Sensorimotor rhythm-based brain–computer interface (BCI): model order selection for autoregressive spectral analysis

Abstract

People can learn to control EEG features consisting of sensorimotor rhythm amplitudes and can use this control to move a cursor in one or two dimensions to a target on a screen. Cursor movement depends on the estimate of the amplitudes of sensorimotor rhythms. Autoregressive models are often used to provide these estimates. The order of the autoregressive model has varied widely among studies. Through analyses of both simulated and actual EEG data, the present study examines the effects of model order on sensorimotor rhythm measurements and BCI performance. The results show that resolution of lower frequency signals requires higher model orders; and that this requirement reflects the temporal span of the model coefficients. This is true for both simulated EEG data and actual EEG data during brain-computer interface (BCI) operation. Increasing model order and decimating the signal were similarly effective in increasing spectral resolution. Furthermore, for BCI control of two-dimensional cursor movement, higher model orders produced better performance in each dimension and greater independence between horizontal and vertical movements. In sum, these results show that autoregressive model order selection is an important determinant of BCI performance and should be based on criteria that reflect system performance.

Oscillatory entrainment of the motor cortical network during motor imagery is modulated by the feedback modality

“…Every trial consisted of a cued task design with different task epochs. Each trial was initiated by a preparatory epoch, lasting for 2 s, followed by a MI epoch, lasting for 6 s, and completed by a rest period lasting for 6 s. During each trial, the regional oscillatory activity of the preceding 500 ms was estimated every 40 ms using an autoregressive model based on the Burg Algorithm with a model order of 32 (McFarland and Wolpaw, 2008). Participants were instructed to perform kinesthetic MI (Neuper et al, 2005) of right-hand opening, thus resulting in eventrelated desynchronization of β-oscillations (β-ERD) over contralateral sensorimotor electrodes (FC3, C3, and CP3) which were used for online classification.…”

Rehabilitation of post stroke patients using a bioengineering system "brain-computer interface + exoskeleton"

“…Во-вторых, сам пациент не имеет обратной связи от воображае-мого движения, что мешает ему контролировать собственные усилия. ИМК позволяет разрешить эти две проблемы, переводя биоэлектрическую актив-ность головного мозга в команды, управляющие различными устройствами [17,19]. Именно этот принцип, описанный ранее и опробованный на здо-ровых добровольцах, был заложен в основу исполь-зованного в исследовании реабилитационного био-инженерного комплекса «ИМК + экзоскелет» [15,20].…”

Classification of Mental Tasks using EEG and Hierarchical Classifier employing Optimised Neural Networks

“…This paper claims that RBFNN is useful for real-time detection of attention-related ERP and thus can be an effective tool for the ERP amplitude and latency change estimation. Various feature extraction methods have been applied to obtain features from the EEG signals including adaptive autoregressive models (AAR) [11][12][13], common spatial filters [14,15] and wavelet transform [16 , 17].…”