Investigating Music imagery as a Cognitive Paradigm for low-Cost brain-Computer Interfaces

  title={Investigating Music imagery as a Cognitive Paradigm for low-Cost brain-Computer Interfaces},
  author={Lukas Gro{\ss}berger and Matthias Hohmann and Jan Peters and Moritz Grosse-Wentrup},
Many current brain-computer interfaces (BCIs) rely on motor imagery or oculomotor paradigms to transfer information, yet these functions are impaired in people that suffer from late stage Amyotrophic Lateral Sclerosis (ALS). Additionally, patients have limited access to cutting-edge BCI technology for home-use because the necessary, medical grade equipment is expensive and difficult to setup. We addressed both issues with the current study. First, we devised a novel paradigm that relies on… 

Figures from this paper

MYND: Unsupervised Evaluation of Novel BCI Control Strategies on Consumer Hardware
This work introduces MYND: An open-source framework that couples consumer-grade recording hardware with an easy-to-use application for the unsupervised evaluation of BCI control strategies and uses a four-channel electroencephalogram (EEG) with MYND as a use case.
Compact Convolutional Neural Networks for Multi-Class, Personalised, Closed-Loop EEG-BCI
The preliminary results show that an efficient architecture (SmallNet), with only one convolutional layer, can classify 4 mental activities chosen by the user, and that models trained with data collected online better predicted the behaviour of the system in real-time suggests that similar (CNN based) offline classifying methods might experience a drop in performance when applied online.
Towards Development of a Robust Asynchronous EEG-BCI using Error-Related Potentials
The findings of these studies support the addition of ErrP-informed correction to maximize the accuracy of cue-based and self-paced BCIs based on non-MI cognitive tasks.


A Cognitive Brain-Computer Interface for Patients with Amyotrophic Lateral Sclerosis
A new paradigm that targets higher level cognitive processes to transmit information from the user to the BCI is devised that could serve as a basis for a novel tool which allows for simple, reliable communication with patients in late stages of ALS.
Individually Adapted Imagery Improves Brain-Computer Interface Performance in End-Users with Disability
This study investigated the impact of mental tasks on binary classification performance in BCI users with central nervous system (CNS) tissue damage such as persons with stroke or spinal cord injury (SCI).
A brain–computer interface based on self-regulation of gamma-oscillations in the superior parietal cortex
Self-regulation of gamma-power in the SPC is a feasible paradigm for brain-computer interfacing and may be preserved in late stages of ALS, providing a novel approach to testing whether completely locked-in ALS patients retain the capacity for goal-directed thinking.
The effect of distinct mental strategies on classification performance for brain-computer interfaces.
Does the ‘P300’ speller depend on eye gaze?
The results show that the performance of the 'P300' matrix speller in normal subjects depends in considerable measure on gaze direction, and disprove a widespread assumption in BCI research, and suggest that this BCI might function more effectively for people who retain some eye-movement control.
Transfer Learning in Brain-Computer Interfaces
A framework for transfer learning in the context of BCIs that can be applied to any arbitrary feature space, as well as a novel regression estimation method that is specifically designed for the structure of a system based on the electroencephalogram (EEG).
Music perception and imagery in EEG: alpha band effects of task and stimulus.
  • R. Schaefer, R. Vlek, P. Desain
  • Psychology, Biology
    International journal of psychophysiology : official journal of the International Organization of Psychophysiology
  • 2011
Oscillatory EEG correlates of arithmetic strategy use in addition and subtraction
The present high-resolution electroencephalography study analysed event-related synchronisation (ERS) and desynchronisation (ERD) in the theta and alpha bands while participants solved addition and subtraction problems, which displayed a high probability of retrieval or procedural strategy use.
Brain–computer interfaces in amyotrophic lateral sclerosis: A metanalysis
Neural oscillations involved in self-referential processing