A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals

Utilizing risk-controlling prediction calibration to reduce false alarm rates in epileptic seizure prediction

Introduction

Epilepsy is a neurological disease characterized by sudden, unprovoked seizures. The unexpected nature of epileptic seizures is a major component of the disease burden. Predicting seizure onset and alarming patients may allow timely intervention, which would improve clinical outcomes and patient quality of life. Currently, algorithms aiming to predict seizures suffer from a high false alarm rate, rendering them unsuitable for clinical use.

Methods

We adopted here a risk-controlling prediction calibration method called Learn then Test to reduce false alarm rates of seizure prediction. This method calibrates the output of a "black-box" model to meet a specified false alarm rate requirement. The method was initially validated on synthetic data and subsequently tested on publicly available electroencephalogram (EEG) records from 15 patients with epilepsy by calibrating the outputs of a deep learning model.

Results and discussion

Validation showed that the calibration method rigorously controlled the false alarm rate at a user-desired level after our adaptation. Real data testing showed an average of 92% reduction in the false alarm rate, at the cost of missing four of nine seizures of six patients. Better-performing prediction models combined with the proposed method may facilitate the clinical use of real-time seizure prediction systems.

TastePeptides-EEG: An Ensemble Model for Umami Taste Evaluation Based on Electroencephalogram and Machine Learning

In the field of food, the sensory evaluation of food still relies on the results of manual sensory evaluation, but the results of human sensory evaluation are not universal, and there is a problem of speech fraud. This work proposed an electroencephalography (EEG)-based analysis method that effectively enables the identification of umami/non-umami substances. First, the key features were extracted using percentage conversion, standardization, and significance screening, and based on these features, the top four models were selected from 19 common binary classification algorithms as submodels. Then, the support vector machine (SVM) algorithm was used to fit the outputs of these four submodels to establish TastePeptides-EEG. The validation set of the model achieved a judgment accuracy of 90.2%, and the test set achieved a judgment accuracy of 77.8%. This study discovered the frequency change of α wave in umami taste perception and found the frequency response delay phenomenon of the F/RT/C area under umami taste stimulation for the first time. The model is published at www.tastepeptides-meta.com/TastePeptides-EEG, which is convenient for relevant researchers to speed up the analysis of umami perception and provide help for the development of the next generation of brain-computer interfaces for flavor perception.

An effective fusion model for seizure prediction: GAMRNN

The early prediction of epileptic seizures holds paramount significance in patient care and medical research. Extracting useful spatial-temporal features to facilitate seizure prediction represents a primary challenge in this field. This study proposes GAMRNN, a novel methodology integrating a dual-layer gated recurrent unit (GRU) model with a convolutional attention module. GAMRNN aims to capture intricate spatial-temporal characteristics by highlighting informative feature channels and spatial pattern dynamics. We employ the Lion optimization algorithm to enhance the model's generalization capability and predictive accuracy. Our evaluation of GAMRNN on the widely utilized CHB-MIT EEG dataset demonstrates its effectiveness in seizure prediction. The results include an impressive average classification accuracy of 91.73%, sensitivity of 88.09%, specificity of 92.09%, and a low false positive rate of 0.053/h. Notably, GAMRNN enables early seizure prediction with a lead time ranging from 5 to 35 min, exhibiting remarkable performance improvements compared to similar prediction models.

Differentiating brain states via multi-clip random fragment strategy-based interactive bidirectional recurrent neural network

EEG is widely adopted to study the brain and brain computer interface (BCI) for its non-invasiveness and low costs. Specifically EEG can be applied to differentiate brain states, which is important for better understanding the working mechanisms of the brain. Recurrent neural network (RNN)-based learning strategy has been widely utilized to differentiate brain states, because its optimization architectures improve the classification performance for differentiating brain states at the group level. However, present classification performance is still far from satisfactory. We have identified two major focal points for improvements: one is about organizing the input EEG signals, and the other is related to the design of the RNN architecture. To optimize the above-mentioned issues and achieve better brain state classification performance, we propose a novel multi-clip random fragment strategy-based interactive bidirectional recurrent neural network (McRFS-IBiRNN) model in this work. This model has two advantages over previous methods. First, the McRFS component is designed to re-organize the input EEG signals to make them more suitable for the RNN architecture. Second, the IBiRNN component is an innovative design to model the RNN layers with interaction connections to enhance the fusion of bidirectional features. By adopting the proposed model, promising brain states classification performances are obtained. For example, 96.97% and 99.34% of individual and group level four-category classification accuracies are successfully obtained on the EEG motor/imagery dataset, respectively. A 99.01% accuracy can be observed for four-category classification tasks with new subjects not seen before, which demonstrates the generalization of our proposed method. Compared with existing methods, our model outperforms them with superior results. Overall, the proposed McRFS-IBiRNN model demonstrates great superiority in differentiating brain states on EEG signals.

Patient-Specific Preictal Pattern-Aware Epileptic Seizure Prediction with Federated Learning

Electroencephalography (EEG) signals are the primary source for discriminating the preictal from the interictal stage, enabling early warnings before the seizure onset. Epileptic siezure prediction systems face significant challenges due to data scarcity, diversity, and privacy. This paper proposes a three-tier architecture for epileptic seizure prediction associated with the Federated Learning (FL) model, which is able to achieve enhanced capability by utilizing a significant number of seizure patterns from globally distributed patients while maintaining data privacy. The determination of the preictal state is influenced by global and local model-assisted decision making by modeling the two-level edge layer. The Spiking Encoder (SE), integrated with the Graph Convolutional Neural Network (Spiking-GCNN), works as the local model trained using a bi-timescale approach. Each local model utilizes the aggregated seizure knowledge obtained from the different medical centers through FL and determines the preictal probability in the coarse-grained personalization. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized in fine-grained personalization to recognize epileptic seizure patients by examining the outcomes of the FL model, heart rate variability features, and patient-specific clinical features. Thus, the proposed approach achieved 96.33% sensitivity and 96.14% specificity when tested on the CHB-MIT EEG dataset when modeling was performed using the bi-timescale approach and Spiking-GCNN-based epileptic pattern learning. Moreover, the adoption of federated learning greatly assists the proposed system, yielding a 96.28% higher accuracy as a result of addressing data scarcity.

Spatiotemporal characteristics of cortical activities of REM sleep behavior disorder revealed by explainable machine learning using 3D convolutional neural network

Isolated rapid eye movement sleep behavior disorder (iRBD) is a sleep disorder characterized by dream enactment behavior without any neurological disease and is frequently accompanied by cognitive dysfunction. The purpose of this study was to reveal the spatiotemporal characteristics of abnormal cortical activities underlying cognitive dysfunction in patients with iRBD based on an explainable machine learning approach. A convolutional neural network (CNN) was trained to discriminate the cortical activities of patients with iRBD and normal controls based on three-dimensional input data representing spatiotemporal cortical activities during an attention task. The input nodes critical for classification were determined to reveal the spatiotemporal characteristics of the cortical activities that were most relevant to cognitive impairment in iRBD. The trained classifiers showed high classification accuracy, while the identified critical input nodes were in line with preliminary knowledge of cortical dysfunction associated with iRBD in terms of both spatial location and temporal epoch for relevant cortical information processing for visuospatial attention tasks.

An end-to-end seizure prediction approach using long short-term memory network

There are increasing epilepsy patients suffering from the pain of seizure onsets, and effective prediction of seizures could improve their quality of life. To obtain high sensitivity for epileptic seizure prediction, current studies generally need complex feature extraction operations, which heavily depends on the artificial experience (or domain knowledge) and is highly subjective. To address these issues, in this paper we propose an end-to-end epileptic seizure prediction approach based on the long short-term memory network (LSTM). In the new method, only the gamma band of raw electroencephalography (EEG) signals is extracted as network input directly for seizure prediction, thus avoiding subjective and expensive feature design process. Despite its simplicity, the proposed method achieves the mean sensitivity of 91.76% and false prediction rate (FPR) of 0.29/h on Children's Hospital Boston-MIT (CHB-MIT) scalp EEG Database, respectively, when identifying the preictal stage from the EEG signals. Furthermore, different from traditional methods that only consider the classification of preictal and interictal EEG, we introduce the postictal stage as an extra class in the proposed method. As a result, the performance of seizure prediction is further improved, obtaining a higher sensitivity of 92.17% and a low FPR of 0.27/h. The mean warning time is 44.46 min, which suggests that sufficient time is reserved for patients to take intervention measures by this prediction method.

Transformer-Based Network with Optimization for Cross-Subject Motor Imagery Identification

Exploring the effective signal features of electroencephalogram (EEG) signals is an important issue in the research of brain-computer interface (BCI), and the results can reveal the motor intentions that trigger electrical changes in the brain, which has broad research prospects for feature extraction from EEG data. In contrast to previous EEG decoding methods that are based solely on a convolutional neural network, the traditional convolutional classification algorithm is optimized by combining a transformer mechanism with a constructed end-to-end EEG signal decoding algorithm based on swarm intelligence theory and virtual adversarial training. The use of a self-attention mechanism is studied to expand the receptive field of EEG signals to global dependence and train the neural network by optimizing the global parameters in the model. The proposed model is evaluated on a real-world public dataset and achieves the highest average accuracy of 63.56% in cross-subject experiments, which is significantly higher than that found for recently published algorithms. Additionally, good performance is achieved in decoding motor intentions. The experimental results show that the proposed classification framework promotes the global connection and optimization of EEG signals, which can be further applied to other BCI tasks.

Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction

Epilepsy is the second common neurological disorder after headache, accurate and reliable prediction of seizures is of great clinical value. Most epileptic seizure prediction methods consider only the EEG signal or extract and classify the features of EEG and ECG signals separately, the improvement of prediction performance from multimodal data is not fully considered. In addition, epilepsy data are time-varying, with differences between each episode in a patient, making it difficult for traditional curve-fitting models to achieve high accuracy and reliability. In order to improve the accuracy and reliability of the prediction system, we propose a novel personalized approach based on data fusion and domain adversarial training to predict epileptic seizures using leave-one-out cross-validation, which achieves an average accuracy, sensitivity and specificity of 99.70, 99.76, and 99.61%, respectively, with an average error alarm rate (FAR) of 0.001. Finally, the advantage of this approach is demonstrated by comparison with recent relevant literature. This method will be incorporated into clinical practice to provide personalized reference information for epileptic seizure prediction.

Study on characteristic of epileptic multi-electroencephalograph base on Hilbert-Huang transform and brain network dynamics

Lots of studies have been carried out on characteristic of epileptic Electroencephalograph (EEG). However, traditional EEG characteristic research methods lack exploration of spatial information. To study the characteristics of epileptic EEG signals from the perspective of the whole brain，this paper proposed combination methods of multi-channel characteristics from time-frequency and spatial domains. This paper was from two aspects: Firstly, signals were converted into 2D Hilbert Spectrum (HS) images which reflected the time-frequency characteristics by Hilbert-Huang Transform (HHT). These images were identified by Convolutional Neural Network (CNN) model whose sensitivity was 99.8%, accuracy was 98.7%, specificity was 97.4%, F1-score was 98.7%, and AUC-ROC was 99.9%. Secondly, the multi-channel signals were converted into brain networks which reflected the spatial characteristics by Symbolic Transfer Entropy (STE) among different channels EEG. And the results show that there are different network properties between ictal and interictal phase and the signals during the ictal enter the synchronization state more quickly, which was verified by Kuramoto model. To summarize, our results show that there was different characteristics among channels for the ictal and interictal phase, which can provide effective physical non-invasive indicators for the identification and prediction of epileptic seizures.

The Effects of Exam-Induced Stress on EEG Profiles and Memory Scores

Common stressors amongst postsecondary students are exam-induced anxiety and stress. The purpose of this study was to measure stress alterations in the student population around examinations and determine how they affect electroencephalogram (EEG) profiles and memory scores. Twenty university students were measured multiple times in the study. During each measurement, participants were administered a cortisol saliva test and an EEG. We hypothesized that cortisol levels, memory scores, and EEG profiles would all demonstrate changes near examinations. The brain regions of interest (ROIs) were the parahippocampal gyrus, the medial frontal gyrus, and the middle frontal gyrus. Results demonstrated that memory performance and parahippocampal activity were correlated, specifically in the 5-9 Hz frequency band. Correlations were also computed between cortisol levels, memory performance, and parahippocampal activity. The medial frontal gyrus also displayed changes in the mean (19-20 Hz) current source density (CSD) throughout the experiment. The middle frontal gyrus activation was highly variable during the different measurement time points. Essentially, when an individual's memory scores were consistent between exam and nonexam trials, there was an increase in middle frontal gyrus activation during examination periods. Lastly, the right parahippocampal gyrus was found to be the most activated one day away from examination time. These results indicate that memory scores are related to cortisol levels and examination periods, but most importantly, there are overt and predictable alterations in student EEG profiles near examinations.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

Discriminating and understanding brain states in children with epileptic spasms using deep learning and graph metrics analysis of brain connectivity

BACKGROUND AND OBJECTIVE

Epilepsy is a brain disorder consisting of abnormal electrical discharges of neurons resulting in epileptic seizures. The nature and spatial distribution of these electrical signals make epilepsy a field for the analysis of brain connectivity using artificial intelligence and network analysis techniques since their study requires large amounts of data over large spatial and temporal scales. For example, to discriminate states that would otherwise be indistinguishable from the human eye. This paper aims to identify the different brain states that appear concerning the intriguing seizure type of epileptic spasms. Once these states have been differentiated, an attempt is made to understand their corresponding brain activity.

METHODS

The representation of brain connectivity can be done by graphing the topology and intensity of brain activations. Graph images from different instants within and outside the actual seizure are used as input to a deep learning model for classification purposes. This work uses convolutional neural networks to discriminate the different states of the epileptic brain based on the appearance of these graphs at different times. Next, we apply several graph metrics as an aid to interpret what happens in the brain regions during and around the seizure.

RESULTS

Results show that the model consistently finds distinctive brain states in children with epilepsy with focal onset epileptic spasms that are indistinguishable under the expert visual inspection of EEG traces. Furthermore, differences are found in brain connectivity and network measures in each of the different states.

CONCLUSIONS

Computer-assisted discrimination using this model can detect subtle differences in the various brain states of children with epileptic spasms. The research reveals previously undisclosed information regarding brain connectivity and networks, allowing for a better understanding of the pathophysiology and evolving characteristics of this particular seizure type. From our data, we speculate that the prefrontal, premotor, and motor cortices could be more involved in a hypersynchronized state occurring in the few seconds immediately preceding the visually evident EEG and clinical ictal features of the first spasm in a cluster. On the other hand, a disconnection in centro-parietal areas seems a relevant feature in the predisposition and repetitive generation of epileptic spasms within clusters.

An Enhanced EEG Microstate Recognition Framework Based on Deep Neural Networks: An Application to Parkinson's Disease

Variations in brain activity patterns reveal impairments of motor and cognitive functions in the human brain. Electroencephalogram (EEG) microstates embody brain activity patterns at a microscopic time scale. However, current microstate analysis method can only recognize less than 90% of EEG signals per subject, which severely limits the characterization of dynamic brain activity. As an application to early Parkinson's disease (PD), we propose an enhanced EEG microstate recognition framework based on deep neural networks, which yields recognition rates from 90% to 99%, as accompanied by a strong anti-artifact property. Additionally, gradient-weighted class activation mapping, as a visualization technique, is employed to locate the activated functional brain regions of each microstate class. We find that each microstate class corresponds to a particular activated brain region. Finally, based on the improved identification of microstate sequences, we explore the EEG microstate characteristics and their clinical associations. We show that the decreased occurrences of a particular microstate class reflect the degree of cognitive decline in early PD, and reduced transitions between certain microstates suggest injury in motor-related brain regions. The novel EEG microstate recognition framework paves the way to revealing more effective biomarkers for early PD.

Epileptic seizure detection by using interpretable machine learning models

Objective.Accurate detection of epileptic seizures using electroencephalogram (EEG) data is essential for epilepsy diagnosis, but the visual diagnostic process for clinical experts is a time-consuming task. To improve efficiency, some seizure detection methods have been proposed. Regardless of traditional or machine learning methods, the results identify only seizures and non-seizures. Our goal is not only to detect seizures but also to explain the basis for detection and provide reference information to clinical experts.Approach.In this study, we follow the visual diagnosis mechanism used by clinical experts that directly processes plotted EEG image data and apply some commonly used models of LeNet, VGG, deep residual network (ResNet), and vision transformer (ViT) to the EEG image classification task. Before using these models, we propose a data augmentation method using random channel ordering (RCO), which adjusts the channel order to generate new images. The Gradient-weighted class activation mapping (Grad-CAM) and attention layer methods are used to interpret the models.Main results.The RCO method can balance the dataset in seizure and non-seizure classes. The models achieved good performance in the seizure detection task. Moreover, the Grad-CAM and attention layer methods explained the detection basis of the model very well and calculate a value that measures the seizure degree.Significance.Processing EEG data in the form of images can flexibility to use a variety of machine learning models. The imbalance problem that exists widely in clinical practice is well solved by the RCO method. Since the method follows the visual diagnosis mechanism of clinical experts, the model interpretation results can be presented to clinical experts intuitively, and the quantitative information provided by the model is also a good diagnostic reference.

EEG datasets for seizure detection and prediction- A review

Electroencephalogram (EEG) datasets from epilepsy patients have been used to develop seizure detection and prediction algorithms using machine learning (ML) techniques with the aim of implementing the learned model in a device. However, the format and structure of publicly available datasets are different from each other, and there is a lack of guidelines on the use of these datasets. This impacts the generatability, generalizability, and reproducibility of the results and findings produced by the studies. In this narrative review, we compiled and compared the different characteristics of the publicly available EEG datasets that are commonly used to develop seizure detection and prediction algorithms. We investigated the advantages and limitations of the characteristics of the EEG datasets. Based on our study, we identified 17 characteristics that make the EEG datasets unique from each other. We also briefly looked into how certain characteristics of the publicly available datasets affect the performance and outcome of a study, as well as the influences it has on the choice of ML techniques and preprocessing steps required to develop seizure detection and prediction algorithms. In conclusion, this study provides a guideline on the choice of publicly available EEG datasets to both clinicians and scientists working to develop a reproducible, generalizable, and effective seizure detection and prediction algorithm.

C2SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

Recent developments in brain-machine interface technology have rendered seizure prediction possible. However, the transmission of a large volume of electrophysiological signals between sensors and processing apparatuses and the related computation become two major bottlenecks for seizure prediction systems due to the constrained bandwidth and limited computational resources, especially for power-critical wearable and implantable medical devices. Although many data compression methods can be adopted to compress the signals to reduce communication bandwidth requirement, they require complex compression and reconstruction procedures before the signal can be used for seizure prediction. In this paper, we propose $\text{C}^{{2}}$ SP-Net, a framework to jointly solve compression, prediction, and reconstruction without extra computation overhead. The framework consists of a plug-and-play in-sensor compression matrix to reduce transmission bandwidth requirements. The compressed signal can be utilized for seizure prediction without additional reconstruction steps. Reconstruction of the original signal can also be carried out in high fidelity. Compression and classification overhead from the energy consumption perspective, prediction accuracy, sensitivity, false prediction rate, and reconstruction quality of the proposed framework are evaluated using various compression ratios. The experimental results illustrate that our proposed framework is energy efficient and outperforms the competitive state-of-the-art baselines by a large margin in prediction accuracy. In particular, our proposed method produces an average loss of 0.6% in prediction accuracy with a compression ratio ranging from 1/2 to 1/16.

Deep Learning Staging of Liver Iron Content From Multiecho MR Images

BACKGROUND

MRI represents the most established liver iron content (LIC) evaluation approach by estimation of liver T2* value, but it is dependent on the choice of the measurement region and the software used for image analysis.

PURPOSE

To develop a deep-learning method for unsupervised classification of LIC from magnitude T2* multiecho MR images.

STUDY TYPE

Retrospective.

POPULATION/SUBJECTS

A total of 1069 thalassemia major patients enrolled in the core laboratory of the Myocardial Iron Overload in Thalassemia (MIOT) network, which were included in the training (80%) and test (20%) sets. Twenty patients from different MRI vendors included in the external test set.

FIELD STRENGTH/SEQUENCE

A5 T, T2* multiecho magnitude images.

ASSESSMENT

Four deep-learning convolutional neural networks (HippoNet-2D, HippoNet-3D, HippoNet-LSTM, and an ensemble network HippoNet-Ensemble) were used to achieve unsupervised staging of LIC using five classes (normal, borderline, middle, moderate, severe). The training set was employed to construct the deep-learning model. The performance of the LIC staging model was evaluated in the test set and in the external test set. The model's performances were assessed by evaluating the accuracy, sensitivity, and specificity with respect to the ground truth labels obtained by T2* measurements and by comparison with operator-induced variability originating from different region of interest (ROI) placements.

STATISTICAL TESTS

The network's performances were evaluated by single-class accuracy, specificity, and sensitivity and compared by one-way repeated measures analysis of variance (ANOVA) and one-way ANOVA.

RESULTS

HippoNet-Ensemble reached an accuracy significantly higher than the other networks, and a sensitivity and specificity higher than HippoNet-LSTM. Accuracy, sensitivity, and specificity values for the LIC stages were: normal: 0.96/0.93/0.97, borderline: 0.95/0.85/0.98, mild: 0.96/0.88/0.98, moderate: 0.95/0.89/0.97, severe: 0.97/0.95/0.98. Correctly staging of cases was in the range of 85%-95%, depending on the LIC class. Multiclass accuracy was 0.90 against 0.92 for the interobserver variability.

DATA CONCLUSION

The proposed HippoNet-Ensemble network can perform unsupervised LIC staging and achieves good prognostic performance.

EVIDENCE LEVEL

4 TECHNICAL EFFICACY: Stage 2.

Automatic prediction of epileptic seizure using hybrid deep ResNet-LSTM model

Numerous advanced data processing and machine learning techniques for identifying epileptic seizures have been developed in the last two decades. Nonetheless, many of these solutions need massive data sets and intricate computations. Our approach transforms electroencephalogram (EEG) data into the time-frequency domain by utilizing a short-time fourier transform (STFT) and the spectrogram (t-f) images as the input stage of the deep learning model. Using EEG data, we have constructed a hybrid model comprising of a Deep Convolution Network (ResNet50) and a Long Short-Term Memory (LSTM) for predicting epileptic seizures. Spectrogram images are used to train the proposed hybrid model for feature extraction and classification. We analyzed the CHB-MIT scalp EEG dataset. For each preictal period of 5, 15, and 30 minutes, experiments are conducted to evaluate the performance of the proposed model. The experimental results indicate that the proposed model produced the optimum performance with a 5-minute preictal duration. We achieved an average accuracy of 94.5%, the average sensitivity of 93.7%, the f1-score of 0.9376, and the average false positive rate (FPR) of 0.055. Our proposed technique surpassed the random predictor and other current algorithms used for seizure prediction for all patients’ data in the dataset. One can use the effectiveness of our proposed model to help in the early diagnosis of epilepsy and provide early treatment.

Machine learning seizure prediction: one problematic but accepted practice

Objective.Epilepsy is one of the most common neurological disorders and can have a devastating effect on a person's quality of life. As such, the search for markers which indicate an upcoming seizure is a critically important area of research which would allow either on-demand treatment or early warning for people suffering with these disorders. There is a growing body of work which uses machine learning methods to detect pre-seizure biomarkers from electroencephalography (EEG), however the high prediction rates published do not translate into the clinical setting. Our objective is to investigate a potential reason for this.Approach.We conduct an empirical study of a commonly used data labelling method for EEG seizure prediction which relies on labelling small windows of EEG data in temporal groups then selecting randomly from those windows to validate results. We investigate a confound for this approach for seizure prediction and demonstrate the ease at which it can be inadvertently learned by a machine learning system.Main results.We find that non-seizure signals can create decision surfaces for machine learning approaches which can result in false high prediction accuracy on validation datasets. We prove this by training an artificial neural network to learn fake seizures (fully decoupled from biology) in real EEG.Significance.The significance of our findings is that many existing works may be reporting results based on this confound and that future work should adhere to stricter requirements in mitigating this confound. The problematic, but commonly accepted approach in the literature for seizure prediction labelling is potentially preventing real advances in developing solutions for these sufferers. By adhering to the guidelines in this paper future work in machine learning seizure prediction is more likely to be clinically relevant.

Unsupervised EEG preictal interval identification in patients with drug-resistant epilepsy

Typical seizure prediction models aim at discriminating interictal brain activity from pre-seizure electrographic patterns. Given the lack of a preictal clinical definition, a fixed interval is widely used to develop these models. Recent studies reporting preictal interval selection among a range of fixed intervals show inter- and intra-patient preictal interval variability, possibly reflecting the heterogeneity of the seizure generation process. Obtaining accurate labels of the preictal interval can be used to train supervised prediction models and, hence, avoid setting a fixed preictal interval for all seizures within the same patient. Unsupervised learning methods hold great promise for exploring preictal alterations on a seizure-specific scale. Multivariate and univariate linear and nonlinear features were extracted from scalp electroencephalography (EEG) signals collected from 41 patients with drug-resistant epilepsy undergoing presurgical monitoring. Nonlinear dimensionality reduction was performed for each group of features and each of the 226 seizures. We applied different clustering methods in searching for preictal clusters located until 2 h before the seizure onset. We identified preictal patterns in 90% of patients and 51% of the visually inspected seizures. The preictal clusters manifested a seizure-specific profile with varying duration (22.9 ± 21.0 min) and starting time before seizure onset (47.6 ± 27.3 min). Searching for preictal patterns on the EEG trace using unsupervised methods showed that it is possible to identify seizure-specific preictal signatures for some patients and some seizures within the same patient.

Prediction of the COVID-19 infectivity and the sustainable impact on public health under deep learning algorithm

The aim is to explore the development trend of COVID-19 (Corona Virus Disease 2019) and predict the infectivity of 2019-nCoV (2019 Novel Coronavirus), as well as its impact on public health. First, the existing data are analyzed through data pre-processing to extract useful feature factors. Then, the LSTM (Long-Short Term Memory) prediction model in the deep learning algorithm is used to predict the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country, respectively. Meanwhile, the impact of intervention time changes on the epidemic situation is compared. The results show that the prediction results are almost consistent with the actual values. Specifically, Hubei Province abolishes quarantine restrictions after the Spring Festival holiday, and the first COVID-19 peak is reached in late February, while the second COVID-19 peak has been reached in early March. Finally, the cumulative number of diagnoses reaches 85,000 cases, with an increase of 15,000 cases compared with the nationwide cases outside Hubei under the continuous implementation of prevention and control measures. Under the prediction of the proposed LSTM model, if the nationwide implementation of prevention and control interventions is postponed by 5 days, the epidemic will peak in early March, and the cumulative number of diagnoses will be about 200,000; and if the intervention measures are implemented five days earlier, the epidemic will peak in mid-February, with a cumulative number of diagnoses of approximately 40,000. Meanwhile, the proposed LSTM model predicts the RMSE values of the epidemic situation in Hubei Province, outside Hubei nationwide, and the whole country as 34.63, 75.42, and 50.27, respectively. Under model comparison analysis, the prediction error of the proposed LSTM model is small and has better applicability over similar algorithms. The results show that the LSTM model is effective and has high performance in infectious disease prediction, and the research results can provide scientific and effective references for subsequent related research.

A Feature Extraction Method for Seizure Detection Based on Multi-Site Synchronous Changes and Edge Detection Algorithm

Automatic detection of epileptic seizures is important in epilepsy control and treatment, and specific feature extraction assists in accurate detection. We developed a feature extraction method for seizure detection based on multi-site synchronous changes and an edge detection algorithm. We investigated five chronic temporal lobe epilepsy rats with 8- and 12-channel detection sites in the hippocampus and limbic system. Multi-site synchronous changes were selected as a specific feature and implemented as a seizure detection method. For preprocessing, we used magnitude-squared coherence maps and Canny edge detection algorithm to find the frequency band with the most significant change in synchronization and the important channel pairs. In detection, we used the maximal cross-correlation coefficient as an indicator of synchronization and the correlation coefficient curves' average value and standard deviation as two detection features. The method achieved high performance, with an average 96.60% detection rate, 2.63/h false alarm rate, and 1.25 s detection delay. The experimental results show that synchronization is an appropriate feature for seizure detection. The magnitude-squared coherence map can assist in selecting a specific frequency band and channel pairs to enhance the detection result. We found that individuals have a specific frequency band that reflects the most significant synchronization changes, and our method can individually adjust parameters and has good detection performance.

Seizure forecasting using machine learning models trained by seizure diaries

Objectives.People with refractory epilepsy are overwhelmed by the uncertainty of their next seizures. Accurate prediction of future seizures could greatly improve the quality of life for these patients. New evidence suggests that seizure occurrences can have cyclical patterns for some patients. Even though these cyclicalities are not intuitive, they can be identified by machine learning (ML), to identify patients with predictable vs unpredictable seizure patterns.Approach.Self-reported seizure logs of 153 patients from the Human Epilepsy Project with more than three reported seizures (totaling 8337 seizures) were used to obtain inter-seizure interval time-series for training and evaluation of the forecasting models. Two classes of prediction methods were studied: (1) statistical approaches using Bayesian fusion of population-wise and individual-wise seizure patterns; and (2) ML-based algorithms including least squares, least absolute shrinkage and selection operator, support vector machine (SVM) regression, and long short-term memory regression. Leave-one-person-out cross-validation was used for training and evaluation, by training on seizure diaries of all except one subject and testing on the left-out subject.Main results.The leading forecasting models were the SVM regression and a statistical model that combined the median of population-wise seizure time-intervals with a test subject's prior seizure intervals. SVM was able to forecast 50%, 70%, 81%, 84%, and 87% of seizures of unseen subjects within 0, 1, 2, 3 to 4 d of mean absolute forecasting error, respectively. The subject-wise performances show that patients with more frequent seizures were generally better predicted.Significance.ML models can leverage non-random patterns within self-reported seizure diaries to forecast future seizures. While diary-based seizure forecasting alone is only one of many aspects of clinical care of patients with epilepsy, studying the level of predictability across seizures and patients paves the path towards a better understanding of predictable vs unpredictable seizures on individualized and population-wise bases.

An Explainable Statistical Method for Seizure Prediction Using Brain Functional Connectivity from EEG

Background. Epilepsy is a group of chronic neurological disorders characterized by recurrent and abrupt seizures. The accurate prediction of seizures can reduce the burdens of this disorder. Now, existing studies use brain network features to classify patients’ preictal or interictal states, enabling seizure prediction. However, most predicting methods are based on deep learning techniques, which have weak interpretability and high computational complexity. To address these issues, in this study, we proposed a novel two-stage statistical method that is interpretable and easy to compute. Methods. We used two datasets to evaluate the performance of the proposed method, including the well-known public dataset CHB-MIT. In the first stage, we estimated the dynamic brain functional connectivity network for each epoch. Then, in the second stage, we used the derived network predictor for seizure prediction. Results. We illustrated the results of our method in seizure prediction in two datasets separately. For the FH-PKU dataset, our approach achieved an AUC value of 0.963, a prediction sensitivity of 93.1%, and a false discovery rate of 7.7%. For the CHB-MIT dataset, our approach achieved an AUC value of 0.940, a prediction sensitivity of 93.0%, and a false discovery rate of 11.1%, outperforming existing state-of-the-art methods. Significance. This study proposed an explainable statistical method, which can estimate the brain network using the scalp EEG method and use the net-work predictor to predict epileptic seizures. Availability and Implementation. R Source code is available at https://github.com/HaoChen1994/Seizure-Prediction.

DSCNN-LSTMs: A Lightweight and Efficient Model for Epilepsy Recognition

Epilepsy is the second most common disease of the nervous system. Because of its high disability rate and the long course of the disease, it is a worldwide medical problem and social public health problem. Therefore, the timely detection and treatment of epilepsy are very important. Currently, medical professionals use their own diagnostic experience to identify seizures by visual inspection of the electroencephalogram (EEG). Not only does it require a lot of time and effort, but the process is also very cumbersome. Machine learning-based methods have recently been proposed for epilepsy detection, which can help clinicians make rapid and correct diagnoses. However, these methods often require extracting the features of EEG signals before using the data. In addition, the selection of features often requires domain knowledge, and feature types also have a significant impact on the performance of the classifier. In this paper, a one-dimensional depthwise separable convolutional neural network and long short-term memory networks (1D DSCNN-LSTMs) model is proposed to identify epileptic seizures by autonomously extracting the features of raw EEG. On the UCI dataset, the performance of the proposed 1D DSCNN-LSTMs model is verified by cross-validation and time complexity comparison. Compared with other previous models, the experimental results show that the highest recognition rates of binary and quintuple classification are 99.57% and 81.30%, respectively. It can be concluded that the 1D DSCNN-LSTMs model proposed in this paper is an effective method to identify seizures based on EEG signals.

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.

The performance evaluation of the state-of-the-art EEG-based seizure prediction models

The recurrent and unpredictable nature of seizures can lead to unintentional injuries and even death. The rapid development of electroencephalogram (EEG) and Artificial Intelligence (AI) technologies has made it possible to predict seizures in real-time through brain-machine interfaces (BCI), allowing advanced intervention. To date, there is still much room for improvement in predictive seizure models constructed by EEG using machine learning (ML) and deep learning (DL). But, the most critical issue is how to improve the performance and generalization of the model, which involves some confusing conceptual and methodological issues. This review focuses on analyzing several factors affecting the performance of seizure prediction models, focusing on the aspects of post-processing, seizure occurrence period (SOP), seizure prediction horizon (SPH), and algorithms. Furthermore, this study presents some new directions and suggestions for building high-performance prediction models in the future. We aimed to clarify the concept for future research in related fields and improve the performance of prediction models to provide a theoretical basis for future applications of wearable seizure detection devices.

A multi-frame network model for predicting seizure based on sEEG and iEEG data

Introduction

Analysis and prediction of seizures by processing the EEG signals could assist doctors in accurate diagnosis and improve the quality of the patient's life with epilepsy. Nowadays, seizure prediction models based on deep learning have become one of the most popular topics in seizure studies, and many models have been presented. However, the prediction results are strongly related to the various complicated pre-processing strategies of models, and cannot be directly applied to raw data in real-time applications. Moreover, due to the inherent deficiencies in single-frame models and the non-stationary nature of EEG signals, the generalization ability of the existing model frameworks is generally poor.

Methods

Therefore, we proposed an end-to-end seizure prediction model in this paper, where we designed a multi-frame network for automatic feature extraction and classification. Instance and sequence-based frames are proposed in our approach, which can help us simultaneously extract features of different modes for further classification. Moreover, complicated pre-processing steps are not included in our model, and the novel frames can be directly applied to the raw data. It should be noted that the approaches proposed in the paper can be easily used as the general model which has been validated and compared with existing model frames.

Results

The experimental results showed that the multi-frame network proposed in this paper was superior to the existing model frame in accuracy, sensitivity, specificity, F1-score, and AUC in the classification performance of EEG signals.

Discussion

Our results provided a new research idea for this field. Researchers can further integrate the idea of the multi-frame network into the state-of-the-art single-frame seizure prediction models and then achieve better results.

Spatio-Temporal-Spectral Hierarchical Graph Convolutional Network With Semisupervised Active Learning for Patient-Specific Seizure Prediction

Graph theory analysis using electroencephalogram (EEG) signals is currently an advanced technique for seizure prediction. Recent deep learning approaches, which fail to fully explore both the characterizations in EEGs themselves and correlations among different electrodes simultaneously, generally neglect the spatial or temporal dependencies in an epileptic brain and, thus, produce suboptimal seizure prediction performance consequently. To tackle this issue, in this article, a patient-specific EEG seizure predictor is proposed by using a novel spatio-temporal-spectral hierarchical graph convolutional network with an active preictal interval learning scheme (STS-HGCN-AL). Specifically, since the epileptic activities in different brain regions may be of different frequencies, the proposed STS-HGCN-AL framework first infers a hierarchical graph to concurrently characterize an epileptic cortex under different rhythms, whose temporal dependencies and spatial couplings are extracted by a spectral-temporal convolutional neural network and a variant self-gating mechanism, respectively. Critical intrarhythm spatiotemporal properties are then captured and integrated jointly and further mapped to the final recognition results by using a hierarchical graph convolutional network. Particularly, since the preictal transition may be diverse from seconds to hours prior to a seizure onset among different patients, our STS-HGCN-AL scheme estimates an optimal preictal interval patient dependently via a semisupervised active learning strategy, which further enhances the robustness of the proposed patient-specific EEG seizure predictor. Competitive experimental results validate the efficacy of the proposed method in extracting critical preictal biomarkers, indicating its promising abilities in automatic seizure prediction.

A general sample-weighted framework for epileptic seizure prediction

OBJECTIVE

Effective epileptic seizure prediction can make the patients know the onset of the seizure in advance to take timely preventive measures. Many studies based on machine learning methods have been proposed to tackle this problem and achieve significant progress in recent years. However, most studies treat each EEG training sample's contribution to the model as equal, while different samples have different predictive effects on epileptic seizures (e.g., preictal samples from different times). To this end, in this paper, we propose a general sample-weighted framework for patient-specific epileptic seizure prediction.

METHODS

Specifically, we define the mapping from the sample weights of training sets to the performance of the validation sets as the fitness function to be optimized. Then, the genetic algorithm is employed to optimize this fitness function and obtain the optimal sample weights. Finally, we obtain the final model by using the training sets with optimized sample weights.

RESULTS

To evaluate the effectiveness of our framework, we conduct extensive experiments on both traditional machine learning methods and prevalent deep learning methods. Our framework can significantly improve performance based on these methods. Among them, our framework based on Transformer achieves an average sensitivity of 94.6%, an average false prediction rate of 0.06/h, and an average AUC of 0.939 in 12 pediatric patients from the CHB-MIT database with the leave-one-out method, which outperforms the state-of-the-art methods.

CONCLUSION

This study provides new insights into the field of epileptic seizure prediction by considering the discrepancies between EEG samples. Moreover, we develop a general sample-weighted framework, which applies to almost all classical classification methods and can significantly improve performance based on these methods.

Epileptic seizure prediction using successive variational mode decomposition and transformers deep learning network

As one of the most common neurological disorders, epilepsy causes great physical and psychological damage to the patients. The long-term recurrent and unprovoked seizures make the prediction necessary. In this paper, a novel approach for epileptic seizure prediction based on successive variational mode decomposition (SVMD) and transformers is proposed. SVMD is extended to multidimensional form for time-frequency analysis of multi-channel signals. It could adaptively extract common band-limited intrinsic modes among all channels on different time scales by solving a variational optimization problem. In the proposed seizure prediction method, data are first decomposed into multiple modes on different time scales by multivariate SVMD, and then, irrelevant modes are removed for preprocessing. Finally, power spectrum of denoised data is input to a pre-trained bidirectional encoder representations from transformers (BERTs) for prediction. The BERT could identify the mode information related to epileptic seizures in time-frequency domain. It shows fair prediction performance on an intracranial EEG dataset with the average sensitivity of 0.86 and FPR of 0.18/h.

EEG-Based Person Identification during Escalating Cognitive Load

With the development of human society, there is an increasing importance for reliable person identification and authentication to protect a person's material and intellectual property. Person identification based on brain signals has captured substantial attention in recent years. These signals are characterized by original patterns for a specific person and are capable of providing security and privacy of an individual in biometric identification. This study presents a biometric identification method based on a novel paradigm with accrual cognitive brain load from relaxing with eyes closed to the end of a serious game, which includes three levels with increasing difficulty. The used database contains EEG data from 21 different subjects. Specific patterns of EEG signals are recognized in the time domain and classified using a 1D Convolutional Neural Network proposed in the MATLAB environment. The ability of person identification based on individual tasks corresponding to a given degree of load and their fusion are examined by 5-fold cross-validation. Final accuracies of more than 99% and 98% were achieved for individual tasks and task fusion, respectively. The reduction of EEG channels is also investigated. The results imply that this approach is suitable to real applications.

Performance analysis of remote photoplethysmography deep filtering using long short-term memory neural network

BACKGROUND

Remote photoplethysmography (rPPG) is a technique developed to estimate heart rate using standard video cameras and ambient light. Due to the multiple sources of noise that deteriorate the quality of the signal, conventional filters such as the bandpass and wavelet-based filters are commonly used. However, after using conventional filters, some alterations remain, but interestingly an experienced eye can easily identify them.

RESULTS

We studied a long short-term memory (LSTM) network in the rPPG filtering task to identify these alterations using many-to-one and many-to-many approaches. We used three public databases in intra-dataset and cross-dataset scenarios, along with different protocols to analyze the performance of the method. We demonstrate how the network can be easily trained with a set of 90 signals totaling around 45 min. On the other hand, we show the stability of the LSTM performance with six state-of-the-art rPPG methods.

CONCLUSIONS

This study demonstrates the superiority of the LSTM-based filter experimentally compared with conventional filters in an intra-dataset scenario. For example, we obtain on the VIPL database an MAE of 3.9 bpm, whereas conventional filtering improves performance on the same dataset from 10.3 bpm to 7.7 bpm. The cross-dataset approach presents a dependence in the network related to the average signal-to-noise ratio on the rPPG signals, where the closest signal-to-noise ratio values in the training and testing set the better. Moreover, it was demonstrated that a relatively small amount of data are sufficient to successfully train the network and outperform the results obtained by classical filters. More precisely, we have shown that about 45 min of rPPG signal could be sufficient to train an effective LSTM deep-filter.

Cross-subject emotion recognition using visibility graph and genetic algorithm-based convolution neural network

An efficient emotion recognition model is an important research branch in electroencephalogram (EEG)-based brain-computer interfaces. However, the input of the emotion recognition model is often a whole set of EEG channels obtained by electrodes placed on subjects. The unnecessary information produced by redundant channels affects the recognition rate and depletes computing resources, thereby hindering the practical applications of emotion recognition. In this work, we aim to optimize the input of EEG channels using a visibility graph (VG) and genetic algorithm-based convolutional neural network (GA-CNN). First, we design an experiment to evoke three types of emotion states using movies and collect the multi-channel EEG signals of each subject under different emotion states. Then, we construct VGs for each EEG channel and derive nonlinear features representing each EEG channel. We employ the genetic algorithm (GA) to find the optimal subset of EEG channels for emotion recognition and use the recognition results of the CNN as fitness values. The experimental results show that the recognition performance of the proposed method using a subset of EEG channels is superior to that of the CNN using all channels for each subject. Last, based on the subset of EEG channels searched by the GA-CNN, we perform cross-subject emotion recognition tasks employing leave-one-subject-out cross-validation. These results demonstrate the effectiveness of the proposed method in recognizing emotion states using fewer EEG channels and further enrich the methods of EEG classification using nonlinear features.

Effective Evaluation of Medical Images Using Artificial Intelligence Techniques

This work is implemented for the management of patients with epilepsy, and methods based on electroencephalography (EEG) analysis have been proposed for the timely prediction of its occurrence. The proposed system is used for crisis detection and prediction system; it is useful for both patients and medical staff to know their status easily and more accurately. In the treatment of Parkinson's disease, the affected patients with Parkinson's disease can assess the prognostic risk factors, and the symptoms are evaluated to predict rapid progression in the early stages after diagnosis. The presented seizure prediction system introduces deep learning algorithms into EEG score analysis. This proposed work long short-term memory (LSTM) network model is mainly implemented for the identification and classification of qualitative patterns in the EEG of patients. While compared with other techniques like deep learning models such as convolutional neural networks (CNNs) and traditional machine learning algorithms, the proposed LSTM model plays a significant role in predicting impending crises over 4 different qualifying intervals from 10 minutes to 1.5 hours with very few wrong predictions.

Efficient graph convolutional networks for seizure prediction using scalp EEG

Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.

A Hybrid Expert System for Individualized Quantification of Electrical Status Epilepticus During Sleep Using Biogeography-Based Optimization

Electrical status epilepticus during sleep (ESES) is an epileptic encephalopathy in children with complex clinical manifestations. It is accompanied by specific electroencephalography (EEG) patterns of continuous spike and slow-waves. Quantifying such EEG patterns is critical to the diagnosis of ESES. While most of the existing automatic ESES quantification systems ignore the morphological variations of the signal as well as the individual variability among subjects. To address these issues, this paper presents a hybrid expert system that dedicates to mimicking the decision-making process of clinicians in ESES quantification by taking the morphological variations, individual variability, and medical knowledge into consideration. The proposed hybrid system not only offers a general scheme that could propel a semi-auto morphology analysis-based expert decision model to a fully automated ESES quantification with biogeography-based optimization (BBO), but also proposes a more precise individualized quantification system to involve the personalized characteristics by adopting an individualized parameters-selection framework. The feasibility and reliability of the proposed method are evaluated on a clinical dataset collected from twenty subjects at Children's Hospital of Fudan University, Shanghai, China. The estimation error for the individualized quantitative descriptor ESES is 0-4.32% and the average estimation error is 0.95% for all subjects. Experimental results show the presented system outperforms existing works and the individualized system significantly improves the performance of ESES quantification. The favorable results indicate that the proposed hybrid expert system for automatic ESES quantification is promising to support the diagnosis of ESES.

Effect of time windows in LSTM networks for EEG-based BCIs

People with impaired motor function could be helped by an effective brain–computer interface (BCI) based on a real-time electroencephalogram (EEG) and artificial intelligence algorithms. However, current methodologies for interpreting patient instructions from an EEG are not accurate enough to be completely safe in a real-world situation , where a poor decision would place their physical integrity at risk, such as when traveling in an electric wheelchair in a city. For various reasons, such as the low signal-to-noise ratio of portable EEGs or the effects of signal contamination (disturbances due to user movement, temporal variation of the features of EEG signals, etc.), a long short-term memory network (LSTM) (a type of recurrent neural network) that is able to learn data flow patterns from EEG signals could improve the classification of the actions taken by the user. In this paper, the effectiveness of using an LSTM with a low-cost wireless EEG device in real time is tested, and the time window that maximizes its classification accuracy is studied. The goal is to be able to implement it in the BCI of a smart wheelchair with a simple coded command protocol, such as opening or closing the eyes, which could be executed by patients with reduced mobility. Results show a higher resolution of the LSTM with an accuracy range between 77.61 and 92.14% compared to traditional classifiers (59.71%), and an optimal time window of around 7 s for the task done by users in this work. In addition, tests in real-life contexts show that a trade-off between accuracy and response times is necessary to ensure detection.

Multi-Channel Vision Transformer for Epileptic Seizure Prediction

Epilepsy is a neurological disorder that causes recurrent seizures and sometimes loss of awareness. Around 30% of epileptic patients continue to have seizures despite taking anti-seizure medication. The ability to predict the future occurrence of seizures would enable the patients to take precautions against probable injuries and administer timely treatment to abort or control impending seizures. In this study, we introduce a Transformer-based approach called Multi-channel Vision Transformer (MViT) for automated and simultaneous learning of the spatio-temporal-spectral features in multi-channel EEG data. Continuous wavelet transform, a simple yet efficient pre-processing approach, is first used for turning the time-series EEG signals into image-like time-frequency representations named Scalograms. Each scalogram is split into a sequence of fixed-size non-overlapping patches, which are then fed as inputs to the MViT for EEG classification. Extensive experiments on three benchmark EEG datasets demonstrate the superiority of the proposed MViT algorithm over the state-of-the-art seizure prediction methods, achieving an average prediction sensitivity of 99.80% for surface EEG and 90.28-91.15% for invasive EEG data.

Vowel speech recognition from rat electroencephalography using long short-term memory neural network

Over the years, considerable research has been conducted to investigate the mechanisms of speech perception and recognition. Electroencephalography (EEG) is a powerful tool for identifying brain activity; therefore, it has been widely used to determine the neural basis of speech recognition. In particular, for the classification of speech recognition, deep learning-based approaches are in the spotlight because they can automatically learn and extract representative features through end-to-end learning. This study aimed to identify particular components that are potentially related to phoneme representation in the rat brain and to discriminate brain activity for each vowel stimulus on a single-trial basis using a bidirectional long short-term memory (BiLSTM) network and classical machine learning methods. Nineteen male Sprague-Dawley rats subjected to microelectrode implantation surgery to record EEG signals from the bilateral anterior auditory fields were used. Five different vowel speech stimuli were chosen, /a/, /e/, /i/, /o/, and /u/, which have highly different formant frequencies. EEG recorded under randomly given vowel stimuli was minimally preprocessed and normalized by a z-score transformation to be used as input for the classification of speech recognition. The BiLSTM network showed the best performance among the classifiers by achieving an overall accuracy, f1-score, and Cohen's κ values of 75.18%, 0.75, and 0.68, respectively, using a 10-fold cross-validation approach. These results indicate that LSTM layers can effectively model sequential data, such as EEG; hence, informative features can be derived through BiLSTM trained with end-to-end learning without any additional hand-crafted feature extraction methods.

CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition

Speech is a complex mechanism allowing us to communicate our needs, desires and thoughts. In some cases of neural dysfunctions, this ability is highly affected, which makes everyday life activities that require communication a challenge. This paper studies different parameters of an intelligent imaginary speech recognition system to obtain the best performance according to the developed method that can be applied to a low-cost system with limited resources. In developing the system, we used signals from the Kara One database containing recordings acquired for seven phonemes and four words. We used in the feature extraction stage a method based on covariance in the frequency domain that performed better compared to the other time-domain methods. Further, we observed the system performance when using different window lengths for the input signal (0.25 s, 0.5 s and 1 s) to highlight the importance of the short-term analysis of the signals for imaginary speech. The final goal being the development of a low-cost system, we studied several architectures of convolutional neural networks (CNN) and showed that a more complex architecture does not necessarily lead to better results. Our study was conducted on eight different subjects, and it is meant to be a subject’s shared system. The best performance reported in this paper is up to 37% accuracy for all 11 different phonemes and words when using cross-covariance computed over the signal spectrum of a 0.25 s window and a CNN containing two convolutional layers with 64 and 128 filters connected to a dense layer with 64 neurons. The final system qualifies as a low-cost system using limited resources for decision-making and having a running time of 1.8 ms tested on an AMD Ryzen 7 4800HS CPU.