Motor Imagery Signal Classification using EEG and ECoG signal for Brain
Computer InterfaceMd. Redwan Islam
Student no-1006066, Umme Fatema
Student no – 1006194,
Supervised by: Dr. Mohammed Imamul Hassan Bhuiyan,
Professor,Department of electrical & electronic engineering,
Bangladesh university of engineering & technology.
Introduction
› Brain Computer interfacing(BCI) is a communication system where commands or messages are sent to a device or computer by means of one’s mind or brain activity.
› BCI is an emerging technology dealing with computer-aided control using exclusively brain activity, and has found application across bio-engineering fields and in neuroprosthetics.
Importance of BCI• Communication through mind is an advanced and
simpler way of interaction for fully paralyzed or partially paralyzed patients communication through mind is easier or only possible way.• Improves the life style.• Gives severely paralyzed people another way to
communicate, a way that does not depend on muscle control
Data acquisition for BCI
• Implanted directly into the grey matter of the brain • Produce the highest quality signals of BCI devices• Prone to scar-tissue build-up, causing the signal to become weaker,
or even non-existent, as the body reacts to a foreign object in the brain.
Invasive BCI
• Implanted inside the skull but rest outside the brain.• Produce better resolution signals than non-invasive BCIs.• Have a lower risk of forming scar-tissue in the brain than fully
invasive BCIs.
Partially Invasive BCI
• Electrodes are placed on specified positions on the scalp. • Relatively poor spatial resolution • Easy to wear and do not require surgery.
Non-Invasive BCI
ECoG (Electrocorticography)› Partially non-Invasive BCI data acquisition technique. › Electrodes placed directly on the exposed surface of the
brain to record electrical activity from the cerebral cortex.
EEG (Electroencephalography)› Noninvasive BCI data acquisition method› Electrodes placed along the scalp, although
invasive electrodes are sometimes used in specific applications.
Objective› To develop a method for 2 class classification of
partially invasive BCI using ECoG signal. › To develop a method for 2 class classification of
non-invasive BCI using EEG signal.› To compare the classification accuracy of the
developed methods with other previously proposed methods using Brain Computer Interface BCI Competition databases.
General scheme of BCI
Determination of cognitive state
Machine learning
Signal processing
Data acquisition
Classification of ECoG signal› Since placed directly on the exposed surface of the
brain, ECoG signals are obtained at a lower noise and higher sampling rate.
› Typical sampling rate is 1kHz. › We are using BCI Competition III dataset I. The
dataset contains ECoG signals corresponding to imagined left pinky and tongue movement.
Database I:BCI competition III dataset I
• The subject was not a lock-In patient but suffered fromepilepsy. • Recording consisted of 278 trails each either left pinky or tongue
movement. • 8×8 ECoG platinum electrode grid which was placed on the
contralateral (right) motor cortex.• Covered right motor cortex completely and due to its size
(approx. 8×8cm), also partly covered surrounding cortexareas. • Sampling frequency was 1000Hz.• To avoid VEP (visually evoked potential), the recording intervals
started after end of 0.5s visual cue.
Schematics for Classification of imagined left pinky vs tongue from
ECoG signal (method 1)
Data acquisition
Ratio of theta band power and alpha
band power
Statistical classification
Imagined movement
identification
Feature extraction
Average p value = 0.000356
Classifiers used for classification › Discriminant classifier› KNN classifier› SVM classifier
Results›Per sample validation accuracy was calculated.
›The Highest Accuracy was obtained by using SVM classifier with radial bias kernel and with a spread of 16 and it was about 87.6%.
Area Under ROC Curve
0.7715
Sensitivity
76.21%
Specificity
81.71%
Classification Accuracy with variation of distance metric and number of neighbors
in KNN classification
Classification Accuracy with variation of radial bias in SVM classifier
Comparison with other methods using BCI Competition III dataset I
Researcher & Publication Proposed method Reported accuracy (%)Hai-bin Zhao et.al. [Classifying ECoG Signals Using Probabilistic Neural Network] [Information Engineering (ICIE), 2010 WASE International Conference on (Volume:1 )]
Common Average Filter Downsample Channel selection by observation Bandpower Windsorizing PNN
85.6
Onder AYDEMIR et. Al. [Wavelet Transform Based Classification of Invasive Brain Computer Interface Data][RADIOENGINEERING, VOL. 20, NO. 1, APRIL 2011 ]
Wavelet coefficient mean & variance SVM classifier
86.1
We obtained higher accuracy and using further feature selection algorithm, feature length can also be reduced for faster classification.
Classification of EEG signal› Since placed on the scalp, EEG signals are obtained
at a with noise due to probe movement and neural activity of the skin.
› Typical sampling rate is 100Hz. › We are using BCI Competition IV dataset I which
contains imagined left hand and right hand movement.
Database II:BCI Competition IV Dataset I
›Recorded from a healthy person. ›Cues were displayed for a period of 4s during which the subject was instructed to perform the cued motor imagery task.
Schematics for Classification of imagined left hand and right hand movement from EEG
signal (method 2)
Data acquisition
Cepstrum analysis
Channel Selection
Common Spatial
Patterns
Statistical classificati
on
Cognitive movement identificati
on
Cepstrum Analysis. › Cepstrum analysis is a nonlinear signal processing
technique which is frequently used in speech processing.
› The cepstrum of a sequence x is calculated by finding the logarithm of the magnitude of the Fourier transform of x, then the inverse Fourier transform of the resulting sequence.
Signal |FFT| Log IFFT
Common Spatial Patterns› Common spatial pattern (CSP) is a mathematical
procedure which determines spatial filtersthat maximize the variance of signals in one class and simultaneously minimize the variance of signals in the other class.
› After obtaining the transformed projection, the data matrix is classified using the mentioned classifiers.
Form separate matrix for two classes
Determine normalized spatial covariance
Do generalized eigenvalue
decompositionUse the spatial filters
to the data matrix
For 2 class classification, one of
the class should be of minimum and another should be of maximum
variance.
Feature extraction
Average P values = 0.0004
Results obtained from different classifiers
› Using KNN classifier, 100% accuracy was obtained. › Using SVM classifier, linear kernel gave a lower
accuracy, but the Gaussian kernel gave 98.9% accuracy. Area Under ROC Curve
0.98
Sensitivity
97.3%
Specificity
98.6%
Comparison with other methods using BCI Competition IV dataset I
Researcher & Publication
Proposed method Reported accuracy (%)
Cheolsoo Park et.al. [Classification of Motor Imagery BCI UsingMultivariate Empirical Mode Decomposition] [IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, VOL. 21, NO. 1, JANUARY 2013]
MEMD Selection of IMF CSP classification
85.6
We obtained about 98.9% success. Besides we used cepstrum analysis which avoids splitting of signals into multiple signals and only changes the domain of the signal which is also suitable for real time BCI.
Thank You
Any Question?