CSU scientists help people with motor impairments perform daily tasks through computers

Christina Dennison

(From left) Elliott Forney, a graduate computer science student, meticulously applies gel to Fereydoon Vafaei, computer science doctoral candidate, to ensure a solid connection to collect electroencephalograms, or, EEG for short. Both are part of a study where the long-term goal of the research is a new mode of communication for victims of diseases and injuries that will lead to a stable and healthy control of muscle movement. (Photo credit: Kevin Olson)
(From left) Elliott Forney, a graduate computer science student, meticulously applies gel to Fereydoon Vafaei, computer science doctoral candidate, to ensure a solid connection to collect electroencephalograms, or, EEG for short. Both are part of a study where the long-term goal of the research is a new mode of communication for victims of diseases and injuries that will lead to a stable and healthy control of muscle movement. (Photo credit: Kevin Olson)

People who are unable to move due to spinal cord injuries or neurodegenerative disorders often require assistance from another person to perform activities of daily living. Researchers in the Brain Computer Interface Lab at Colorado State University are using brain waves to communicate with computers, so that people who have lost motor movement can become more independent.

“An unfortunate group of people who have neurodegenerative diseases eventually lose all voluntary muscle control,” said Charles Anderson, professor in the Department of Computer Science and researcher in the BCI Lab. “But, their brains are still very active.”

Ad

For these individuals, the lines of communication between the brain and the muscles are damaged, but neurons in their brain can remain active as if they are still commanding the muscles to move. Anderson explained that this neural activity produces electrical signals that can be recorded using electrodes placed on the scalp. These signals are known as electroencephalography, or EEG.

According to Anderson, a unique pattern of neural activity is produced when people perform or visualize themselves performing a specific task. The researchers in Anderson’s lab mine the EEG data to find patterns of neural activity that distinguishes between tasks such as moving a wheelchair versus adjusting the thermostat.

Elliott Forney and Fereydoon Vafaei are Ph.D. students in computer science working on BCI and EEG in Anderson’s lab. Forney and Vafaei are currently developing software that will be able to make accurate predictions for tasks based on mistakes it made in the past.

“If the system can identify what it is doing incorrectly, it can learn not to do that in the future,” Forrney said.

Forney and Vafaei demonstrated a task with the software they have been working on.

While wearing a cap with electrodes to measure the EEG signal, Vafaei thought about closing his left or right fist. Based on Vafaei’s pattern of neural activity, the computer predicted what fist he wanted to close. If the computer selected the wrong fist, he altered how he performed the mental task to help the computer make a more accurate prediction.

“The simultaneous learning between the computer and the person is going to be necessary (for real-world application),” Anderson said.

The long term goal of this work is to have systems make decisions and adapt in real-time for people who are unable to perform basic activities of daily living. Patients with degenerative disease like ALS experience a progressive loss of motor function, so having a system adapt to their changing needs is important to the patients working with the BCI lab.

Anderson said he has always been curious about the brain. He explained that his interest in finding a way for people to communicate who have lost that ability is a driving force behind his work. Anderson said he hopes that one day this research will lead to assistive robots or a robotic arm that could reach out to grab a bottle of water and bring it to the patient’s mouth.

Anderson enjoys living in Fort Collins and working at CSU because of the work and life balance supported by these communities.

Ad

“CSU has a good focus on both teaching and research, which I like,” Anderson said. “Another nice thing about CSU is the lack of really strong boundaries between departments and colleges, and people are willing to work with anybody.”

Anderson encourages undergraduates who are interested in machine learning, brain computer interface or EEG to volunteer in his lab or with Pattie Davies and Bill Gavin in the Department of Occupational Therapy. He said volunteering in the lab is a great way for students with math and computer programming backgrounds to get hands-on experience.

Forney’s experience in the BCI lab has been rewarding. He explained that as a computer scientist he enjoys writing computer programs, software and algorithms. Yet, he is also encouraged by the potential to positively impact people’s lives.

“The BCI project is encouraging because of the potential for people to be able to use this and have some benefit to their lives,” said Forney. “It’s something that I am hoping will have real-world application.”

Collegian Science Beat Reporter Christina Dennison can be reached at news@collegian.com or on Twitter @csdennison.