Spectral Transfer Learning Using Information Geometry for a User-Independent Brain-Computer Interface

Abstract

Recent advances in signal processing and machine learning techniques have enabled the application of Brain-Computer Interface (BCI) technologies to fields such as medicine, industry, and recreation; however, BCIs still suffer from the requirement of frequent calibration sessions due to the intra- and inter-individual variability of brain-signals, which makes calibration suppression through transfer learning an area of increasing interest for the development of practical BCI systems. In this paper, we present an unsupervised transfer method (spectral transfer using information geometry, STIG), which ranks and combines unlabeled predictions from an ensemble of information geometry classifiers built on data from individual training subjects. The STIG method is validated in both off-line and real-time feedback analysis during a rapid serial visual presentation task (RSVP). For detection of single-trial, event-related potentials (ERPs), the proposed method can significantly outperform existing calibration-free techniques as well as outperform traditional within-subject calibration techniques when limited data is available. This method demonstrates that unsupervised transfer learning for single-trial detection in ERP-based BCIs can be achieved without the requirement of costly training data, representing a step-forward in the overall goal of achieving a practical user-independent BCI system.

Riemannian geometry for EEG-based brain-computer interfaces; a primer and a review

“…Cross-subject learning with the MDM Riemannian classifier has been treated in a supervised fashion in [58,118] and in an unsupervised fashion in [119,120]. The use of power means as a generalization of the geometric mean has been proposed in [88].…”

Cross-Subject Transfer Learning Improves the Practicality of Real-World Applications of Brain-Computer Interfaces

“…So, the calibration procedure is often laborious and time-consuming, hindering the practicality of BCIs in a real-world context. Many researchers have attempted to adopt transfer-learning techniques to shorten the calibration process without compromising classification accuracy [10], [11]. For instance, Yuan et al [10], [11] proposed subject-to-subject transfer learning methods, which transfer SSVEP data from existing subjects to new ones.…”

“…Many researchers have attempted to adopt transfer-learning techniques to shorten the calibration process without compromising classification accuracy [10], [11]. For instance, Yuan et al [10], [11] proposed subject-to-subject transfer learning methods, which transfer SSVEP data from existing subjects to new ones. More recently, Nakanishi et al made it possible to transfer SSVEP data across sessions even with different electrode montages [4].…”

Evolving Training Sets for Improved Transfer Learning in Brain Computer Interfaces

“…Some conditions, such as Amyotrophic Lateral Sclerosis (ALS), cause degradation of physical movement [2], rendering patients unable to communicate with the outside world. Detection of neural activity can allow patients to control computers, and produce synthetic speech [1]. A common form of the system involves using a computer screen displaying a 6x6 grid of alphanumeric characters.…”

“…Uses for BCI range from manipulation of prosthetic limbs, psychological interventions, and assisted communication devices [1]. Approaches to obtain these recordings can be separated into two main groupings; invasive and non-invasive.…”