Direct comparison of supervised and semi-supervised retraining approaches for co-adaptive BCIs

Simultaneous multiple-stimulus auditory brain-computer interface with semi-supervised learning and prior probability distribution tuning

Objective.Auditory brain-computer interfaces (BCIs) enable users to select commands based on the brain activity elicited by auditory stimuli. However, existing auditory BCI paradigms cannot increase the number of available commands without decreasing the selection speed, because each stimulus needs to be presented independently and sequentially under the standard oddball paradigm. To solve this problem, we propose a double-stimulus paradigm that simultaneously presents multiple auditory stimuli.Approach.For addition to an existing auditory BCI paradigm, the best discriminable sound was chosen following a subjective assessment. The new sound was located on the right-hand side and presented simultaneously with an existing sound from the left-hand side. A total of six sounds were used for implementing the auditory BCI with a 6 × 6 letter matrix. We employ semi-supervised learning (SSL) and prior probability distribution tuning to improve the accuracy of the paradigm. The SSL method involved updating of the classifier weights, and their prior probability distributions were adjusted using the following three types of distributions: uniform, empirical, and extended empirical (e-empirical). The performance was evaluated based on the BCI accuracy and information transfer rate (ITR).Main results.The double-stimulus paradigm resulted in a BCI accuracy of 67.89 ± 11.46% and an ITR of 2.67 ± 1.09 bits min^-1, in the absence of SSL and with uniform distribution. The proposed combination of SSL with e-empirical distribution improved the BCI accuracy and ITR to 74.59 ± 12.12% and 3.37 ± 1.27 bits min^-1, respectively. The event-related potential analysis revealed that contralateral and right-hemispheric dominances contributed to the BCI performance improvement.Significance.Our study demonstrated that a BCI based on multiple simultaneous auditory stimuli, incorporating SSL and e-empirical prior distribution, can increase the number of commands without sacrificing typing speed beyond the acceptable level of accuracy.

Information sparseness in cortical microelectrode channels while decoding movement direction using an artificial neural network

Implanted microelectrode arrays can directly pick up electrode signals from the primary motor cortex (M1) during movement, and brain-machine interfaces (BMIs) can decode these signals to predict the directions of contemporaneous movements. However, it is not well known how much each individual input is responsible for the overall performance of a BMI decoder. In this paper, we seek to quantify how much each channel contributes to an artificial neural network (ANN)-based decoder, by measuring how much the removal of each individual channel degrades the accuracy of the output. If information on movement direction was equally distributed among channels, then the removal of one would have a minimal effect on decoder accuracy. On the other hand, if that information was distributed sparsely, then the removal of specific information-rich channels would significantly lower decoder accuracy. We found that for most channels, their removal did not significantly affect decoder performance. However, for a subset of channels (16 out of 61), removing them significantly reduced the decoder accuracy. This suggests that information is not uniformly distributed among the recording channels. We propose examining these channels further to optimize BMIs more effectively, as well as understand how M1 functions at the neuronal level.

Interface, interaction, and intelligence in generalized brain-computer interfaces

A brain-computer interface (BCI) establishes a direct communication channel between a brain and an external device. With recent advances in neurotechnology and artificial intelligence (AI), the brain signals in BCI communication have been advanced from sensation and perception to higher-level cognition activities. While the field of BCI has grown rapidly in the past decades, the core technologies and innovative ideas behind seemingly unrelated BCI systems have never been summarized from an evolutionary point of view. Here, we review various BCI paradigms and present an evolutionary model of generalized BCI technology which comprises three stages: interface, interaction, and intelligence (I3). We also highlight challenges, opportunities, and future perspectives in the development of new BCI technology.

A Comprehensive Review on Critical Issues and Possible Solutions of Motor Imagery Based Electroencephalography Brain-Computer Interface

Motor imagery (MI) based brain–computer interface (BCI) aims to provide a means of communication through the utilization of neural activity generated due to kinesthetic imagination of limbs. Every year, a significant number of publications that are related to new improvements, challenges, and breakthrough in MI-BCI are made. This paper provides a comprehensive review of the electroencephalogram (EEG) based MI-BCI system. It describes the current state of the art in different stages of the MI-BCI (data acquisition, MI training, preprocessing, feature extraction, channel and feature selection, and classification) pipeline. Although MI-BCI research has been going for many years, this technology is mostly confined to controlled lab environments. We discuss recent developments and critical algorithmic issues in MI-based BCI for commercial deployment.

Multi-class motor imagery EEG classification using collaborative representation-based semi-supervised extreme learning machine

Both labeled and unlabeled data have been widely used in electroencephalographic (EEG)-based brain-computer interface (BCI). However, labeled EEG samples are generally scarce and expensive to collect, while unlabeled samples are considered to be abundant in real applications. Although the semi-supervised learning (SSL) allows us to utilize both labeled and unlabeled data to improve the classification performance as against supervised algorithms, it has been reported that unlabeled data occasionally undermine the performance of SSL in some cases. To overcome this challenge, we propose a collaborative representation-based semi-supervised extreme learning machine (CR-SSELM) algorithm to evaluate the risk of unlabeled samples by a new safety-control mechanism. Specifically, the ELM model is firstly used to predict unlabeled samples and then the collaborative representation (CR) approach is employed to reconstruct the unlabeled samples according to the obtained prediction results, from which the risk degree of unlabeled sample is defined. A risk-based regularization term is then constructed accordingly and embedded into the objective function of the SS-ELM. Experiments conducted on benchmark and EEG datasets demonstrate that the proposed method outperforms the ELM and SS-ELM algorithm. Moreover, the proposed CR-SSELM even offers the best performance while SS-ELM yields worse performance compared with its supervised counterpart (ELM). Graphical abstract This paper proposes a collaborative representation-based semi-supervised extreme learning machine (CR-SSELM) algorithm to evaluate the risk of unlabeled samples by a new safety-control mechanism. It is aim to solve the safety problem of SS-ELM method that SS-ELM yields worse performance than ELM. With the help of safety mechanism, the performance of our method is still better than supervised ELM method.

Decoding hand movements from human EEG to control a robotic arm in a simulation environment

OBJECTIVE

Daily life tasks can become a significant challenge for motor impaired persons. Depending on the severity of their impairment, they require more complex solutions to retain an independent life. Brain-computer interfaces (BCIs) are targeted to provide an intuitive form of control for advanced assistive devices such as robotic arms or neuroprostheses. In our current study we aim to decode three different executed hand movements in an online BCI scenario from electroencephalographic (EEG) data.

APPROACH

Immersed in a desktop-based simulation environment, 15 non-disabled participants interacted with virtual objects from daily life by an avatar's robotic arm. In a short calibration phase, participants performed executed palmar and lateral grasps and wrist supinations. Using this data, we trained a classification model on features extracted from the low frequency time domain. In the subsequent evaluation phase, participants controlled the avatar's robotic arm and interacted with the virtual objects in case of a correct classification.

MAIN RESULTS

On average, participants scored online 48% of all movement trials correctly (3-condition scenario, adjusted chance level 40%, alpha = 0.05). The underlying movement-related cortical potentials (MRCPs) of the acquired calibration data show significant differences between conditions over contralateral central sensorimotor areas, which are retained in the data acquired from the online BCI use.

SIGNIFICANCE

We could show the successful online decoding of two grasps and one wrist supination movement using low frequency time domain features of the human EEG. These findings can potentially contribute to the development of a more natural and intuitive BCI-based control modality for upper limb motor neuroprostheses or robotic arms for people with motor impairments.