VG features are proposed based on the complex network theory to describe the global characteristics of the binary matrix. The 12 local VG features are proposed based on the texture analysis method of images, Gaussian Markov random fields, to describe the local characteristics of the binary matrix. The feature selection algorithm is applied to select the VG feature subsets with the best performance. Experimental results are shown for the Case Western Reserve University Bearing Data. The efficiency of the visibility graph feature model is verified by the higher diagnosis accuracy compared to the statistical and wavelet package feature model. The VG features can be used to recognize the fault of rolling bearings under variable working conditions.

Automated seizure prediction

In the past two decades, significant advances have been made on automated electroencephalogram (EEG)-based diagnosis of epilepsy and seizure detection. A number of innovative algorithms have been introduced that can aid in epilepsy diagnosis with a high degree of accuracy. In recent years, the frontiers of computational epilepsy research have moved to seizure prediction, a more challenging problem. While antiepileptic medication can result in complete seizure freedom in many patients with epilepsy, up to one-third of patients living with epilepsy will have medically intractable epilepsy, where medications reduce seizure frequency but do not completely control seizures. If a seizure can be predicted prior to its clinical manifestation, then there is potential for abortive treatment to be given, either self-administered or via an implanted device administering medication or electrical stimulation. This will have a far-reaching impact on the treatment of epilepsy and patient's quality of life. This paper presents a state-of-the-art review of recent efforts and journal articles on seizure prediction. The technologies developed for epilepsy diagnosis and seizure detection are being adapted and extended for seizure prediction. The paper ends with some novel ideas for seizure prediction using the increasingly ubiquitous machine learning technology, particularly deep neural network machine learning.

A Novel Wavelet Transform-Homogeneity Model for Sudden Cardiac Death Prediction Using ECG Signals

Sudden cardiac death (SCD) is one of the main causes of death among people. A new methodology is presented for predicting the SCD based on ECG signals employing the wavelet packet transform (WPT), a signal processing technique, homogeneity index (HI), a nonlinear measurement for time series signals, and the Enhanced Probabilistic Neural Network classification algorithm. The effectiveness and usefulness of the proposed method is evaluated using a database of measured ECG data acquired from 20 SCD and 18 normal patients. The proposed methodology presents the following significant advantages: (1) compared with previous works, the proposed methodology achieves a higher accuracy using a single nonlinear feature, HI, thus requiring low computational resource for predicting an SCD onset in real-time, unlike other methodologies proposed in the literature where a large number of nonlinear features are used to predict an SCD event; (2) it is capable of predicting the risk of developing an SCD event up to 20 min prior to the onset with a high accuracy of 95.8%, superseding the prior 12 min prediction time reported recently, and (3) it uses the ECG signal directly without the need for transforming the signal to a heart rate variability signal, thus saving time in the processing.

Accurate Indoor Localization Based on CSI and Visibility Graph

Passive indoor localization techniques can have many important applications. They are nonintrusive and do not require users carrying measuring devices. Therefore, indoor localization techniques are widely used in many critical areas, such as security, logistics, healthcare, etc. However, because of the unpredictable indoor environment dynamics, the existing nonintrusive indoor localization techniques can be quite inaccurate, which greatly limits their real-world applications. To address those problems, in this work, we develop a channel state information (CSI) based indoor localization technique. Unlike the existing methods, we employ both the intra-subcarrier statistics features and the inter-subcarrier network features. Specifically, we make the following contributions: (1) we design a novel passive indoor localization algorithm which combines the statistics and network features; (2) we modify the visibility graph (VG) technique to build complex networks for the indoor localization applications; and (3) we demonstrate the effectiveness of our technique using real-world deployments. The experimental results show that our technique can achieve about 96% accuracy on average and is more than 9% better than the state-of-the-art techniques.

A recurrence quantification analysis-based channel-frequency convolutional neural network for emotion recognition from EEG

Constructing a reliable and stable emotion recognition system is a critical but challenging issue for realizing an intelligent human-machine interaction. In this study, we contribute a novel channel-frequency convolutional neural network (CFCNN), combined with recurrence quantification analysis (RQA), for the robust recognition of electroencephalogram (EEG) signals collected from different emotion states. We employ movie clips as the stimuli to induce happiness, sadness, and fear emotions and simultaneously measure the corresponding EEG signals. Then the entropy measures, obtained from the RQA operation on EEG signals of different frequency bands, are fed into the novel CFCNN. The results indicate that our system can provide a high emotion recognition accuracy of 92.24% and a relatively excellent stability as well as a satisfactory Kappa value of 0.884, rendering our system particularly useful for the emotion recognition task. Meanwhile, we compare the performance of the entropy measures, extracted from each frequency band, in distinguishing the three emotion states. We mainly find that emotional features extracted from the gamma band present a considerably higher classification accuracy of 90.51% and a Kappa value of 0.858, proving the high relation between emotional process and gamma frequency band.

Multivariate weighted recurrence network analysis of EEG signals from ERP-based smart home system

Smart home has been widely used to improve the living quality of people. Recently, the brain-computer interface (BCI) contributes greatly to the smart home system. We design a BCI-based smart home system, in which the event-related potentials (ERP) are induced by the image interface based on the oddball paradigm. Then, we investigate the influence of mental fatigue on the ERP classification by the Fisher linear discriminant analysis. The results indicate that the classification accuracy of ERP decreases as the brain evolves from the normal stage to the mental fatigue stage. In order to probe into the difference of the brain, cognitive process between mental fatigue and normal states, we construct multivariate weighted recurrence networks and analyze the variation of the weighted clustering coefficient and weighted global efficiency corresponding to these two brain states. The findings suggest that these two network metrics allow distinguishing normal and mental fatigue states and yield novel insights into the brain fatigue behavior resulting from a long use of the ERP-based smart home system. These properties render the multivariate recurrence network, particularly useful for analyzing electroencephalographic recordings from the ERP-based smart home system.

Link Prediction Investigation of Dynamic Information Flow in Epilepsy

As a brain disorder, epilepsy is characterized with abnormal hypersynchronous neural firings. It is known that seizures initiate and propagate in different brain regions. Long-term intracranial multichannel electroencephalography (EEG) reflects broadband ictal activity under seizure occurrence. Network-based techniques are efficient in discovering brain dynamics and offering finger-print features for specific individuals. In this study, we adopt link prediction for proposing a novel workflow aiming to quantify seizure dynamics and uncover pathological mechanisms of epilepsy. A dataset of EEG signals was enrolled that recorded from 8 patients with 3 different types of pharmocoresistant focal epilepsy. Weighted networks are obtained from phase locking value (PLV) in subband EEG oscillations. Common neighbor (CN), resource allocation (RA), Adamic-Adar (AA), and Sorenson algorithms are brought in for link prediction performance comparison. Results demonstrate that RA outperforms its rivals. Similarity, matrix was produced from the RA technique performing on EEG networks later. Nodes are gathered to form sequences by selecting the ones with the highest similarity. It is demonstrated that variations are in accordance with seizure attack in node sequences of gamma band EEG oscillations. What is more, variations in node sequences monitor the total seizure journey including its initiation and termination.