Development of a low cost pc-based single-channel eeg monitoring system
EE Senior Project Presentation (2)
1. EpiCap
EE Senior Project
SeizureA mobile real-time epileptic
seizure detector using only a
MCU and a lot of Machine
Learning
Hector D. Villarreal
Jose Galindo
2. What is Epilepsy?
Epilepsy is the 4th most common neurological
disease in the world.
It is a chronic disease that produces seizures that
affect control of the body motor functions.
In a third of patients with epilepsy the disorder
becomes refractory and randomly subjects patients
to seizures.
3. In simple terms...
Build a real-time wearable non-invasive
epileptic seizure detector that runs on a MCU
powered by a reasonably small battery.
7. Still an open research question...
What is the problem with the
published approaches?
Causality
Diagnosis
tool (CAD)
Clinical
environment
MATLAB
(Non-RT)
8. We propose...
Filtering
Notch + Bandpass
MCU
Feature
Calculation
8 simple features x
channel
SVM
Classification
Just a dot product.
EpiCap
Ch A
Ch B
Ch C
3 chs
51 feats
Decision>0? epileptic:normal
9. Filtering
Multi-stage filtering for acquiring the most accurate EEG
signals.
Common noise sources include:
• 60Hz from AC power
• Ambient background noise
• Amplification stage noise
10. Filtering
60Hz notch filter to be used
as first stage of amplification
to immediately cut off this
spike in noise from the
source.
11. Filtering
Second stage of amplification and noise reduction to be used
is digitally using an FIR low-pass filter with a cutoff frequency
of 2.5 kHz.
14. One task, two architectures
● Data selection (16 bits)
● Digital filtering
● Epoch segmentation
● Feature extraction
● Majority class reduction
● Classifier training
● Classification
● Performance tuning
Python
Intel i7 2.2 GHz, 64 bit, 8 GB
RAM
● Feature Extraction
● Classification
TI MCU
(TM4C123X)
ARM Based 80 MHz, 32 bit,
256KB Flash
ADC 12 bits
15. Python: Preparing data for classification
Data selection
Labeled EEG data was
provided by the HifoCap
Research Group (EE).
One patient,
115 hours
22 seizures
21 channels
256 S/s (Hz)
Digital filtering
FIR Low pass
Fpass= 55 Hz
Fstop= 60Hz
65 taps
Epoch creation
Epilepsy is already
diagnosed, we know the
parts of the brain were
the seizure originates.
3 channels
CZ, F3, C3
1s windows
256 samples per
16. Feature extraction...
O(n )
2
We are limited to features with a
maximum complexity of n^2, in
order to maintain real-time
operation and low power
consumption.
Energy RMS Line-length
Mean Rhythmicity
Standard
deviation
Specialized Features
Amplitude Features
Total
power
Power per bandPeak frequency
Power Features
34. C=1e-7, kernel=linear
The best kernel and C hyperparameter were
found using an exhaustive Grid Search
algorithm. Polynomial and RBF kernels,
generated only marginal improvements.
35. Support Vector Machine
● If D(x) > 0, the sample contains an epileptic
seizure.
● If D(x) < 0, the sample is not a seizure.
● D(x) = 0 is impossible.