Brain Computer Interfaces on Track to Home: Results and Lessons Learnt

Eloisa Vargiu

EURECATBarcelona

Rome, July 31, 2015

Brain Computer Interfaces on Track to Home: Results and

Lessons Learnt

2

The BackHome project

FP7/2007-2013grant agreement n. 288566

3

BackHome is the first European research project aimed at delivering the ambitious, but critical, step to bring BNCI

systems to mainstream markets

The Objectives To study the transition from the hospital to the home To learn how different BNCIs and other assistive

technologies work together To reduce the cost and hassle of the

transition from the hospital to the home

4

BackHome is aimed at… …producing applied results, developing

o new and better integrated practical electrode systems

o friendlier and more flexible BNCI softwareo better telemonitoring and home support tools

5

Practical Electrodes

6

Practical electrode systems

Its design is completely different from all other devices and it sets a new standard of usability

The dry electrode version is based on the worldwide proven g.SAHARA electrodes

The tiny and lightweight device is attached to the EEG cap to avoid cable movements and to allow completely free movements

7


8


9


10

Flexible BNCI software

11


12

Flexible BNCI softwareSmart Home Control

13

Flexible BNCI softwareSmart Home Control Speller

14


Web Browsing, e-mail and social networks

15


Web Browsing, e-mail and social networksMultimedia player

16



Brain Painting

17



Brain PaintingCognitive Rehabilitation Games

18

Telemonitoring and Home Support

19


20

Home

4 in 1:DoorMotionTemperatureLuminosity

3 in 1:MotionTemperatureLuminosity

z-wave

smartphone

Raspberry pi

21

Therapist Station

22

Therapist Station

23

Therapist Station

24

Therapist Station

25

Therapist Station

26

Therapist Station

27

Intelligent Monitoring

28


PP Its goal is to preprocess the data iteratively sending

a chunk c to both ED and RA according to a sliding window approach

Starting from the overall data streaming, the system sequentially considers a range of time |ti - ti+1| between a sensor measure si at time ti and the subsequent measure si+1 at time ti+1

The output of PP is a window c from ts to ta, where ts is the starting time of a given period and ta is the actual time

29


ED It aims to detect and inform about emergency

situations for the end-users and about sensor-based system critical failures

Regarding the critical situations for the end-users, simple rules are defined and implemented to raise an emergency, when specific values appear on c

Regarding the system failures, ED is able to detect whenever user’s home is disconnected from the middleware as well as when a malfunctioning of a sensor occurs

Each emergency is a pair <si; lei> composed of the sensor measure si and the corresponding label lei that indicates the corresponding emergency

30


AD Its goal is to recognize

activities performed by the user

To recognize if the user is at home or away and if s/he is alone, we implemented a solution based on machine learning techniques

The output is a triple <ts; te; l>

31


EN It is able to detect events to be notified Each event is defined by a pair <ti; l> corresponding

to the time ti in which the event happens together with a label l that indicates the kind of event

Currently, this module is able to detect the following events: o leaving the homeo going back to homeo receiving a visito remaining alone after a visito going to the bathroomo going out of the bathroomo going to sleepo awaking from sleep

32


SC Once all the activities and events have been

classified, measures aimed at representing the summary of the user’s monitoring during a given period are performed

Two kinds of summary are providedo Historicalo Actual

A QoL assessment system is also provided to assess a specific QoL itemso Mobilityo Sleepingo Mood

33


RA It is aimed at advising therapist about one or more

risky situations before they happen The module executes the corresponding rules, defined

by therapists through the healthcare center, at runtime

A rule is a quadruple <i; v; o; ar>

34

Results

35

Cedar Foundation (Belfast) Control Group: N= 5 End User Group: N=5

(1 F, M= 37 yrs ± 8.7, Post ABI M= 9.8 yrs, ±3.7) Home Users: N=3

University of Würzburg Control User Group (gel-based): N=10

(6 F, M: 24.5 yrs ±3.4) Control User Group (dry electrodes): N=10

(9 F, M: 24.4 yrs ±2.7) End User Group: N=6

(2 F, M=47.3 yrs ± 11)

End-users

36


37


38


39


40


41


42


43


44

Lessons Learnt

45

BCI can now be considered as an assistive technology

To move a technology from the lab to a real home is a very difficult task

Testing in a controlled environment is essential Data are nothing if you don’t know how to read them

A user center design approach helps in building a system accepted by end-users

A continuous assistance must be given tocaregivers

Therapists and engineers don’t speak thesame language

Lessons learned

46

BackHome

Acknowledgements

Web• www.Backhome-FP7.eu

LinkedIn• BackHome-FP7-Research-Innovation

Twitter• @BackHomeFP7

Youtube• BackHomeFP7

Consortium EURECAT/BDigital Team

And also…Javier BaustistaEloi CasalsJosé Alejandro CorderoJuan Manuel FernándezJoan ProtaAlexander Steblin

47

[email protected]

Brain Computer Interfaces on Track to Home: Results and Lessons Learnt

Healthcare

bnci systems

users home

home support tools

therapist station

practical electrodes

range of time ti ti

starting time

actual time