Automated detection of abnormalities from an EEG recording of epilepsy patients with a compact convolutional neural network

STaRNet: A spatio-temporal and Riemannian network for high-performance motor imagery decoding

Brain-computer interfaces (BCIs), representing a transformative form of human-computer interaction, empower users to interact directly with external environments through brain signals. In response to the demands for high accuracy, robustness, and end-to-end capabilities within BCIs based on motor imagery (MI), this paper introduces STaRNet, a novel model that integrates multi-scale spatio-temporal convolutional neural networks (CNNs) with Riemannian geometry. Initially, STaRNet integrates a multi-scale spatio-temporal feature extraction module that captures both global and local features, facilitating the construction of Riemannian manifolds from these comprehensive spatio-temporal features. Subsequently, a matrix logarithm operation transforms the manifold-based features into the tangent space, followed by a dense layer for classification. Without preprocessing, STaRNet surpasses state-of-the-art (SOTA) models by achieving an average decoding accuracy of 83.29% and a kappa value of 0.777 on the BCI Competition IV 2a dataset, and 95.45% accuracy with a kappa value of 0.939 on the High Gamma Dataset. Additionally, a comparative analysis between STaRNet and several SOTA models, focusing on the most challenging subjects from both datasets, highlights exceptional robustness of STaRNet. Finally, the visualizations of learned frequency bands demonstrate that temporal convolutions have learned MI-related frequency bands, and the t-SNE analyses of features across multiple layers of STaRNet exhibit strong feature extraction capabilities. We believe that the accurate, robust, and end-to-end capabilities of the STaRNet will facilitate the advancement of BCIs.

Automatic rehabilitation exercise task assessment of stroke patients based on wearable sensors with a lightweight multichannel 1D-CNN model

Approximately 75% of stroke survivors have movement dysfunction. Rehabilitation exercises are capable of improving physical coordination. They are mostly conducted in the home environment without guidance from therapists. It is impossible to provide timely feedback on exercises without suitable devices or therapists. Human action quality assessment in the home setting is a challenging topic for current research. In this paper, a low-cost HREA system in which wearable sensors are used to collect upper limb exercise data and a multichannel 1D-CNN framework is used to automatically assess action quality. The proposed 1D-CNN model is first pretrained on the UCI-HAR dataset, and it achieves a performance of 91.96%. Then, five typical actions were selected from the Fugl-Meyer Assessment Scale for the experiment, wearable sensors were used to collect the participants' exercise data, and experienced therapists were employed to assess participants' exercise at the same time. Following the above process, a dataset was built based on the Fugl-Meyer scale. Based on the 1D-CNN model, a multichannel 1D-CNN model was built, and the model using the Naive Bayes fusion had the best performance (precision: 97.26%, recall: 97.22%, F1-score: 97.23%) on the dataset. This shows that the HREA system provides accurate and timely assessment, which can provide real-time feedback for stroke survivors' home rehabilitation.

Multiclass Classification of Visual Electroencephalogram Based on Channel Selection, Minimum Norm Estimation Algorithm, and Deep Network Architectures

This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K).

BrainGridNet: A two-branch depthwise CNN for decoding EEG-based multi-class motor imagery

Brain-computer interfaces (BCIs) based on motor imagery (MI) enable the disabled to interact with the world through brain signals. To meet demands of real-time, stable, and diverse interactions, it is crucial to develop lightweight networks that can accurately and reliably decode multi-class MI tasks. In this paper, we introduce BrainGridNet, a convolutional neural network (CNN) framework that integrates two intersecting depthwise CNN branches with 3D electroencephalography (EEG) data to decode a five-class MI task. The BrainGridNet attains competitive results in both the time and frequency domains, with superior performance in the frequency domain. As a result, an accuracy of 80.26 percent and a kappa value of 0.753 are achieved by BrainGridNet, surpassing the state-of-the-art (SOTA) model. Additionally, BrainGridNet shows optimal computational efficiency, excels in decoding the most challenging subject, and maintains robust accuracy despite the random loss of 16 electrode signals. Finally, the visualizations demonstrate that BrainGridNet learns discriminative features and identifies critical brain regions and frequency bands corresponding to each MI class. The convergence of BrainGridNet's strong feature extraction capability, high decoding accuracy, steady decoding efficacy, and low computational costs renders it an appealing choice for facilitating the development of BCIs.

Nonlinear and chaos features over EMD/VMD decomposition methods for ictal EEG signals detection

The detection and identification of epileptic seizures attracted considerable relevance for the neurophysiologists. In order to accomplish the detection of epileptic seizures or equivalently ictal EEG states, this paper proposes the use of nonlinear and chaos features not computed over the raw EEG signals as it was commonly experienced, but instead over intrinsic mode functions (IMFs) extracted subsequently to the application of newly time-frequency signal decomposition methods on the basis of empirical mode decomposition (EMD) and variational mode decomposition (VMD) methods. The first step within the proposed methodology is to excerpt the various components of the IMFs by EMD and VMD decomposition methods on time EEG segments. The Hjorth parameters, the Hurst exponent, the Recurrence Quantification Analysis (RQA), the detrended fluctuation analysis (DFA), the Largest Lyapunov Exponent (LLE), The Higuchi and Katz fractal dimensions (HFD and KFD), seven nonlinear and chaos features computed over the IMFs were investigated and their classification performances evaluated using the k-nearest neighbor (KNN) and the multilayer perceptron neural network (MLPNN) classifiers. Furthermore, the combination of the best nonlinear features has also been examined in terms of sensitivity, specificity and overall classification accuracy. The publicly available Bonn EEG dataset has been has been employed to validate the efficiency of the proposed method for detecting ictal EEG signals from normal or interictal EEG segments. Among the several experiments involved in the current study, the ultimate results establish that the overall classification accuracy can achieve 100%, 99.45%, 99.8%, 99.8%, 98.6% and 99.1% for six different epileptic seizure detection case problems studied, confirming the ability of the proposed methodology in helping the clinic practitioners in the epilepsy detection care units to classify seizure events with a great confidence.

Motor Imagery Multi-Tasks Classification for BCIs Using the NVIDIA Jetson TX2 Board and the EEGNet Network

Nowadays, Brain-Computer Interfaces (BCIs) still captivate large interest because of multiple advantages offered in numerous domains, explicitly assisting people with motor disabilities in communicating with the surrounding environment. However, challenges of portability, instantaneous processing time, and accurate data processing remain for numerous BCI system setups. This work implements an embedded multi-tasks classifier based on motor imagery using the EEGNet network integrated into the NVIDIA Jetson TX2 card. Therefore, two strategies are developed to select the most discriminant channels. The former uses the accuracy based-classifier criterion, while the latter evaluates electrode mutual information to form discriminant channel subsets. Next, the EEGNet network is implemented to classify discriminant channel signals. Additionally, a cyclic learning algorithm is implemented at the software level to accelerate the model learning convergence and fully profit from the NJT2 hardware resources. Finally, motor imagery Electroencephalogram (EEG) signals provided by HaLT's public benchmark were used, in addition to the k-fold cross-validation method. Average accuracies of 83.7% and 81.3% were achieved by classifying EEG signals per subject and motor imagery task, respectively. Each task was processed with an average latency of 48.7 ms. This framework offers an alternative for online EEG-BCI systems' requirements, dealing with short processing times and reliable classification accuracy.

Satelight: Self-attention-based model for epileptic spike detection from multi-electrode EEG

OBJECTIVE

Because of the lack of highly skilled experts, automated technologies that support electroencephalogram (EEG)-based in epilepsy diagnosis are advancing. Deep convolutional neural network-based models have been used successfully for detecting epileptic spikes, one of the biomarkers, from EEG. However, a sizeable number of supervised EEG records are required for training.

APPROACH

This study introduces the Satelight model, which uses the self-attention (SA) mechanism. The model was trained using a clinical EEG dataset labeled by  ve specialists, including 16,008 epileptic spikes and 15,478 artifacts from 50 children. The SA mechanism is expected to reduce the number of parameters and efficiently extract features from a small amount of EEG data. To validate the effectiveness, we compared various spike detection approaches with the clinical EEG data.

MAIN RESULTS

The experimental results showed that the proposed method detected epileptic spikes more effectively than other models (accuracy = 0:876 and false positive rate = 0:133).

SIGNIFICANCE

The proposed model had only one-tenth the number of parameters as the other effective model, despite having such a high detection performance. Further exploration of the hidden parameters revealed that the model automatically attended to the EEG's characteristic waveform locations of interest.

Improving Motor Imagery EEG Classification Based on Channel Selection Using a Deep Learning Architecture

Recently, motor imagery EEG signals have been widely applied in Brain–Computer Interfaces (BCI). These signals are typically observed in the first motor cortex of the brain, resulting from the imagination of body limb movements. For non-invasive BCI systems, it is not apparent how to locate the electrodes, optimizing the accuracy for a given task. This study proposes a comparative analysis of channel signals exploiting the Deep Learning (DL) technique and a public dataset to locate the most discriminant channels. EEG channels are usually selected based on the function and nomenclature of electrode location from international standards. Instead, the most suitable configuration for a given paradigm must be determined by analyzing the proper selection of the channels. Therefore, an EEGNet network was implemented to classify signals from different channel location using the accuracy metric. Achieved results were then contrasted with results from the state-of-the-art. As a result, the proposed method improved BCI classification accuracy.

Intelligent Extraction of Salient Feature From Electroencephalogram Using Redundant Discrete Wavelet Transform

At present, electroencephalogram (EEG) signals play an irreplaceable role in the diagnosis and treatment of human diseases and medical research. EEG signals need to be processed in order to reduce the adverse effects of irrelevant physiological process interference and measurement noise. Wavelet transform (WT) can provide a time-frequency representation of a dynamic process, and it has been widely utilized in salient feature analysis of EEG. In this paper, we investigate the problem of translation variability (TV) in discrete wavelet transform (DWT), which causes degradation of time-frequency localization. It will be verified through numerical simulations that TV is caused by downsampling operations in decomposition process of DWT. The presence of TV may cause severe distortions of features in wavelet subspaces. However, this phenomenon has not attracted much attention in the scientific community. Redundant discrete wavelet transform (RDWT) is derived by eliminating the downsampling operation. RDWT enjoys the attractive merit of translation invariance. RDWT shares the same time-frequency pattern with that of DWT. The discrete delta impulse function is used to test the time-frequency response of DWT and RDWT in wavelet subspaces. The results show that DWT is very sensitive to the translation of delta impulse function, while RDWT keeps the decomposition results unchanged. This conclusion has also been verified again in decomposition of actual EEG signals. In conclusion, to avoid possible distortions of features caused by translation sensitivity in DWT, we recommend the use of RDWT with more stable performance in BCI research and clinical applications.

Both Cross-Patient and Patient-Specific Seizure Detection Based on Self-Organizing Fuzzy Logic

Automatic epilepsy detection is of great significance for the diagnosis and treatment of patients. Most detection methods are based on patient-specific models and have achieved good results. However, in practice, new patients do not have their own previous EEG data and therefore cannot be initially diagnosed. If the EEG data of other patients can be used to achieve cross-patient detection, and cross-patient and patient-specific experiments can be combined at the same time, this method will be more widely used. In this work, an EEG classification model based on a self-organizing fuzzy logic (SOF) classifier is proposed for both cross-patient and patient-specific seizure detection. After preprocessing, the features of the original EEG signal are extracted and sent to the SOF classifier. This classification model is free from predefined parameters or a prior assumption regarding the EEG data generation model and only stores the key meta-parameters in memory. Therefore, it is very suitable for large-scale EEG signals in cross-patient detection. Selecting different granularity and classification distance in two different experiments after post-processing will achieve the best results. Experiments were conducted using a long-term continuous scalp EEG database and the [Formula: see text]-mean of cross-patient and patient-specific detection reached 83.35% and 92.04%, respectively. A comparison with other methods shows that there is greater performance and generalizability with this method.