Title: Brain Computer Interface in BMI
1Brain Computer Interface in BMI
Ioannis Papavasileiou Computer Science
Engineering Department The University of
Connecticut 371 Fairfield Road, Unit 4155 Storrs,
CT 06269-2155
papabasile_at_engr.uconn.edu
2What is BCI?
- BCI is
- System that allows direct communication pathway
between human brain and computer - It consists of data acquisition devices, and
appropriate algorithms - How is it used in BMI
- Clinical research
- Disease-condition detection and treatment
- Human computer interfaces for
- Control
- Emotions detection
- Text input - communication
3Research areas involved
- Computer science
- Data mining
- Machine learning
- Human computer interaction
- Neuroscience
- Cognitive science
- Engineering
4Key challenges
- Technology-related
- Sensor quality low SNR
- Supervised learning curse of dimensionality
- System usability
- Real-time constraints
- Non-invasive EEG information transfer rate is
approx. 1 order of magn. lower - People-related
- People are not always familiar with technology
- Preparation training phases are not fun!
- Concentration, attention consciousness levels
- Task difficulty
5BCI components
- Data acquisition
- Electroencephalography (EEG)
- Electrical activity recording
- Invasive or not
- Functional Near Infrared Spectroscopy (fNIRS)
- Recording of infrared light reflections of the
brain - Functional magnetic resonance imaging (FMRI)
- Detection of changes in blood flow
- Data Analysis
- Data mining machine learning
- Decision making
- Output Control
- HCI
6Typical BCI architecture
7Electroencephalography (EEG)
- What is it
- Recoding of the electrical activity of the brain
- Types
- Invasive
- Non-invasive
- Properties
- High temporal resolution
- Low spatial resolution
- Scalp acts as filter!
8International 10-20 standard
- Electrodes located at the scalp at predefined
positions - Number of electrodes can vary
9The EEG waves
- Alpha occipitally
- Beta frontally and parietally
- Theta children, sleeping adults
- Delta infants, sleeping adults
10fMRI
- Functional magnetic resonance imaging
- Fact
- Cerebral blood flow and neuronal activation
coupled - Detection of blood flow changes
- Use of magnetic fields
- High spatial resolution
- Low temporal resolution
- Clinical use
- Assess risky brain surgery
- Study brain functions
- Normal
- Diseased
- Injured
- Map functional areas of the brain
11fNIRS
- Functional Near Infrared Spectroscopy
- Project near infrared light into the brain from
the scalp - Measure changes in the reflection of the light
due to - Oxygen levels associated with brain activity
- Result absorption and scattering of the light
photons - Used to build maps of brain activity
- High spatial resolution
- lt1 cm
- Lower temporal resolution
- gt2-5 seconds
12BMI clinical applications
- Diagnose
- Epilepsy seizures
- Brain-death
- Alzheimers disease
- Physical or mental problems
- Study of
- Problems with loss of consciousness
- Schizophrenia (reduced
- Delta waves during sleep)
- Find location of
- Tumor
- Infection
- bleeding
13Sleep disorders mental tasks
- Sleep disorders study
- Insomnia
- Hypersomnia
- Circadian rhythm disorders
- Parasomnia (disruptions in slow sleep waves)
- Mental tasks monitoring
- Mathematical operations
- Counting
- Etc.
14Neurofeedback
- Applications in
- Autistic Spectrum Disorder (ASD)
- Anxiety
- Depression
- Personality
- Mood
- Nervous system
- Self control
15Feedback EEG-BCI architecture
16Typical data analysis process
- Data acquisition and segmentation
- Preprocessing
- Removal of artifacts
- Facial muscle activity
- External sources, like power lines
- Feature extraction
- Typically sliding window
- Time-frequency features
- Latency introduced
17Feature extraction
- Model-based methods
- Require selection of the model order
- FFT (Fast Fourier Transform) based methods
- Apply a smoothing window
- Features used
- Specific frequency band power
- Band-pass filtering and squaring
- Autoregressive spectral analysis
- Many times a feature selection or projection is
done to reduce the huge feature vectors
18Data Classification
- Typical classifiers used
- Artificial Neural Networks (ANN)
- Linear Discriminant analysis (LDA)
- Support Vector Machines (SVM)
- Bayesian classifier
- Hidden Markov Models (HMM)
- K-nearest neighbor (KNN)
- Parameters for each classifier can affect the
performance - of hidden units in ANN
- of supporting vectors for SVMs
- Etc.
19Human computer interaction
- BCIs are considered to be means of communication
and control for their users - HCI community defines three types
- Active BCIs
- Consciously controlled by the user
- E.g. sensorimotor imagery (multi-valued control
signal) - Reactive BCIs
- Output derived from reaction to external
stimulation - Like P300 spellers
- Passive BCIs
- Output is related to arbitrary brain activity
- E.g. memory load, emotional state, surprise, etc.
- Used in assistive technologies and rehabilitation
therapies
20BCI Assistive Technologies
- Communication systems
- Basic yes/no
- Character spellers
- Virtual keyboards
- Control
- Movement imagination
- Cursor
- Wheelchairs
- Artificial limbs prosthesis
- Automation in smart environments
- Current BCI systems have at most 10-25
bits/minute maximum information transfer rates - It can be valuable for those with severe
disabilities
21P300 spellers
- Most typical reactive BCI
- 3-4 characters / min with 95 success
22P300 wave
- Event related potential (ERP)
- Elicited in the process of decision making
- Occurs when person reacts to stimulus
- Characteristics
- Positive deflection in voltage
- Latency 250 to 500 ms
- Typically 300 ms
- Close to the parietal lobe in the brain
- Averaging over multiple records required
23Other ERP uses
- Lie detection
- Increased legal permissibility
- Compared to other methods
- ERP abnormalities related to conditions such as
- Parkinsons
- Stroke
- Head injuries
- And others
- Typical ERP paradigms
- Event related synchronization (ERS)
- Event related de-synchronization (ERD)
24Other Control BCI paradigms
- Lateralized readiness potential
- Game control
- 12 seconds latency
- Negative shift in EEG develops before actual
movement onset - Steady-state visually evoked potentials (SSVEPs)
- Slow cortical potential (SCP)
- Imaged movements affect mu-rhythms
- They shift polarity ( or -) of SCP
- Sensorimotor cortex rhythms (SMR)
- EMG
25SCP SMR vs P300
- Typically SCP and SMR BCIs require significant
training to gain sufficient control - In contrast P300 BCIs require less as they record
response to stimuli - However, they require some sort of stimuli like
visual (monitor always in place) or audio - Also SCP BCIs have longer response times
26Binary speller control
- User imagines movement of cursor
- Typically hand movement
- The goal is to select a character
27Wheel chair control
- All the mentioned BCI paradigms have been applied
to wheelchair control - Either using a monitor for feedback
- Or active paradigms as sensorimotor imagery (SMR)
- Similar approaches have been applied to robotics
- Artificial limbs
- etc
28Environment control
- BCIs used by disabled to improve quality of life
- Operation of devices like
- Lights
- TV
- Stereo sets
- Motorized beds
- Doors
- Etc
- Typically use of P300, SMR and EMG related BCIs
29EMG-based human-robot interface example
- Motion prediction based on hand position
- EMG pattern classification as control command
- Combination of both yields motion command to
prosthetic hand
30Emotions detection
- Use of facial expressions to imply user emotions
- ERD/ERS based BCIs
- Emotional state can change the asymmetry of the
frontal alpha - P300 - SSVEP
- Emotional state can change the amplitude of the
signal from 200ms after stimulus presentation
31BCIs for recreation
- Games
- EPOC headset
- Mindset
- Virtual reality
- Outputs of a BCI are
- Shown virtual environment
- Creative Expression
- Music
- Generated form EEG signals
- Visual art
- Painting for artists who are locked in as a
result of ALS amyotrophic lateral sclerosis
32Security and EEG
- EEG has been used in user authentication
- Every brain is different
- Different characteristics of EEG waves are used
in user authentication - Pros
- User has nothing to remember
- Harmless
- Automatically applied
- Cons
- User has to wear an EEG headset
- Accuracy is still not 100
- Still not used in practice
33Thank you!