Brain-computer interface
(BCI) research is growing at a significant pace and, since the
beginning of the 21st century, has seen explosive growth. The depth
and breadth of BCI research in progress today is indicative of its
application potential – this is exemplified by the year-on-year
exponential increase in peer review journal publications, regular
news items in the media, formation of BCI related companies and
substantial investment in BCI-specific projects. BCI technology can
provide a communication pathway from the brain to the computer which
does not rely on neuromuscular control therefore there are many
potential beneficiaries of the technology. Even though BCI
technology has been under investigation concertedly for the past ten
years, there remain many challenges and barriers to providing this
technology easily and effectively to the intended beneficiaries
i.e., those who require an alternative means of
communication/control such as people with neuromuscular deficiencies
due to disease, spinal chord injury or brain damage. Being able to
offer these people an alternative means of communication through BCI
could have an obvious impact on their quality of life. There are
other applications of BCI, yet to be fully proven and exploited,
such as neurofeedback for stroke rehabilitation and epileptic
seizure prediction, awareness/alertness detection for long distance
drivers and personalised computing environment adaptation through
workload monitoring. BCI is also emerging as an augmentative
technology in computer games and virtual reality technology and has
been associated with numerous military applications.
As yet BCI is a nascent technology. There have been many advances
but there are still a significant number of problems and issues to
be resolved. The main problem stems from the fact the brain is a
complex and non-stationary system and therefore neural signals,
especially the electroencephalogram (EEG), are complex and unwieldy.
In general, interpreting and discriminating biosignals is
challenging. Traditional signal processing techniques have been
applied in BCI and for biological signal processing however most
biosystems are several orders of magnitude more complex than the
man-made systems for which these techniques were developed. The
complexity in biosystems arises from multiple factors such as
multiple layered architectures, systematic changes due to evolution
and mutation, the asynchronous nature of many interactions and the
level of parallelism and redundancy, resulting in complex, random,
or unpredictable behaviour. Biosignal processing methods require
additional considerations to account for these inherent
complexities.
Research in artificial intelligence (AI) and computational
intelligence (CI) is producing novel methodologies to tackle the
complexity of biosignals and this field is offering new insights
into the way these signals can be analyzed and utilized. The AI and
CI research community are well placed to tackle all of these
challenges in BCI development and likewise BCI is an ideal domain
for the study and application of AI and CI.