Support vector machines
Research Papers
EEG-Based Anxious States Classification Using Affective BCI-Based Closed Neurofeedback System
Purpose: Anxiety disorder is one of the psychiatric disorders that involves extreme fear or worry, which can change the balance of chemicals in the brain. To the best of our knowledge, the evaluation of anxiety state is still based on some subjective questionnaires and there is no objective standard assessment yet. Unlike other methods, our approach focuses on study the neural changes to identify and classify the anxiety state using electroencephalography (EEG) signals. Methods: We designed a closed neurofeedback experiment that contains three experimental stages to adjust subjects’ mental state. The EEG resting state signal was recorded from thirty-four subjects in the first and third stages while EEG-based mindfulness recording was recorded in the second stage. At the end of each stage, the subjects were asked to fill a Visual Analogue Scale (VAS). According to their VAS score, the subjects were classified into three groups: non-anxiety, moderate or severe anxiety groups. Results: After processing the EEG data of each group, support vector machine (SVM) classifiers were able to classify and identify two mental states (non-anxiety and anxiety) using the Power Spectral Density (PSD) as patterns. The highest classification accuracies using Gaussian kernel function and polynomial kernel function are 92.48 ± 1.20% and 88.60 ± 1.32%, respectively. The highest average of the classification accuracies for healthy subjects is 95.31 ± 1.97% and for anxiety subjects is 87.18 ± 3.51%. Conclusions: The results suggest that our proposed EEG neurofeedback-based classification approach is efficient for developing affective BCI system for detection and evaluation of anxiety disorder states.
View Full Paper →The Time-Robustness Analysis of Individual Identification Based on Resting-State EEG
An ongoing interest towards identification based on biosignals, such as electroencephalogram (EEG), magnetic resonance imaging (MRI), is growing in the past decades. Previous studies indicated that the inherent information about brain activity may be used to identify individual during resting-state of eyes open (REO) and eyes closed (REC). Electroencephalographic (EEG) records the data from the scalp, and it is believed that the noisy EEG signals can influence the accuracies of one experiment causing unreliable results. Therefore, the stability and time-robustness of inter-individual features can be investigated for the purpose of individual identification. In this work, we conducted three experiments with the time interval of at least 2 weeks, and used different types of measures (Power Spectral Density, Cross Spectrum, Channel Coherence and Phase Lags) to extract the individual features. The Pearson Correlation Coefficient (PCC) is calculated to measure the level of linear correlation for intra-individual, and Support Vector Machine (SVM) is used to obtain the related classification accuracy. Results show that the classification accuracies of four features were 85-100% for intra-experiment dataset, and were 80-100% for fusion experiments dataset. For inter-experiments classification of REO features, the optimized frequency range is 13-40 Hz for three features, Power Spectral Density, Channel Coherence and Cross Spectrum. For inter-experiments classification of REC, the optimized frequency range is 8-40 Hz for three features, Power Spectral Density, Channel Coherence and Cross Spectrum. The classification results of Phase Lags are much lower than the other three features. These results show the time-robustness of EEG, which can further use for individual identification system.
View Full Paper →Identifying Stable Patterns over Time for Emotion Recognition from EEG
In this paper, we investigate stable patterns of electroencephalogram (EEG) over time for emotion recognition using a machine learning approach. Up to now, various findings of activated patterns associated with different emotions have been reported. However, their stability over time has not been fully investigated yet. In this paper, we focus on identifying EEG stability in emotion recognition. We systematically evaluate the performance of various popular feature extraction, feature selection, feature smoothing and pattern classification methods with the DEAP dataset and a newly developed dataset called SEED for this study. Discriminative Graph regularized Extreme Learning Machine with differential entropy features achieves the best average accuracies of 69.67 and 91.07 percent on the DEAP and SEED datasets, respectively. The experimental results indicate that stable patterns exhibit consistency across sessions; the lateral temporal areas activate more for positive emotions than negative emotions in beta and gamma bands; the neural patterns of neutral emotions have higher alpha responses at parietal and occipital sites; and for negative emotions, the neural patterns have significant higher delta responses at parietal and occipital sites and higher gamma responses at prefrontal sites. The performance of our emotion recognition models shows that the neural patterns are relatively stable within and between sessions.
View Full Paper →Emotion Regulation Using Virtual Environments and Real-Time fMRI Neurofeedback
Neurofeedback (NFB) enables the voluntary regulation of brain activity, with promising applications to enhance and recover emotion and cognitive processes, and their underlying neurobiology. It remains unclear whether NFB can be used to aid and sustain complex emotions, with ecological validity implications. We provide a technical proof of concept of a novel real-time functional magnetic resonance imaging (rtfMRI) NFB procedure. Using rtfMRI-NFB, we enabled participants to voluntarily enhance their own neural activity while they experienced complex emotions. The rtfMRI-NFB software (FRIEND Engine) was adapted to provide a virtual environment as brain computer interface (BCI) and musical excerpts to induce two emotions (tenderness and anguish), aided by participants' preferred personalized strategies to maximize the intensity of these emotions. Eight participants from two experimental sites performed rtfMRI-NFB on two consecutive days in a counterbalanced design. On one day, rtfMRI-NFB was delivered to participants using a region of interest (ROI) method, while on the other day using a support vector machine (SVM) classifier. Our multimodal VR/NFB approach was technically feasible and robust as a method for real-time measurement of the neural correlates of complex emotional states and their voluntary modulation. Guided by the color changes of the virtual environment BCI during rtfMRI-NFB, participants successfully increased in real time, the activity of the septo-hypothalamic area and the amygdala during the ROI based rtfMRI-NFB, and successfully evoked distributed patterns of brain activity classified as tenderness and anguish during SVM-based rtfMRI-NFB. Offline fMRI analyses confirmed that during tenderness rtfMRI-NFB conditions, participants recruited the septo-hypothalamic area and other regions ascribed to social affiliative emotions (medial frontal/temporal pole and precuneus). During anguish rtfMRI-NFB conditions, participants recruited the amygdala and other dorsolateral prefrontal and additional regions associated with negative affect. These findings were robust and were demonstrable at the individual subject level, and were reflected in self-reported emotion intensity during rtfMRI-NFB, being observed with both ROI and SVM methods and across the two sites. Our multimodal VR/rtfMRI-NFB protocol provides an engaging tool for brain-based interventions to enhance emotional states in healthy subjects and may find applications in clinical conditions associated with anxiety, stress and impaired empathy among others.
View Full Paper →Ready to Optimize Your Brain?
Schedule a free consultation to discuss support vector machines and how neurofeedback training can help
Or call us directly at 855-88-BRAIN
View Programs & Pricing →