SlideShare une entreprise Scribd logo
1  sur  16
WP 5 Presentation
Christoph Hintermüller (g.tec)
Proposed Structure for the Talk
• goals
• achievements
• problems
• outlook/ future work
• lessons learned
• list of publications
11.06.2013 WP 5 Presentation 2
Goals
• Develop an EEG based brain-computer interface for
robot control
• Usage of the BCI system for goal oriented and
continuous control
• Test the BCI system for different applications
11.06.2013 WP 5 Presentation 3
Goals
11.06.2013 WP 5 Presentation 4
• Milestones
M3: First release of BCI (Month 12)
M4: First ALIAS pilot (Month 12)
M7: Second ALIAS pilot (Month 24)
M9: Final ALIAS pilot (Month 35)
• Deliverables
D5.1: Rapid Prototyping Environment (Month 6)
D5.2: BCI System (Month 12)
D5.3: Tests of the BCI System with the Robot (Month 36)
• Gantt
Y1 Y2 Y3
Task 1 2 1 2 1 2
3
05. Jan Setup Rapid Prototyping D5.1
05. Feb Development of P100, SSVEP and oscillatroy BCI D5.2
05. Mrz Interfacing BCI system to robot D5.3
05. Apr BCI system tests with robot D5.3
Milestones M3,4 M7 M9
Activity
WP5 Brain Computer Interface
Achievements
11.06.2013 WP 5 Presentation 5
• 2 x g.MOBIlab 8 channel devices including EEG cap,
active electrodes, Matlab Simulink BCI Models
(SSVEP, P300), g.BSanalyze, EEG processing
toolboxes
• Installed at Fraunhofer FhG, g.tec, Jade
Achievements
11.06.2013 WP 5 Presentation 6
• First dry electrode system that works for motor imagery, SSVEP and
P300 (same accuracies reached for all)
• Whole frequency range available: 0.1-40 Hz
• First dry electrode system that covers extended 10/20 system on
frontal, central, parietal and occipital sites
• More low frequency components in the EEG spectrum below 3 Hz
• Careful montage required and more sensitive to surrounding noise
• Group studies submitted in March 2011 to Journal of Neural
Engineering and BCI conference in Graz 2011.
Achievements: SSVEP P-Statistics
11.06.2013 WP 5 Presentation 7
• Rectification of SNR signals to
zero sample median.
• Soft-Max transformation used to estimate probabilities p
• Sample assigned to Virtual Zero Class if 1 – p < Confidence interval
Achievements: P300 decisions using p-statistic
• Online selection of # of flashes: p-statistics based
• Residual error limits: 0.15% decision, 25% P300 validation
• Minimum 2, maximum 15, average 7 flashes
11.06.2013 WP 5 Presentation 8
min mean max min mean max min mean max
off 2,33 6,94 14,11 6,00 7,33 9,33 3,17 6,58 9,67
30,00 2,44 7,11 14,78 7,67 7,67 7,67 3,56 6,51 10,22
25,00 2,44 7,11 14,78 5,00 6,33 9,00 3,78 7,13 10,56
20,00 2,44 7,22 14,44 5,00 6,93 9,00 3,44 7,02 10,78
15,00 2,44 7,16 14,44 3,33 8,06 12,00 3,44 7,06 10,56
10,00 2,44 6,80 14,00 4,33 6,13 8,33 3,33 7,56 12,44
5,00 3,56 7,33 14,00 5,57 6,43 7,29 4,22 8,64 12,22
2,50 3,67 7,14 13,67 5,17 8,39 11,67 4,33 9,00 13,56
1,00 4,11 7,06 12,11 6,71 8,79 10,86 4,22 8,57 13,56
0,50 3,25 5,71 10,13 5,86 7,93 10,00 4,56 8,22 12,89
0,10 5,43 6,52 8,57 2,80 5,40 8,00 4,56 8,03 12,56
TTP
FTP
FP
True positive selection
Positiv selection, false assignment
False Positiv selection
Total spelled 28 char
Total ignored 28 char
Residal Error
Probability [%]
Parameters
considered
Average Values: count(p>1-r) = 1
# Repetitions
P3selectionerrorprobability[%]
0,15
TTP FTP FP
Achievements: BCI ACTOR
11.06.2013 WP 5 Presentation 9
Network (UDP)
Communication
Interface
Structure
• General structure
– UI is controlled with the BCI system
( MI BCI, SSVEP BCI, P300 BCI)
– AIM: Adaptive Interface Module
• Grouping of applications
• Receives real time updates
• Prepares information for UI
– Application group: applications controlled by
one network node (e.g. Home Automation)
• XML string from UDP message or local file
– Mask layout and structure
– ICONs
– Command Types and Instructions
• Initialized via UDP socket
Achievements: BCI ACTOR
11.06.2013 WP 5 Presentation 10
Mask
Description
Chat Mask
Contact Mask
Achievements: Integration
• with Dialog Manager
• with Gui
11.06.2013 WP 5 Presentation 11
Component/Service Status Paradigm
Entertainment Yes
P300
Games Yes
Audio Books Yes
TV Yes
WII Switching to WII
Communication Yes
Skype outgoing call Yes
Skype incoming call Yes/Schiedlberg
Initiate emergency
call
Yes
Web-browser Loading browser
Call/Dismiss No/2013
SSVEPDirect emergency call No/2013
Cancel emergency call No/2013
Paradigm SOCI BCI
processing
Integrated
P300 single
character
Yes
Yes YES
P300 row
column
No
Yes -
SSVEP
onscreen
Yes
Yes -
SSVEP
LED
-
Yes No
Achievements: Fieldtrials 2012
11.06.2013 WP 5 Presentation 12
Problems
11.06.2013 WP 5 Presentation 13
Outlook / Future Work
• Ongoing developments
• Integration signal check module
• Combination: accuracy based selection of optimal # of flashes
and p-statistics
• SOCI multi line text
• SOCI icon size independent of mask size and window size
• SOCI support for greyscale, color Icons
• SOCI elimination shared network drive
• ACTOR protocol improvements and speedup
• User tests
• Munich in coordination with TUM
• Only tested with ALIAS members
11.06.2013 WP 5 Presentation 14
Lessons Learned
11.06.2013 WP 5 Presentation 15
List of Publications
• Papers, Book Chapters
• C. Guger, G. Krausz, B. Allison, G. Edlinger (2012): Comparison of dry and gel based
electrodes for P300 brain–computer interfaces. Front. Neurosci. 6 :60. doi:
10.3389/fnins.2012.00060.
• Fazel-Rezai R, Allison BZ, Guger C, Sellers EW, Kleih SC and Kübler A (2012): P300 brain
computer interface: current challenges and emerging trends. Front. Neuroeng. 5:14. doi:
10.3389/fneng.2012.00014
• J.A. Wilson; C. Guger, G. Schalk: BCI Hardware and Software. In Jonathan R. Wolpaw,
Elizabeth Winter Wolpaw (2012): Brain-Computer Interfaces: Principles and Practice. Edited by:
Jonathan R. Wolpaw, Elizabeth Winter Wolpaw. Publisher: Oxford Univ Pr. Publication Date: 1.
Edition, January 24, 2012. ISBN: 978-0-195-38885-5.
• Lechner, R. Ortner, F. Aloise, R. Prueckl, F. Schettini, V. Putz, J. Scharinger, E. Opisso, U.
Costa, J. Medina, C. Guger (2012): Comparing the accuracy of a P300 speller for people with
major physical disability. In Proceedings of ICCHP. July 11 – 13,2012. Linz, AT.
• C. Hintermüller, C. Kapeller, G. Edlinger, C. Guger, BCI Integration: Application Interfaces, In
Brain Computer Interface, Edited by: Fazel-Razi, Intech, 2013, ISBN 980-953-307-960-3
• Fares/Conferences
• IEEE Biorob 2012, Rom, IT. June 24 – 28, 2012.
• Measuring Behaviour 2012. Aug 28 – 31, 2012. Utrecht, NL
• Joint Annual Meeting ECNS - ISNIP - ISBET – EPIC. Sep 12 – 16, 2012. Bristol, TN, US.
11.06.2013 WP 5 Presentation 16

Contenu connexe

En vedette

Tulip Festival
Tulip FestivalTulip Festival
Tulip FestivalIHTDO
 
Ocf Li Quick Presentation Company
Ocf Li Quick Presentation CompanyOcf Li Quick Presentation Company
Ocf Li Quick Presentation CompanyJeremyLutterloch
 
Liberação motora.
Liberação motora.Liberação motora.
Liberação motora.Ipsun
 
24 04 la segunda gsma
24 04 la segunda gsma24 04 la segunda gsma
24 04 la segunda gsmaAtelmo
 
Jogos e atividades
Jogos e atividades  Jogos e atividades
Jogos e atividades Ipsun
 
Riesgos en Internet
Riesgos en InternetRiesgos en Internet
Riesgos en Internetguest392791
 
Ky nang quan ly thoi gian
Ky nang quan ly thoi gianKy nang quan ly thoi gian
Ky nang quan ly thoi gianThao Media 99
 
Manish g badlani(130210125002)
Manish g badlani(130210125002)Manish g badlani(130210125002)
Manish g badlani(130210125002)manishgbadlani
 
A evolução da ciência psicológica
A evolução da ciência psicológicaA evolução da ciência psicológica
A evolução da ciência psicológicaGirlenia Lima
 
Ky nang cham soc khach hang
Ky nang cham soc khach hangKy nang cham soc khach hang
Ky nang cham soc khach hangThao Media 99
 
My holidays
My holidaysMy holidays
My holidaysanapili
 
Ky nang quan ly xung dot
Ky nang quan ly xung dotKy nang quan ly xung dot
Ky nang quan ly xung dotThao Media 99
 

En vedette (15)

Stock3
Stock3Stock3
Stock3
 
Prawo autorskie i licencje Creative Commons w fotografii / Kamil Śliwowski
Prawo autorskie i licencje Creative Commons w fotografii / Kamil ŚliwowskiPrawo autorskie i licencje Creative Commons w fotografii / Kamil Śliwowski
Prawo autorskie i licencje Creative Commons w fotografii / Kamil Śliwowski
 
Tulip Festival
Tulip FestivalTulip Festival
Tulip Festival
 
Ocf Li Quick Presentation Company
Ocf Li Quick Presentation CompanyOcf Li Quick Presentation Company
Ocf Li Quick Presentation Company
 
Liberação motora.
Liberação motora.Liberação motora.
Liberação motora.
 
24 04 la segunda gsma
24 04 la segunda gsma24 04 la segunda gsma
24 04 la segunda gsma
 
Jogos e atividades
Jogos e atividades  Jogos e atividades
Jogos e atividades
 
Riesgos en Internet
Riesgos en InternetRiesgos en Internet
Riesgos en Internet
 
Ky nang quan ly thoi gian
Ky nang quan ly thoi gianKy nang quan ly thoi gian
Ky nang quan ly thoi gian
 
Manish g badlani(130210125002)
Manish g badlani(130210125002)Manish g badlani(130210125002)
Manish g badlani(130210125002)
 
A evolução da ciência psicológica
A evolução da ciência psicológicaA evolução da ciência psicológica
A evolução da ciência psicológica
 
Ky nang cham soc khach hang
Ky nang cham soc khach hangKy nang cham soc khach hang
Ky nang cham soc khach hang
 
My holidays
My holidaysMy holidays
My holidays
 
Ky nang quan ly xung dot
Ky nang quan ly xung dotKy nang quan ly xung dot
Ky nang quan ly xung dot
 
Group--Capism
Group--CapismGroup--Capism
Group--Capism
 

Similaire à EEG-Based BCI Robot Control Presentation

Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Zbigniew Jerzak
 
Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_Jeffrey Shomaker
 
1-bit semantic segmentation
1-bit semantic segmentation1-bit semantic segmentation
1-bit semantic segmentationJeonghoonKim30
 
Aplications for machine learning in IoT
Aplications for machine learning in IoTAplications for machine learning in IoT
Aplications for machine learning in IoTYashesh Shroff
 
Collective Knowledge: python and scikit-learn based open research SDK for col...
Collective Knowledge: python and scikit-learn based open research SDK for col...Collective Knowledge: python and scikit-learn based open research SDK for col...
Collective Knowledge: python and scikit-learn based open research SDK for col...Grigori Fursin
 
IRJET- 3D Object Recognition of Car Image Detection
IRJET-  	  3D Object Recognition of Car Image DetectionIRJET-  	  3D Object Recognition of Car Image Detection
IRJET- 3D Object Recognition of Car Image DetectionIRJET Journal
 
Pruning convolutional neural networks for resource efficient inference
Pruning convolutional neural networks for resource efficient inferencePruning convolutional neural networks for resource efficient inference
Pruning convolutional neural networks for resource efficient inferenceKaushalya Madhawa
 
Software Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceSoftware Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceCarole Goble
 
Runtime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM SimulationRuntime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM SimulationFisnik Kraja
 
A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...
A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...
A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...Francisco (Paco) Florez-Revuelta
 
I/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue SimulationI/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue Simulationinside-BigData.com
 
Iit kgp workshop
Iit kgp workshopIit kgp workshop
Iit kgp workshopArpan Pal
 
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDSFACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDSIRJET Journal
 
PIMRC-2012, Sydney, Australia, 28 July, 2012
PIMRC-2012, Sydney, Australia, 28 July, 2012PIMRC-2012, Sydney, Australia, 28 July, 2012
PIMRC-2012, Sydney, Australia, 28 July, 2012Charith Perera
 

Similaire à EEG-Based BCI Robot Control Presentation (20)

LEGaTO: Use cases
LEGaTO: Use casesLEGaTO: Use cases
LEGaTO: Use cases
 
Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...Optimization of Continuous Queries in Federated Database and Stream Processin...
Optimization of Continuous Queries in Federated Database and Stream Processin...
 
Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_Neural nets jeff_shomaker_7-6-16_
Neural nets jeff_shomaker_7-6-16_
 
1-bit semantic segmentation
1-bit semantic segmentation1-bit semantic segmentation
1-bit semantic segmentation
 
Aplications for machine learning in IoT
Aplications for machine learning in IoTAplications for machine learning in IoT
Aplications for machine learning in IoT
 
rerngvit_phd_seminar
rerngvit_phd_seminarrerngvit_phd_seminar
rerngvit_phd_seminar
 
Mps intro
Mps introMps intro
Mps intro
 
Collective Knowledge: python and scikit-learn based open research SDK for col...
Collective Knowledge: python and scikit-learn based open research SDK for col...Collective Knowledge: python and scikit-learn based open research SDK for col...
Collective Knowledge: python and scikit-learn based open research SDK for col...
 
IRJET- 3D Object Recognition of Car Image Detection
IRJET-  	  3D Object Recognition of Car Image DetectionIRJET-  	  3D Object Recognition of Car Image Detection
IRJET- 3D Object Recognition of Car Image Detection
 
Pruning convolutional neural networks for resource efficient inference
Pruning convolutional neural networks for resource efficient inferencePruning convolutional neural networks for resource efficient inference
Pruning convolutional neural networks for resource efficient inference
 
Software Sustainability: Better Software Better Science
Software Sustainability: Better Software Better ScienceSoftware Sustainability: Better Software Better Science
Software Sustainability: Better Software Better Science
 
TiMetmay10
TiMetmay10TiMetmay10
TiMetmay10
 
Ti met may10
Ti met may10Ti met may10
Ti met may10
 
Runtime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM SimulationRuntime Performance Optimizations for an OpenFOAM Simulation
Runtime Performance Optimizations for an OpenFOAM Simulation
 
A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...
A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...
A Multiple Kernel Learning Based Fusion Framework for Real-Time Multi-View Ac...
 
I/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue SimulationI/O Challenges in Brain Tissue Simulation
I/O Challenges in Brain Tissue Simulation
 
Iit kgp workshop
Iit kgp workshopIit kgp workshop
Iit kgp workshop
 
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDSFACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
FACE COUNTING USING OPEN CV & PYTHON FOR ANALYZING UNUSUAL EVENTS IN CROWDS
 
PIMRC-2012, Sydney, Australia, 28 July, 2012
PIMRC-2012, Sydney, Australia, 28 July, 2012PIMRC-2012, Sydney, Australia, 28 July, 2012
PIMRC-2012, Sydney, Australia, 28 July, 2012
 
2016Resume
2016Resume2016Resume
2016Resume
 

Dernier

Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Scott Keck-Warren
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024The Digital Insurer
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostZilliz
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machinePadma Pradeep
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesZilliz
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfSeasiaInfotech2
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLScyllaDB
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Wonjun Hwang
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 

Dernier (20)

Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024Advanced Test Driven-Development @ php[tek] 2024
Advanced Test Driven-Development @ php[tek] 2024
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024My INSURER PTE LTD - Insurtech Innovation Award 2024
My INSURER PTE LTD - Insurtech Innovation Award 2024
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage CostLeverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
Leverage Zilliz Serverless - Up to 50X Saving for Your Vector Storage Cost
 
Install Stable Diffusion in windows machine
Install Stable Diffusion in windows machineInstall Stable Diffusion in windows machine
Install Stable Diffusion in windows machine
 
Vector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector DatabasesVector Databases 101 - An introduction to the world of Vector Databases
Vector Databases 101 - An introduction to the world of Vector Databases
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
The Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdfThe Future of Software Development - Devin AI Innovative Approach.pdf
The Future of Software Development - Devin AI Innovative Approach.pdf
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Developer Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQLDeveloper Data Modeling Mistakes: From Postgres to NoSQL
Developer Data Modeling Mistakes: From Postgres to NoSQL
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
Bun (KitWorks Team Study 노별마루 발표 2024.4.22)
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 

EEG-Based BCI Robot Control Presentation

  • 1. WP 5 Presentation Christoph Hintermüller (g.tec)
  • 2. Proposed Structure for the Talk • goals • achievements • problems • outlook/ future work • lessons learned • list of publications 11.06.2013 WP 5 Presentation 2
  • 3. Goals • Develop an EEG based brain-computer interface for robot control • Usage of the BCI system for goal oriented and continuous control • Test the BCI system for different applications 11.06.2013 WP 5 Presentation 3
  • 4. Goals 11.06.2013 WP 5 Presentation 4 • Milestones M3: First release of BCI (Month 12) M4: First ALIAS pilot (Month 12) M7: Second ALIAS pilot (Month 24) M9: Final ALIAS pilot (Month 35) • Deliverables D5.1: Rapid Prototyping Environment (Month 6) D5.2: BCI System (Month 12) D5.3: Tests of the BCI System with the Robot (Month 36) • Gantt Y1 Y2 Y3 Task 1 2 1 2 1 2 3 05. Jan Setup Rapid Prototyping D5.1 05. Feb Development of P100, SSVEP and oscillatroy BCI D5.2 05. Mrz Interfacing BCI system to robot D5.3 05. Apr BCI system tests with robot D5.3 Milestones M3,4 M7 M9 Activity WP5 Brain Computer Interface
  • 5. Achievements 11.06.2013 WP 5 Presentation 5 • 2 x g.MOBIlab 8 channel devices including EEG cap, active electrodes, Matlab Simulink BCI Models (SSVEP, P300), g.BSanalyze, EEG processing toolboxes • Installed at Fraunhofer FhG, g.tec, Jade
  • 6. Achievements 11.06.2013 WP 5 Presentation 6 • First dry electrode system that works for motor imagery, SSVEP and P300 (same accuracies reached for all) • Whole frequency range available: 0.1-40 Hz • First dry electrode system that covers extended 10/20 system on frontal, central, parietal and occipital sites • More low frequency components in the EEG spectrum below 3 Hz • Careful montage required and more sensitive to surrounding noise • Group studies submitted in March 2011 to Journal of Neural Engineering and BCI conference in Graz 2011.
  • 7. Achievements: SSVEP P-Statistics 11.06.2013 WP 5 Presentation 7 • Rectification of SNR signals to zero sample median. • Soft-Max transformation used to estimate probabilities p • Sample assigned to Virtual Zero Class if 1 – p < Confidence interval
  • 8. Achievements: P300 decisions using p-statistic • Online selection of # of flashes: p-statistics based • Residual error limits: 0.15% decision, 25% P300 validation • Minimum 2, maximum 15, average 7 flashes 11.06.2013 WP 5 Presentation 8 min mean max min mean max min mean max off 2,33 6,94 14,11 6,00 7,33 9,33 3,17 6,58 9,67 30,00 2,44 7,11 14,78 7,67 7,67 7,67 3,56 6,51 10,22 25,00 2,44 7,11 14,78 5,00 6,33 9,00 3,78 7,13 10,56 20,00 2,44 7,22 14,44 5,00 6,93 9,00 3,44 7,02 10,78 15,00 2,44 7,16 14,44 3,33 8,06 12,00 3,44 7,06 10,56 10,00 2,44 6,80 14,00 4,33 6,13 8,33 3,33 7,56 12,44 5,00 3,56 7,33 14,00 5,57 6,43 7,29 4,22 8,64 12,22 2,50 3,67 7,14 13,67 5,17 8,39 11,67 4,33 9,00 13,56 1,00 4,11 7,06 12,11 6,71 8,79 10,86 4,22 8,57 13,56 0,50 3,25 5,71 10,13 5,86 7,93 10,00 4,56 8,22 12,89 0,10 5,43 6,52 8,57 2,80 5,40 8,00 4,56 8,03 12,56 TTP FTP FP True positive selection Positiv selection, false assignment False Positiv selection Total spelled 28 char Total ignored 28 char Residal Error Probability [%] Parameters considered Average Values: count(p>1-r) = 1 # Repetitions P3selectionerrorprobability[%] 0,15 TTP FTP FP
  • 9. Achievements: BCI ACTOR 11.06.2013 WP 5 Presentation 9 Network (UDP) Communication Interface Structure • General structure – UI is controlled with the BCI system ( MI BCI, SSVEP BCI, P300 BCI) – AIM: Adaptive Interface Module • Grouping of applications • Receives real time updates • Prepares information for UI – Application group: applications controlled by one network node (e.g. Home Automation) • XML string from UDP message or local file – Mask layout and structure – ICONs – Command Types and Instructions • Initialized via UDP socket
  • 10. Achievements: BCI ACTOR 11.06.2013 WP 5 Presentation 10 Mask Description Chat Mask Contact Mask
  • 11. Achievements: Integration • with Dialog Manager • with Gui 11.06.2013 WP 5 Presentation 11 Component/Service Status Paradigm Entertainment Yes P300 Games Yes Audio Books Yes TV Yes WII Switching to WII Communication Yes Skype outgoing call Yes Skype incoming call Yes/Schiedlberg Initiate emergency call Yes Web-browser Loading browser Call/Dismiss No/2013 SSVEPDirect emergency call No/2013 Cancel emergency call No/2013 Paradigm SOCI BCI processing Integrated P300 single character Yes Yes YES P300 row column No Yes - SSVEP onscreen Yes Yes - SSVEP LED - Yes No
  • 13. Problems 11.06.2013 WP 5 Presentation 13
  • 14. Outlook / Future Work • Ongoing developments • Integration signal check module • Combination: accuracy based selection of optimal # of flashes and p-statistics • SOCI multi line text • SOCI icon size independent of mask size and window size • SOCI support for greyscale, color Icons • SOCI elimination shared network drive • ACTOR protocol improvements and speedup • User tests • Munich in coordination with TUM • Only tested with ALIAS members 11.06.2013 WP 5 Presentation 14
  • 15. Lessons Learned 11.06.2013 WP 5 Presentation 15
  • 16. List of Publications • Papers, Book Chapters • C. Guger, G. Krausz, B. Allison, G. Edlinger (2012): Comparison of dry and gel based electrodes for P300 brain–computer interfaces. Front. Neurosci. 6 :60. doi: 10.3389/fnins.2012.00060. • Fazel-Rezai R, Allison BZ, Guger C, Sellers EW, Kleih SC and Kübler A (2012): P300 brain computer interface: current challenges and emerging trends. Front. Neuroeng. 5:14. doi: 10.3389/fneng.2012.00014 • J.A. Wilson; C. Guger, G. Schalk: BCI Hardware and Software. In Jonathan R. Wolpaw, Elizabeth Winter Wolpaw (2012): Brain-Computer Interfaces: Principles and Practice. Edited by: Jonathan R. Wolpaw, Elizabeth Winter Wolpaw. Publisher: Oxford Univ Pr. Publication Date: 1. Edition, January 24, 2012. ISBN: 978-0-195-38885-5. • Lechner, R. Ortner, F. Aloise, R. Prueckl, F. Schettini, V. Putz, J. Scharinger, E. Opisso, U. Costa, J. Medina, C. Guger (2012): Comparing the accuracy of a P300 speller for people with major physical disability. In Proceedings of ICCHP. July 11 – 13,2012. Linz, AT. • C. Hintermüller, C. Kapeller, G. Edlinger, C. Guger, BCI Integration: Application Interfaces, In Brain Computer Interface, Edited by: Fazel-Razi, Intech, 2013, ISBN 980-953-307-960-3 • Fares/Conferences • IEEE Biorob 2012, Rom, IT. June 24 – 28, 2012. • Measuring Behaviour 2012. Aug 28 – 31, 2012. Utrecht, NL • Joint Annual Meeting ECNS - ISNIP - ISBET – EPIC. Sep 12 – 16, 2012. Bristol, TN, US. 11.06.2013 WP 5 Presentation 16