NeuroPhone : Brain-Mobile Phone Interface using a Wireless EEG Headset

Post on 25-Feb-2016

30 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

DESCRIPTION

NeuroPhone : Brain-Mobile Phone Interface using a Wireless EEG Headset . Andrew T. Campbell, Tanzeem Choudhury , Shaohan Hu, Hong Lu, Matthew K. Mukerjee ∗, Mashfiqui Rabbi, and Rajeev D. S. Raizada Dartmouth College, Hanover, NH, USA . Motivation. - PowerPoint PPT Presentation

Transcript

{

NeuroPhone: Brain-Mobile Phone Interface using a Wireless EEG Headset

Andrew T. Campbell, Tanzeem Choudhury, Shaohan Hu, Hong Lu, Matthew K. Mukerjee∗, Mashfiqui Rabbi, and Rajeev D. S. Raizada Dartmouth College, Hanover, NH, USA

Motivation

Control your mobile device without touching or speaking

Make control easier in environment require less movement or silence

library classroom

The narrow version for mobile device

Control many device in a more effortless way

Determent human emotion for many purpose

The generalized version

Terminology

Electroencephalography Device that recording electrical activity of

brain

EEG

P300 is a pattern of certain electrical brain activity

It is usually happened when people try to reacting to certain thing

Typical representation is the record of EEG have a “delay” for 300 to 600 ms

P300

A way to generalize data, to figure out a pattern. So that we can use the pattern to determent or predict new situation

Machine Learning

Y = aX0 + bX1 + cX2 Classification Problem

Test Environment

iPhone

Emotiv EPOC EEG headset

Windows Laptop

Application

P300 Mode

P300 Mode

Similar to P300 mode, but user must winking their eyes

Wink mode

Result

P300 Mode

Winking Mode

The application take very little resource Which means devices like smart phone

could totally hand the brain control system

An acceptable Accuracy

Shows

Algorithm is not perfect yet High battery consuming EEG hardware not good enough

Limitations

Expensive Very little company working in this field A lot of noise in the information Too big Too ugly

EEG

EEG

Conclusion

It is a concept prove application It proved that brain control on mobile

device can be done The compute unit is powerful enough

already The algorithm can be improve EEG still need improve

Question?

Thank you

top related