Data Mining Practical Machine Learning Tools and Techniques

Objective: Most current Electroencephalography (EEG)-based Brain-Computer Interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately 10 years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. Approach: We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. Main results: We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. Significance: This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these Review of Classification Algorithms for EEG-based BCI 2 methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.

https://iopscience.iop.org/article/10.1088/1741-2552/aab2f2/pdf

A Review of Classification Algorithms for EEG-based Brain-Computer Interfaces: A 10-year Update

Brain-machine interfaces (BMIs) combine methods, approaches, and concepts derived from neurophysiology, computer science, and engineering in an effort to establish real-time bidirectional links bet...

Brain-Machine Interfaces: From Basic Science to Neuroprostheses and Neurorehabilitation

A Brain–Computer Interface (BCI) provides a novel non-muscular communication method via brain signals. A BCI-speller can be considered as one of the first published BCI applications and has opened the gate for many advances in the field. Although many BCI-spellers have been developed during the last few decades, to our knowledge, no reviews have described the different spellers proposed and studied in this vital field. The presented speller systems are categorized according to major BCI paradigms: P300, steady-state visual evoked potential (SSVEP), and motor imagery (MI). Different BCI paradigms require specific electroencephalogram (EEG) signal features and lead to the development of appropriate Graphical User Interfaces (GUIs). The purpose of this review is to consolidate the most successful BCI-spellers published since 2010, while mentioning some other older systems which were built explicitly for spelling purposes. We aim to assist researchers and concerned individuals in the field by illustrating the highlights of different spellers and presenting them in one review. It is almost impossible to carry out an objective comparison between different spellers, as each has its variables, parameters, and conditions. However, the gathered information and the provided taxonomy about different BCI-spellers can be helpful, as it could identify suitable systems for first-hand users, as well as opportunities of development and learning from previous studies for BCI researchers.

Brain-Computer Interface Spellers: A Review.

People with severe neurological impairments face many challenges in sensorimotor functions and communication with the environment; therefore they have increased demand for advanced, adaptive and personalized rehabilitation. During the last several decades, numerous studies have developed brain-computer interfaces (BCIs) with the goals ranging from providing means of communication to functional rehabilitation. Here we review the research on non-invasive, electroencephalography (EEG)-based BCI systems for communication and rehabilitation. We focus on the approaches intended to help severely paralyzed and locked-in patients regain communication using three different BCI modalities: slow cortical potentials, sensorimotor rhythms and P300 potentials, as operational mechanisms. We also review BCI systems for restoration of motor function in patients with spinal cord injury and chronic stroke. We discuss the advantages and limitations of these approaches and the challenges that need to be addressed in the future.

/pdf/eeg-based-brain-computer-interfaces-for-communication-and-2lt2av3nyk.pdf

EEG-Based Brain-Computer Interfaces for Communication and Rehabilitation of People with Motor Impairment: A Novel Approach of the 21 st Century.

Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces

Practical motor imagery-based brain computer interface (MI-BCI) applications are limited by the difficult to decode brain signals in a reliable way. In this paper, we propose a processing framework to address non-stationarity, as well as handle spectral, temporal, and spatial characteristics associated with execution of motor tasks. Stacked generalization is used to exploit the power of classifier ensembles for combining information coming from multiple sources and reducing the existing uncertainty in EEG signals. The outputs of several regularized linear discriminant analysis (RLDA) models are combined to account for temporal, spatial, and spectral information. The resultant algorithm is called stacked RLDA (SRLDA). Additionally, an adaptive processing stage is introduced before classification to reduce the harmful effect of intersession non-stationarity. The benefits of the proposed method are evaluated on the BCI Competition IV dataset 2a. We demonstrate its effectiveness in binary and multiclass settings with four different motor imagery tasks: left-hand, right-hand, both feet, and tongue movements. The results show that adaptive SRLDA outperforms the winner of the competition and other approaches tested on this multiclass dataset.

Adaptive Stacked Generalization for Multiclass Motor Imagery-Based Brain Computer Interfaces

The present study aims at developing and assessing an assistive tool for operating electronic devices at home by means of a P300-based brain-computer interface (BCI). Fifteen severely impaired subjects participated in the study. The developed tool allows users to interact with their usual environment fulfilling their main needs. It allows for navigation through ten menus and to manage up to 113 control commands from eight electronic devices. Ten out of the fifteen subjects were able to operate the proposed tool with accuracy above 77 %. Eight out of them reached accuracies higher than 95 %. Moreover, bitrates up to 20.1 bit/min were achieved. The novelty of this study lies in the use of an environment control application in a real scenario: real devices managed by potential BCI end-users. Although impaired users might not be able to set up this system without aid of others, this study takes a significant step to evaluate the degree to which such populations could eventually operate a stand-alone system. Our results suggest that neither the type nor the degree of disability is a relevant issue to suitably operate a P300-based BCI. Hence, it could be useful to assist disabled people at home improving their personal autonomy.

A P300-based brain–computer interface aimed at operating electronic devices at home for severely disabled people

Neurofeedback training (NFT) has shown to be promising and useful to rehabilitate cognitive functions. Recently, brain-computer interfaces (BCIs) were used to restore brain plasticity by inducing brain activity with an NFT. In our study, we hypothesized that an NFT with a motor imagery-based BCI (MI-BCI) could enhance cognitive functions related to aging effects. To assess the effectiveness of our MI-BCI application, 63 subjects (older than 60 years) were recruited. This novel application was used by 31 subjects (NFT group). Their Luria neuropsychological test scores were compared with the remaining 32 subjects, who did not perform NFT (control group). Electroencephalogram changes measured by relative power (RP) endorsed cognitive potential findings under study: visuospatial, oral language, memory, intellectual and attention functions. Three frequency bands were selected to assess cognitive changes: 12, 18, and 21 Hz (bandwidth 3 Hz). Significant increases (p < 0.01) in the RP of these frequency bands were found. Moreover, results from cognitive tests showed significant improvements (p < 0.01) in four cognitive functions after performing five NFT sessions: visuospatial, oral language, memory, and intellectual. This established evidence in the association between NFT performed by a MI-BCI and enhanced cognitive performance. Therefore, it could be a novel approach to help elderly people.

/pdf/neurofeedback-training-with-a-motor-imagery-based-bci-algpk7i04x.pdf

Neurofeedback training with a motor imagery-based BCI: neurocognitive improvements and EEG changes in the elderly

This study performed an analysis of several feature extraction methods and a genetic algorithm applied to a motor imagery-based Brain Computer Interface (BCI) system. Several features can be extracted from EEG signals to be used for classification in BCIs. However, it is necessary to select a small group of relevant features because the use of irrelevant features deteriorates the performance of the classifier. This study proposes a genetic algorithm (GA) as feature selection method. It was applied to the dataset IIb of the BCI Competition IV achieving a kappa coefficient of 0.613. The use of a GA improves the classification results using extracted features separately (kappa coefficient of 0.336) and the winner competition results (kappa coefficient of 0.600). These preliminary results demonstrated that the proposed methodology could be useful to control motor imagery-based BCI applications.

Rebeca Corralejo

Papers

Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces

Adaptive Stacked Generalization for Multiclass Motor Imagery-Based Brain Computer Interfaces

A P300-based brain–computer interface aimed at operating electronic devices at home for severely disabled people

Neurofeedback training with a motor imagery-based BCI: neurocognitive improvements and EEG changes in the elderly

Feature selection using a genetic algorithm in a motor imagery-based Brain Computer Interface