A probabilistic approach for calibration time reduction in hybrid EEG-fTCD brain-computer interfaces

Improved BCI calibration in multimodal emotion recognition using heterogeneous adversarial transfer learning

The use of brain-computer interface (BCI) technology to identify emotional states has gained significant interest, especially with the rise of virtual reality (VR) applications. However, the extensive calibration required for precise emotion recognition models presents a significant challenge, particularly for sensitive groups such as children, elderly, and patients. This study presents a novel approach that utilizes heterogeneous adversarial transfer learning (HATL) to synthesize electroencephalography (EEG) data from various other signal modalities, reducing the need for lengthy calibration phases. We benchmark the efficacy of three generative adversarial network (GAN) architectures, such as conditional GAN (CGAN), conditional Wasserstein GAN (CWGAN), and CWGAN with gradient penalty (CWGAN-GP) within this framework. The proposed framework is rigorously tested on two conventional open sourced datasets, SEED-V and DEAP. Additionally, the framework was applied to an immersive three-dimensional (3D) dataset named GraffitiVR, which we collected to capture the emotional and behavioral reactions of individuals experiencing urban graffiti in a VR environment. This expanded application provides insights into emotion recognition frameworks in VR settings, providing a wider range of contexts for assessing our methodology. When the accuracy of emotion recognition classifiers trained with CWGAN-GP-generated EEG data combined with non-EEG sensory data was compared against those trained using a combination of real EEG and non-EEG sensory data, the accuracy ratios were 93% on the SEED-V dataset, 99% on the DEAP dataset, and 97% on the GraffitiVR dataset. Moreover, in the GraffitiVR dataset, using CWGAN-GP-generated EEG data with non-EEG sensory data for emotion recognition models resulted in up to a 30% reduction in calibration time compared to classifiers trained on real EEG data with non-EEG sensory data. These results underscore the robustness and versatility of the proposed approach, significantly enhancing emotion recognition processes across a variety of environmental settings.

A machine-learning approach for predicting impaired consciousness in absence epilepsy

Behavior during 3-4 Hz spike-wave discharges (SWDs) in absence epilepsy can vary from obvious behavioral arrest to no detectible deficits. Knowing if behavior is impaired is crucial for clinical care but may be difficult to determine without specialized behavioral testing, often inaccessible in practice. We aimed to develop a pure electroencephalography (EEG)-based machine-learning method to predict SWD-related behavioral impairment. Our classification goals were 100% predictive value, with no behaviorally impaired SWDs misclassified as spared; and maximal sensitivity. First, using labeled data with known behavior (130 SWDs in 34 patients), we extracted EEG time, frequency domain, and common spatial pattern features and applied support vector machines and linear discriminant analysis to classify SWDs as spared or impaired. We evaluated 32 classification models, optimized with 10-fold cross-validation. We then generalized these models to unlabeled data (220 SWDs in 41 patients), where behavior during individual SWDs was not known, but observers reported the presence of clinical seizures. For labeled data, the best classifier achieved 100% spared predictive value and 93% sensitivity. The best classifier on the unlabeled data achieved 100% spared predictive value, but with a lower sensitivity of 35%, corresponding to a conservative classification of 8 patients out of 23 as free of clinical seizures. Our findings demonstrate the feasibility of machine learning to predict impaired behavior during SWDs based on EEG features. With additional validation and optimization in a larger data sample, applications may include EEG-based prediction of driving safety, treatment adjustment, and insight into mechanisms of impaired consciousness in absence seizures.

A Domain Adaptation-Based Method for Classification of Motor Imagery EEG

Non-stationarity of EEG signals lead to high variability across sessions, which results in low classification accuracy. To reduce the inter-session variability, an unsupervised domain adaptation method is proposed. Arithmetic mean and covariance are exploited to represent the data distribution. First, overall mean alignment is conducted between the source and target data. Then, the data in the target domain is labeled by a classifier trained with the source data. The per-class mean and covariance of the target data are estimated based on the predicted labels. Next, an alignment from the source domain to the target domain is performed according to the covariance of each class in the target domain. Finally, per-class mean adaptation is required after covariance alignment to remove the shift of data distribution caused by covariance alignment. Two public BCI competition datasets, namely the BCI competition III dataset IVa and the BCI competition IV dataset IIa were used to evaluate the proposed method. On both datasets, the proposed method effectively improved classification accuracy.

A Review on Signal Processing Approaches to Reduce Calibration Time in EEG-Based Brain-Computer Interface

In an electroencephalogram- (EEG-) based brain–computer interface (BCI), a subject can directly communicate with an electronic device using his EEG signals in a safe and convenient way. However, the sensitivity to noise/artifact and the non-stationarity of EEG signals result in high inter-subject/session variability. Therefore, each subject usually spends long and tedious calibration time in building a subject-specific classifier. To solve this problem, we review existing signal processing approaches, including transfer learning (TL), semi-supervised learning (SSL), and a combination of TL and SSL. Cross-subject TL can transfer amounts of labeled samples from different source subjects for the target subject. Moreover, Cross-session/task/device TL can reduce the calibration time of the subject for the target session, task, or device by importing the labeled samples from the source sessions, tasks, or devices. SSL simultaneously utilizes the labeled and unlabeled samples from the target subject. The combination of TL and SSL can take advantage of each other. For each kind of signal processing approaches, we introduce their concepts and representative methods. The experimental results show that TL, SSL, and their combination can obtain good classification performance by effectively utilizing the samples available. In the end, we draw a conclusion and point to research directions in the future.