A Review of Current Approaches of Brain Computer Interfaces

A Review of Current Approaches of Brain Computer Interfaces

Lochi Yu (Escuela de Ingenieria Electrica, Universidad de Costa Rica, San Pedro, San Jose, Costa Rica) and Cristian Ureña (Escuela de Ingenieria Electrica, Universidad de Costa Rica, San Pedro, San Jose, Costa Rica)
DOI: 10.4018/ijmtie.2012040101
OnDemand PDF Download:


Since the first recordings of brain electrical activity more than 100 years ago remarkable contributions have been done to understand the brain functionality and its interaction with environment. Regardless of the nature of the brain-computer interface BCI, a world of opportunities and possibilities has been opened not only for people with severe disabilities but also for those who are pursuing innovative human interfaces. Deeper understanding of the EEG signals along with refined technologies for its recording is helping to improve the performance of EEG based BCIs. Better processing and features extraction methods, like Independent Component Analysis (ICA) and Wavelet Transform (WT) respectively, are giving promising results that need to be explored. Different types of classifiers and combination of them have been used on EEG BCIs. Linear, neural and nonlinear Bayesian have been the most used classifiers providing accuracies ranges between 60% and 90%. Some demand more computational resources like Support Vector Machines (SVM) classifiers but give good generality. Linear Discriminant Analysis (LDA) classifiers provide poor generality but low computational resources, making them optimal for some real time BCIs. Better classifiers must be developed to tackle the large patterns variability across different subjects by using every available resource, method or technology.
Article Preview

2. Bci Basics

2.1. Background

Before refers to the concept of BCI as conceived currently, it is important to mention the origins of EEG. The first references about brain electrical activity recording go back to 1875 taken from the cortical surface in animals (Canton, 1875) and 1933 taken from the human scalp (Berger, 1993). Thanks to these two remarkable historic events, BCI found its origins by 1970 decade when it was possible to detect and classify some evoked responses known as epochs (Vidal, 1977). Early work involved a lot of experimentation with monkeys using invasive methods to acquire the EEG signals. Important neural activity in their motor cortex area was found when they accomplished several tasks stimulated by rewards.

During these years, many research teams were established to work on this field and trying to understand BCI nature using cognitive neuroscience, computing and mathematical models, or a combination of them. Several research projects were supported in improving signals quality, acquisition methods (invasive and non-invasive), temporal and spatial resolution and classification algorithms. As early state-of-art work, it was developed by 1991 one of the first EEG BCIs able to provide a sort of cursor control over a video screen (Wolpaw, McFarland, Neat, & Forneris, 1991).

However, the main achievements have been done during the last 15 years. Innumerable research results have been published since then, making its tracking almost impossible. Uncountable are the contributions from different areas such as materials science, digital signal processing, machine learning, electronics, computing, medicine as many others. All of them have contributed to the relative success of the BCIs up to today, creating a complete field for research.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 6: 2 Issues (2017): Forthcoming, Available for Pre-Order
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing