Quiz 3 Cochlear & ML

Question 1

The three Hjorth parameters are

Answer 1

Fast way to compute characteristic of time-varying signal (mean power, root-mean-square frequency, and root-mean-square frequency spread).

Activity(signal power) = A = a0
Mobility(mean freq of power spectrum) = M = sqrt(a2/a0)
Complexity(change in freq) = C = sqrt(a4/a0)

a0 = variance
a2 = variance of first derivative of signal
a4 = variance of second derivative of signal

Popular in EEG analysis bc they are based on variance so its faster to compute

Question 2

Simple spatial filtering

Answer 2

Si = signal from channel i

To get electrical potential difference btwn two electrodes

Si,j = Si-Sj

Question 3

Laplacian Filtering

Answer 3

Second spatial filter method extracts local activity at electrode i by subtracting average activity in 4 orthogonal neighboring electrodes (x)

Si = Si - 1/4 sum(Si,i for all x)

Question 4

Common average referencing

Answer 4

Enhances the local activity at electrode i by subtracting the average over all electrodes

Si = Si - 1/N sum(Si,i=1 to N)

Question 5

Principal Component Analysis

Answer 5

Discover underlying statistical variability in the date and reduce dimensionality from L to a much small dimension. Achieves this by finding the direction of max variance in L-dimensional data

Av = lambdav

resulting L distinct eigenvectors are orthonormal (principa component vectors

larger variance (more distance btwn points)

Question 6

Behavior of Ag/AgCl electrode

Answer 6

Oxidation of silver on the electrode surface to siliver ions in solution at the interface

Ag <> Ag+ + e-

Ag+ ions combine with Cl- ions in solution to form AgCl

Ag+ + Cl- <> AgCl

Question 7

Electromyography

Answer 7

EMG is skeletal muscle signals, loud and obvious signal to read, signal read across muscle

Signals captures nerves within muscles firing action potentials. Easier to capture than EEG

types: needle, surface foam and gel, gold cup

Question 8

EMG Circuit

Answer 8

2 Electrodes on muscle > amplifer (Rg and reference) > HPF(remove lower freq noise) > LPF (remove higher freq noise) > Displau

Question 9

EMG signal capturing

Answer 9

Place electrode on single large skeletal muscle, reference away from monitored muscle. Don’t place on tendons bc they dont contain nerves

Question 10

Passive vs Active Electrode

Answer 10

Passive: wet or dry, silver or gold cup
Active: dry that are amplified before sending to BCI

Question 11

Invasive BCI

Answer 11

possible infections due to penetration of blood-brain barrier, encapsulation of electrodes in reactive tissue that degrade signal overtime, damage to brain circuits

Question 12

What is sound?

Answer 12

• electromagnetic radiation acoustic waves
• same direction of vibration as direction of travel
• waves exert pressure on medium

Question 13

Characteristic Impedance of Sound Medium

Answer 13

Z = P (acoustic pressure) / ~ ( RMS volume velocity)
I = P~ = P^2/Z

Question 14

How hearing works?

Answer 14

Outer ear (pinna + outer ear canal) gather sound
Pina: impedance transformations, sound amp, and direction finding

Middle ear connects to outer by tympanic membrane (eardrum) through the ear canal. Houses the ear ossicles - couple sound vibrations from eardrum via oval window into the cochlea

Inner ear cochlea is a fluid filled chamber where fluid movement is converted into nerve action potentials by hair cells.

Question 15

Sense of directionality

Answer 15

Differential arrival time at outer ear with arrive time and loudness at the auditory complex of the brain

Question 16

Cochlear Implant Components

Answer 16

Auditory nerve fibers are intact in patients, neurons can be made to fire with electrical stimulation of appropriate strength, duration, and orientation.

Microphone : picks up sound

External sound processor and power supply: filter, select, converts

Transmitting Circuitry: encodes signal and power are transmitted transcutaneously using RF

Receiver-stimulator package

Electrode Array

Question 17

Cochlear Implant Electrodes

Answer 17

Neurons at diff positions along cochlea respond to diff frequencies. Electrodes at tip of array stimulate lower freq and vice versa.

Maximize number of largely non-overlapping population of . Unavoidable dure to electrode sitting in highly conductive perilymph and are relatively far from their target neurons. Don’t want too many electrodes or frequencies will travel to neighboring electrodes

Question 18

Intensity of Sound

Answer 18

Determined by number of neurons activated and their firing rate. Dependent on the amplitude of the stimulus current. One can recreate normal neural response if enough independent spectral channels could be excited

Question 19

Safe Current Density

Answer 19

Nondamaging stimulation by using short duration biphasic current pulses delivered by platinum electrodes. Biphasic pulse ensures the electrochemical reactions that take place are reversible and localized to the electrode tissue interface

Question 20

Cochlear Implant Signal Processing Summary

Answer 20

Electrode array stimulate neuron response along a short section of basilar membrane. Diff electrodes activated by diff parts of sound spectrum. Range of stimulation is much smaller so processors must compress the range of sound

Question 21

Compressed analog principal

Answer 21

Using automatic gain control before the signal is passed through a bank of bandpass filters. Analog signals applied to electrodes

Question 22

Continuous interleaved sampling

Answer 22

Improved compressed analog principal

Apply short impulses to electrodes rather than analog signals to band pass filter. Electrodes are excited sequentially with small time intervals between them in a process CIS. Only one channel opened to prevent overlaps. Maximize method through filter spacing, envelope cutoff frequencies, shape of compression function, and stimulation rate

Question 23

Envelope Detection

Answer 23

1) lPF with cutoff 200-400Hz
2) Hilbert transform: vowel output by a single BPF

Question 24

Compression Function

Answer 24

Compression of the envelope transforms the large dynamic range of the acoustic signal into the small dynamic range required by electrical stimulation

Question 25

Stimulation Rate

Answer 25

Rate at which current pulses are delivered to each electrode (800-2,500 pps)

Question 26

What to include in an abstract?

Answer 26

Goal, contribution to methods, and how to demonstrate results

Question 27

What is machine learning?

Answer 27

scientific study of algorithms and statistic models that computer systems use to perform a specific task without explicit instructions and relies on pattern and inference

Data, Pattern, Algorithm, Computation

Question 28

Classification, vs regression vs unsupervised

Answer 28

Classification: discrete output category
Regression: continuous result (know position)
Unsupervised: interpret data

Question 29

Why ML for BCI?

Answer 29

Need to find and use complex patter in BCI data. Need to design/apply algorithms to conduct computations

Question 30

ML work flow

Answer 30

Data aq > data preprocessing > feature extraction > train/build model > test/eval > improve

Question 31

Basic BCI Circuit Layout

Answer 31

Electrode > 1-100k amp > anti-aliasing filter > ADC > BPF > Notch filter > EEG output

Question 32

Nyquist sampling theorem

Answer 32

continuous <> discrete

sample rate allows discrete sample to capture all the info in a continuous time signal of finite bandwidth

x(t) is spaces 1/(2F) a part

min sampling freq that will not lose signals info is 2x highest freq

Question 33

Mu rhythms

Answer 33

repeat at a freq of 7.5-12.5 hz
prominent when body is physically at rest
occur over the motor cortex

form of alpha wave (8-13 hz)

Question 34

Input and outputs of ML model

Answer 34

Input: feature vectors
Output: classification/clustering results

X1, X2, X3&raquo_space; h(hypothesis)&raquo_space; Y1’,Y2’..

where Y1’~= Y1

Question 35

What is a feature vector?

Answer 35

feature, attribute, input, etc.

Question 36

Feature space

Answer 36

You never know if you covered the space completely, hence why you need large sample size.

Question 37

Binary Classification

Answer 37

Classification > Supervised > learn a function that maps an input too output based on example input-output pairs. Find a boundary btwn two classes based on the labeled training data

Find h based on the Y of X

Question 38

Linear Discriminant Analysis

Answer 38

Has some similarity to PCA but focuses on maximizing separability among categories

Find a hyper plane, different categories are optimally separated. Means as far a possible and variance as small as possible

Hyper plane = h(X) = 0 = W^TX + W0
assign label 1 or -1
W^TX + W0 >0 then label 1
W^TX + W0 <0 then -1