BRAIN-COMPUTER INTERFACES (BCI)

1
BRAIN-COMPUTER INTERFACES (BCI)

• Presentation
• by
• Team 1
• Bintou Kane
• Sridevi Puramsetti
• Raghu Basavaraju
• Robert Zack
• 04/18/09
• DCS861A

2
Agenda

• What is BCI? Why BCI?
• BCI Components
• Invasive vs. Noninvasive BCI
• BCI Benefits/Applications
• BCI Challenges
• Current trends and Future directions
• References

3
What is a BCI?

• BCIs Read electrical signals or other
  manifestations of brain activity and
• Translate them into a digital form that computers
  can understand, process, and
• Convert into actions of some kind, such as moving
  a cursor or turning on a TV.

4
Why BCIs? 1

• The technology holds great promise for people who
  cant use their arms or hands normally because
  they have had spinal cord injuries or suffer from
  conditions such as amyotrophic lateral sclerosis
  (ALS) or cerebral palsy.
• BCI could help them control computers,
  wheelchairs, televisions, or other devices with
  brain activity.

5
The 3 major components of BCIs 4

• Ways of measuring neural signals from the human
  brain
• Methods and algorithms for decoding brain
  states/intentions from these signals
  and
• Methodology and algorithms for mapping the
  decoded brain activity to intended behavior or
  action.

6
Basic Signal-processing blocks of BCIs 5

• Preprocessing To remove noise and artifacts
  (mostly related to ocular, muscular, and cardiac
  activities) to enhance the SNR.
• Feature extraction Performs feature extraction
  and selection to detect the specific target
  patterns in brain activity that encode the users
  mental tasks, detect an event-related response,
  or reflect the subjects motor intentions.
• Classification Translating or associating these
  specific features into useful control (command)
  signals to be sent to an external device.

7
Invasive versus Non-invasive BCI 1

• Invasive techniques which implant electrodes
  directly onto a patients brain
• Noninvasive techniques in which medical
• scanning devices or sensors are mounted on
  caps or headbands read brain signals.

8
Invasive versus Non-invasive BCI 1

• Noninvasive approaches are less intrusive but can
  also read brain signals less effectively because
  the electrodes cannot be located directly on the
  desired part of the brain.
• Invasive techniques, however, require surgery and
  carry the risk of infection or brain damage.
• Noninvasive approaches ability to read signals
  from many points in the brain could help identify
  a wider range of brain activity.
• However, processing the large amount of data
  that neurons in multiple parts of the brain would
  generate would be difficult for BCI systems.

9
BCI Disciplines 1

• Nanotechnology
• Biotechnology
• Information technology
• Cognitive science
• Computer science
• Biomedical engineering
• Neuroscience
• Applied mathematics

10
Benefits of BCI? 2

• BCI might help us better understand how the human
  brain works in terms of reorganization, learning,
  memory, attention, thinking, social interaction,
  motivation etc.
• BCI research allows us to develop a new class of
  bioengineering control devices and robots to
  provide daily life assistance to handicapped and
  elderly people.
• Several potential applications of BCI hold
  promise for rehabilitation and improving
  performance, such as treating emotional disorders
  (for example, depression or anxiety).
• BCI can expand possibilities for advanced human
  computer interfaces (HCIs), by enhancing the
  interaction between the brain, the eyes, the
  body, and a robot or a computer.

11
BCI Potential Applications 1

• Healthcare (Ex Help disabled People)
• Automobile (Ex Help Drivers/pilots)
• Gaming (Ex Help users manipulate systems)
• Biometrics (Ex Pass-thought authentication)
• Unexpected Directions???

12
Carleton Universitys proposed BCI-based
biometric system 1

• Subjects use specific thoughts as passwords
  (called pass-thoughts).When someone
• tries to access a protected computer system or
  building, they think of their pass-
• thought.A headpiece with electrodes records the
  brain signals.
• The system extracts the signals features for
  computer processing,which includes
• identification of the feature subset that best
  and most consistently represents the
• pass-thought.The biometric system then compares
  the subset to those recorded
• for authorized users.

13
BCI Systems Challenges 1

• So new, researchers are still learning how to
  effectively implement it and adapt it to
  different needs.
• Tend to be very expensive, very large, making
  them impractical.
• Complex to use and require the involvement of
  Experts.
• Steep Learning curve for the Users (to learn how
  to use their thoughts to create the brain signals
  that generate desired actions)
• So new, many companies are not investing the
  time and money necessary for effective product
  development.
• An issue particularly noninvasive approaches is
  Signal Accuracy, the ability to accurately
  capture signals from the brain.
• Invasive BCI systems can experience problems with
  their electrodes since the brain recognizes and
  tries to remove foreign objects.

14
Current and future trends in noninvasive BCI 2

• Unimodal to multimodal - that is, simultaneous
  monitoring of brain activity using several
  devices and combining BCI with multimodal HCIs
• Simple signal-processing tools to more advanced
  machine learning and multidimensional data
  mining
• Synchronous binary decision to multidegree
  control and asynchronous self-paced control
• Open-loop to closed-loop control - neurofeedback
  combined with multimodal HCI and
• Laboratory tests to practical trials in the noisy
  real world environment.

15
References

• Sixto Ortiz Jr., "Brain-Computer Interfaces
  Where Human and Machine Meet," Computer, vol. 40,
  no. 1, pp. 17-21, Jan., 2007
• Andrzej Cichocki, Yoshikazu Washizawa, Tomasz
  Rutkowski, Hovagim Bakardjian, Anh-Huy Phan,
  Seungjin Choi, Hyekyoung Lee, Qibin Zhao, Liqing
  Zhang, Yuanqing Li, "Noninvasive BCIs Multiway
  Signal-Processing Array Decompositions,"
  Computer, vol. 41, no. 10, pp. 34-42, Oct., 2008
• Conference on Human Factors in Computing Systems
  CHI '08 extended abstracts on Human factors in
  computing systems Florence, Italy WORKSHOP
  SESSION Workshops table, Pages 3925-3928, 2008
• 1. F. Babiloni, A. Cichocki, and S. Gao, eds.,
  special issue, Brain-Computer Interfaces
  Towards Practical Implementations and Potential
  Applications, ComputationalIntelligence and
  Neuroscience, 2007
• P. Sajda, K-R. Mueller, and K.V. Shenoy, eds.,
  special issue, Brain Computer Interfaces, IEEE
  Signal Processing Magazine,Jan. 2008.
• ACM SIGACCESS Conference on Assistive
  Technologies Proceedings of the 9th international
  ACM SIGACCESS conference on Computers and
  accessibility Tempe, Arizona, USA SESSION
  Keynote addresss, Pages 1 2, 2007.