README.md 4 KB
Newer Older
Alexis Veracruz's avatar
Alexis Veracruz committed
1
# Neuro-ID
Alexis Veracruz's avatar
Alexis Veracruz committed
2
How reliable is EEG as a consistent identifier for individuals with Mild Traumatic Brain Injury (MTBI)?
Can Pervane's avatar
Can Pervane committed
3 4

## Scope
Alexis Veracruz's avatar
Alexis Veracruz committed
5
Pattern recognition and classification in time series data 
Alexis Veracruz's avatar
Alexis Veracruz committed
6

Alexis Veracruz's avatar
Alexis Veracruz committed
7
## Abstract
Alexis Veracruz's avatar
Alexis Veracruz committed
8
Raw brainwave data taken from an electroencephalogram (EEG) system has been shown to be unique for each individual.  Developing a machine learning algorithm to 
Alexis Veracruz's avatar
Alexis Veracruz committed
9 10
identify a specific person by their raw brainwave data can help to determine if a person’s brainwaves become unidentifiable after a concussion and therefore 
indicate changes in the brain.
Can Pervane's avatar
Can Pervane committed
11

Alexis Veracruz's avatar
Alexis Veracruz committed
12
## Methods
Alexis Veracruz's avatar
Alexis Veracruz committed
13
### <i> Tools </i>
14
Python package to analyse EEG Data: https://martinos.org/mne/stable/index.html
Can Pervane's avatar
Can Pervane committed
15

Alexis Veracruz's avatar
Alexis Veracruz committed
16 17 18 19 20 21 22
### <i> Subjects and Data Aquisition </i>
The 98 subjects included in the dataset were college aged males (18-24) Division I football players. Each player had a minimum 
of two EEG recording sessions. The first EEG measurements were recorded before the season began (baseline), and at the end of 
season (~6 months after). Some subjects had EEG retest sessions in order to record potential concussion, 20.4% of subjects indicated
concussion symptoms.  At the time of each measurement, the EEG was recorded for 4-15 minutes, the subjects were in an eye-closed 
resting state throughout the duration of the recording. During the recording sessions artifacts were identified and removed from 
the data analysis for accuracy. 
Alexis Veracruz's avatar
Alexis Veracruz committed
23

Alexis Veracruz's avatar
Alexis Veracruz committed
24 25 26 27 28 29 30
### <i> Biosignal Recording and EEG Parameterisation <i>
The EEG recordings were performed with electrodes secured at sites FP1, FP2, F7, F3, Fz, F4, F8, T3, C3, Cz, C4, T4, T5, P3, Pz,
P4, T6, O1, O2 with 19-channel equipment (WAVi).  A headset containing the electrodes is placed on the patient. The electrodes are 
examined to ensure quality contact.  If contact is unacceptable, conductive gel can be added and the eSocs can be rubbed along 
the scalp to exfoliate the location of the electrode in order to assist in gaining proper contact.  Once contact is deemed 
acceptable, a auditory P300 Eyes Closed Protocol is run. The patient is instructed to avoid any synchronized motions and blinks 
during the P300 test as this will affect the quality of the data.   
Alexis Veracruz's avatar
Alexis Veracruz committed
31
![Image of 10-20 array](https://en.wikipedia.org/wiki/10-20_system_(EEG)#/media/File:21_electrodes_of_International_10-20_system_for_EEG.svg)
Alexis Veracruz's avatar
Alexis Veracruz committed
32

Alexis Veracruz's avatar
Alexis Veracruz committed
33

Alexis Veracruz's avatar
Alexis Veracruz committed
34
### <i> Data </i>
Alexis Veracruz's avatar
Alexis Veracruz committed
35 36 37 38
The subject data is anonymized with number labels, each number represents a different subject. The letters attached to the numbers
represent the session (i.e. a=first session, b=second session etc.). Each session has two files a .raw and a .art. 
The .raw files contain the raw waves  and the .art contain artifacting data for each session. Use both files to build raw waves. 
<br><u>.art file key </u>
Alexis Veracruz's avatar
Alexis Veracruz committed
39
Same dimensions as the raw data. Gives a coloring to the EEG data, that shows how reliability of the data. 
Alexis Veracruz's avatar
Alexis Veracruz committed
40 41 42
* 0= Reliable (black)
* 1= Not Reliable (red)
* 2= May or may not be reilable,to be used or discarded (blue)
Alexis Veracruz's avatar
Alexis Veracruz committed
43 44 45 46 47 48 49

### <i> Waves in EEG </i>
<b> Delta:</b> 0-4 Hz
<br><b> Theta:</b> 4-8 Hz
<br><b> Alpha:</b> 8-13 Hz
<br><b> Beta:</b> 13-20 Hz
<br><b> Gamma:</b> 20-40 Hz
Alexis Veracruz's avatar
Alexis Veracruz committed
50

Alexis Veracruz's avatar
Alexis Veracruz committed
51 52 53 54
<b> Data Files </b>
* 98 subjects
* 19 columns, ~61440 rows (256 s time step total of 4 minute data)

Can Pervane's avatar
Can Pervane committed
55
## Analysis
Alexis Veracruz's avatar
Alexis Veracruz committed
56
1. Extract (𝜶, 𝛽, 𝛾,𝜃) Waveform
Alexis Veracruz's avatar
Alexis Veracruz committed
57
2. Divide into 2s epochs
Alexis Veracruz's avatar
Alexis Veracruz committed
58
3. Features extraction using neural netork
Alexis Veracruz's avatar
Alexis Veracruz committed
59 60 61 62 63 64 65 66 67 68
    a. FFT: static
    b. Short-Time FFT: FFR with window
    c. Compute static features for each epoch
    d. Channel coherence (each wave)
    e. Channel correlation Pearson (each wave)
4. Embedding a lower dimensional manifold 
    a. PCA 
    b. LDA
    c. Localized linear embedding (tSNE)
5. Analyse distances in reduced space between 2013 & 2014 baselines 
Can Pervane's avatar
Can Pervane committed
69 70 71 72 73 74 75 76 77

### Clustering
* Aggloremative
* k-means
* NNMF (Non Negative Matrix Factorization)

#### Measures
* Dynamics Time warping (Distance Meausure)

Alexis Veracruz's avatar
Alexis Veracruz committed
78 79 80 81
## Results
The data did not show siginificant differences in the channel cohernece in alpha frequency between concussed and non concussed subjects. Additional features need
to be analyzed in order to determine if EEG is a reliable identifier for a subject with mTBI.

Can Pervane's avatar
Can Pervane committed
82 83