Classification of EEG Using Adaptive SVM Classifier with CSP and Online Recursive Independent Component Analysis

Self-supervised motor imagery EEG recognition model based on 1-D MTCNN-LSTM network

Objective.Aiming for the research on the brain-computer interface (BCI), it is crucial to design a MI-EEG recognition model, possessing a high classification accuracy and strong generalization ability, and not relying on a large number of labeled training samples.Approach.In this paper, we propose a self-supervised MI-EEG recognition method based on self-supervised learning with one-dimensional multi-task convolutional neural networks and long short-term memory (1-D MTCNN-LSTM). The model is divided into two stages: signal transform identification stage and pattern recognition stage. In the signal transform recognition phase, the signal transform dataset is recognized by the upstream 1-D MTCNN-LSTM network model. Subsequently, the backbone network from the signal transform identification phase is transferred to the pattern recognition phase. Then, it is fine-tuned using a trace amount of labeled data to finally obtain the motion recognition model.Main results.The upstream stage of this study achieves more than 95% recognition accuracy for EEG signal transforms, up to 100%. For MI-EEG pattern recognition, the model obtained recognition accuracies of 82.04% and 87.14% with F1 scores of 0.7856 and 0.839 on the datasets of BCIC-IV-2b and BCIC-IV-2a.Significance.The improved accuracy proves the superiority of the proposed method. It is prospected to be a method for accurate classification of MI-EEG in the BCI system.

Brain-Computer Interface: The HOL-SSA Decomposition and Two-Phase Classification on the HGD EEG Data

An efficient processing approach is essential for increasing identification accuracy since the electroencephalogram (EEG) signals produced by the Brain-Computer Interface (BCI) apparatus are nonlinear, nonstationary, and time-varying. The interpretation of scalp EEG recordings can be hampered by nonbrain contributions to electroencephalographic (EEG) signals, referred to as artifacts. Common disturbances in the capture of EEG signals include electrooculogram (EOG), electrocardiogram (ECG), electromyogram (EMG) and other artifacts, which have a significant impact on the extraction of meaningful information. This study suggests integrating the Singular Spectrum Analysis (SSA) and Independent Component Analysis (ICA) methods to preprocess the EEG data. The key objective of our research was to employ Higher-Order Linear-Moment-based SSA (HOL-SSA) to decompose EEG signals into multivariate components, followed by extracting source signals using Online Recursive ICA (ORICA). This approach effectively improves artifact rejection. Experimental results using the motor imagery High-Gamma Dataset validate our method's ability to identify and remove artifacts such as EOG, ECG, and EMG from EEG data, while preserving essential brain activity.

Classifying Unstable and Stable Walking Patterns Using Electroencephalography Signals and Machine Learning Algorithms

Analyzing unstable gait patterns from Electroencephalography (EEG) signals is vital to develop real-time brain-computer interface (BCI) systems to prevent falls and associated injuries. This study investigates the feasibility of classification algorithms to detect walking instability utilizing EEG signals. A 64-channel Brain Vision EEG system was used to acquire EEG signals from 13 healthy adults. Participants performed walking trials for four different stable and unstable conditions: (i) normal walking, (ii) normal walking with medial-lateral perturbation (MLP), (iii) normal walking with dual-tasking (Stroop), (iv) normal walking with center of mass visual feedback. Digital biomarkers were extracted using wavelet energy and entropies from the EEG signals. Algorithms like the ChronoNet, SVM, Random Forest, gradient boosting and recurrent neural networks (LSTM) could classify with 67 to 82% accuracy. The classification results show that it is possible to accurately classify different gait patterns (from stable to unstable) using EEG-based digital biomarkers. This study develops various machine-learning-based classification models using EEG datasets with potential applications in detecting unsteady gait neural signals and intervening by preventing falls and injuries.

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 Image Definition Assessment of Optoelectronic Tracking Equipment Based on the BRISQUE Algorithm with Gaussian Weights

Defocus is an important factor that causes image quality degradation of optoelectronic tracking equipment in the shooting range. In this paper, an improved blind/referenceless image spatial quality evaluator (BRISQUE) algorithm is formulated by using the image characteristic extraction technology to obtain a characteristic vector (CV). The CV consists of 36 characteristic values that can effectively reflect the defocusing condition of the corresponding image. The image is evaluated and scored subjectively by the human eyes. The subjective evaluation scores and CVs constitute a set of training data samples for the defocusing evaluation model. An image database that contains sufficiently many training samples is constructed. The training model is trained to obtain the support vector machine (SVM) model by using the regression function of the SVM. In the experiments, the BRISQUE algorithm is used to obtain the image feature vector. The method of establishing the image definition evaluation model via SVM is feasible and yields higher subjective and objective consistency.

Emergency Braking Evoked Brain Activities during Distracted Driving

Electroencephalogram (EEG) was used to analyze the mechanisms and differences in brain neural activity of drivers in visual, auditory, and cognitive distracted vs. normal driving emergency braking conditions. A pedestrian intrusion emergency braking stimulus module and three distraction subtasks were designed in a simulated experiment, and 30 subjects participated in the study. The common activated brain regions during emergency braking in different distracted driving states included the inferior temporal gyrus, associated with visual information processing and attention; the left dorsolateral superior frontal gyrus, related to cognitive decision-making; and the postcentral gyrus, supplementary motor area, and paracentral lobule associated with motor control and coordination. When performing emergency braking under different driving distraction states, the brain regions were activated in accordance with the need to process the specific distraction task. Furthermore, the extent and degree of activation of cognitive function-related prefrontal regions increased accordingly with the increasing task complexity. All distractions caused a lag in emergency braking reaction time, with 107.22, 67.15, and 126.38 ms for visual, auditory, and cognitive distractions, respectively. Auditory distraction had the least effect and cognitive distraction the greatest effect on the lag.