ADELPHI, Md. (May 4, 2015) -- Scientists at the U.S. Army Research Laboratory are investigating communication with a computer or phone without making a sound or moving a single muscle, and it may revolutionize both medical applications and battlefield communications.
The science behind the idea is known as Brain-Computer Interface, or BCI, which may lead to technologies for recording brain activity and establishing computational methods and algorithms to translate the signals into computer executable commands.
BCI has been most commonly used with individuals who are paralyzed and cannot move or communicate verbally due to paralysis of nearly all voluntary muscles in the body, with the exception of their eyes.
As a result of recent advances in hardware and software, coupled with breakthroughs in neuroscience and cognitive science, these individuals are able to perform functions such as typing letters, writing emails, making phone calls and controlling a robotic arm, solely by thinking.
There are several different methods of recording brain activity for BCI that allow the above-mentioned functions to be accomplished, but two are most common in BCI research.
The first is noninvasive, where electroencephalography, or EEG, devices record electrical activities of the brain along the scalp using an array of electrodes placed on the scalp. The second method involves more invasive techniques, where electrocorticography, referred to as ECoG, devices record electrical activities from the cerebral cortex of the brain using electrodes placed directly on the exposed surface of the brain.
While the ability to perform these tasks is a great milestone in and of itself, current BCI techniques have been found to only be successful in laboratory settings. In addition, current BCI techniques require extended training and are not practical for ordinary daily lives.
"ARL recognizes that BCI is an emerging area with a high potential for revolutionizing the way we communicate with machines and that the potential exists for larger scale real-world applications such as brain-based communication through everyday devices," said Dr. Liyi Dai, program manager in the Computer Sciences Division at ARL's Army Research Office located in Research Triangle Park, North Carolina.
According to Dai, ARL has established multi-million dollar, multi-year efforts consisting of teams of university researchers from schools, including Albany Medical College and the University of California, Irvine, equipped with multidisciplinary expertise drawn from computer science, mathematics and neuroscience.
These investments focus on two main challenges of BCI technology. The first is that current underlying algorithms are not reliable enough to perform well under a wide range of operation environments and conditions for real-world applications.
"ARL/ARO investments have been focused on creating advanced computation algorithms so that, with the new algorithms, BCI capabilities are moving a step closer toward real applications. The new algorithms put greater emphasis on the dynamics of brain signals and the interaction of different parts of the brain," Dai said.
The second challenge is that current BCI techniques do not include a feedback mechanism to help operators understand why a certain function did or did not occur based on their thinking process.
"Another way to increase BCI performance is the inclusion of a feedback mechanism, that is, the human operator adjusts the way of thinking in response to the outcome of the underlying detection algorithms," Dai said.
For example, if the operator of a BCI capable device is unsuccessful in performing a certain task, he or she will be given feedback to "think harder" to strengthen his or her brain signals to be able to perform that task.
ARL/ARO investments have also led to new capabilities including the detection of imagined speech, or thinking silently to oneself, and attention.
In 2008, ARO's Information Processing and Fusion Program and Neurophysiology and Cognitive Neuroscience Program jointly established a major research initiative under the Multidisciplinary University Research Initiative program.
Two projects are currently funded under this initiative.
One project, entitled "A Brain-Based Communication and Orientation System," works on developing a prototype system for detecting imagined speech and monitoring user's attention and orientation using recordings of brain activities in real time.
The second project, entitled "Silent Spatialized Communication among Dispersed Forces," focuses on understanding physiological biomarkers of brain signals for imagined speech detection, which provides biological basis toward designing computational algorithms to extract biomarkers, or features, for imagined speech detection.
"The ARO MURI projects were the first major investments to address the basic research challenge of signal processing and pattern classification for imagined speech and attention detection. The efforts have successfully demonstrated the feasibility of imagined speech detection using ECoG or EEG, which has led to increased interest among the academic community on this subject," Dai said.
One major achievement that was made through these projects is that ARL/ARO research revealed for the first time that different brain regions are involved in producing vowels and consonants.
Just as in the establishment of other disruptive technologies, it may take many years or even decades to mature BCI technology, but Dai and his fellow researchers are confident that further progress means potentially great capabilities for our Soldiers.
"Progress in BCI based communication is potentially of great importance to the warfighter because BCIs would eliminate the intermediate steps required in traditional human-machine interfaces. Having a Soldier gain the ability to communicate without any overt movement would be invaluable both in the battlefield as well as in combat casualty care," Dai said.
Dai added that BCI communication would provide a revolutionary technology for silent communication and orientation that is inherently immune to external environmental distraction such as sound and light.
Evolution of this research could lead to direct mental control of military systems by thought alone.
Imagined speech detection is also said to have potential medical applications in speech therapy and epilepsy treatment, as the research provides complementary understanding of brain activities for speech, an important part of human capabilities.
Moving forward, Dai noted that substantial individualized experimentation is required to train the underlying algorithms, and further improvements of computing algorithms are needed toward robust brain signal processing and analysis to achieve reliable BCI performance for a wide range of practical applications.
Amidst the challenges faced in BCI research and the progress to still be made, scientists are working hard behind the scenes to bring this technology to fruition and make it applicable in real-world situations for the benefit and protection of our Soldiers.
This article appears in the May/June 2015 issue of Army Technology Magazine, which focuses on Future Computing. The magazine is available as an electronic download, or print publication. The magazine is an authorized, unofficial publication published under Army Regulation 360-1, for all members of the Department of Defense and the general public.
The Army Research Laboratory is part of the U.S. Army Research, Development and Engineering Command, which has the mission to develop technology and engineering solutions for America's Soldiers.
RDECOM is a major subordinate command of the U.S. Army Materiel Command. AMC is the Army's premier provider of materiel readiness--technology, acquisition support, materiel development, logistics power projection and sustainment--to the total force, across the spectrum of joint military operations. If a Soldier shoots it, drives it, flies it, wears it, eats it or communicates with it, AMC provides it.
Army Technology Magazine [PDF]