SSVEP based BCI & Application Presented by M.S. Riazi Supervisor: Dr. M.B. Shamsollahi
Outline Introduction What we did at First New Application References BCI SSVEP What we did at First Application and Results New Application Previous Works Block Diagram Results References
What is BCI ? Abbreviation of Brain Computer Interface Is a direct communication pathway between the brain and an external Falls in 2 major categories External Invasive
Typical BCI System What is BCI ?
What Kind of Activities does Brain Have? What is BCI ? MTB Motor Imagery based BCI MIB Mental task based BCI P300 Related to unpredictability of stimulus VEP Response to rapid visual stimulus SSVEP Response to Oscillator stimulus
What is SSVEP ? Steady State Visual Evoked Potentials Brain response to oscillator stimulus If the stimulus oscillate with a specific frequency, The pattern with the same frequency will appear in the Occipital Lobe
When This oscillating pattern enters the Eyes, these photons are captured by visionary cells What is SSVEP ?
By Recording the brain signals specially from the occipital lope and using FFT we see the following diagram What is SSVEP ?
What We did at First Using Multiple frequencies dedicated to one Class Aim: To select our class much FASTER (less Avg. time) Strategies->dedicating multiple frequencies by: Time Defining different signal level and adding 2 sinusoids arithmetically Location Using different locations for each frequency
What We did at First Our Work Using Emotive EEG (14 channels) for acquiring Brain signals Using MATLAB for processing the channels
Project Implementation Diagram BCI 2000 Field Trip Buffer MATLAB Visual Studio (C#) Emotive Driver Feedback to user Signal Acquisition
Project Implementation Flow BCI 2000: An application which will handle the flow of Data among different side applications. Field Trip Buffer: An interface application which gets Data from BCI 2000 and pass it to MATLAB MATLAB: Core of all Processes! Gets Signal Data form Field Trip Buffer and give the Results to Visual Studio
MATLAB Implementation of Paper “Towards an SSVEP Based BCI With High ITR” [4] Main Idea is that we generate artificial channels by which we can reduce the noise influence will get its min value
MATLAB Eigen values
Visual Studio Our Work 2nd Harmonic Time Location Most Important Concern: Concise Timing Time Location
Testing Application Results Subject looking at 6 Hz oscillating screen Previous Data New application ‘s Data
Subject looking at TIME MIXED 6 Hz and 18 Hz oscillating screen Result: Energy between these Frequencies are scrambled Results Previous Data New application ‘s Data
Subject looking at TIME MIXED 6 Hz and 10 Hz oscillating screen Result: Energy between these Frequencies are scrambled Results Previous Data New application ‘s Data
New Application Aim: Person looks at phone dial keypad for each desired digit and then the digits are complete, a phone call will take a place with that number
New Application Aim: Person looks at phone dial keypad for each desired digit and then the digits are complete, a phone call will take a place with that number
Previous Works A cell-phone-based brain–computer interface for communication in daily life
Previous Works Result A cell-phone-based brain–computer interface for communication in daily life
Project Implementation Diagram BCI 2000 Field Trip Buffer MATLAB Visual Studio (C#) Bluetooth Emotive Driver Android Platform Wireless Data Transfer Feedback to user Signal Acquisition GSM Communication
Design Specifications Key Pad with 12 dedicated buttons (numbers: 0 to 9, Backspace, #) Frequencies Dedicated: 6 8 10 11 13 15 17 19 21 23 25 29 Constraints ! Dedicated with scatter position on Pad Algorithm used: Minimum Energy Combination (MEC) + High Pass Filter + Threshold Scalable Classification + Common Mode Average Filter (CMA) + Dynamic Window Size (DWS) + Special Pattern Construction
Signal Processing Diagram Raw Signal
Signal Processing Diagram After CMA and HP Filter
Results Accuracy of classification Rows: Threshold Columns: Time interval Fixed Time Interval Signal: 4 Channels, 1 Minute Data Acquisition, Person looking at 12Hz (Besides buttons: @10Hz and 14 Hz)
Results Dynamic Window Size (DWS) Accuracy Vs. Threshold
Results Dynamic Window Size (DWS) Distribution of each window size used
References (1/3) “A Study on SSVEP-Based BCI”, Zheng-Hua Wu and De-Zhong Yao ,JOURNAL OF ELECTRONIC SCIENCE AND TECHNOLOGY OF CHINA, VOL. 7, NO. 1, MARCH 2009 Simple communication using a SSVEP-based BCI, Guillermo Sanchez, Pablo F. Diez, Enrique Avila, Eric Laciar Leber, Journal ofPhysics:ConferenceSeries 332 (2011) 012017 doi:10.1088/1742-6596/332/1/012017 “SSVEP and P300 based interfaces”, Fabrizio Beverina,Giorgio Palmas,Stefano Silvoni,Francesco Piccione, PsychNology Journal, 2003, Volume 1, Number 4, 331 – 354 Towards an SSVEP Based BCI With High ITR, Ivan Volosyak, Diana Valbuena, Thorsten L¨uth, and Axel Gr¨aser, G. Dornhege, J. del R. Millan, T. Hinterberger, D. J. McFarland, and K.-R. M¨uller, Toward Brain-Computer Interfacing. MIT Press, 2007 G. Schalk, “Sensor modalities for brain-computer interfacing,” in Human-Computer Interaction, Part II, HCII 2009, LNCS 5611, 2009, pp. 616–622. J. R. Wolpaw, H. Ramoser, D. J. McFarland, and G. Pfurtscheller, “EEG-based communication: improved accuracy by response verification,” IEEE Trans. Rehabil. Eng., vol. 6, no. 3, pp. 326–333, Sep. 1998. E. C. Lalor, S. P. Kelly, C. Finucane, R. Burke, R. Smith, R. B. Reilly, and G. McDarby, “Steady-state VEP-based brain- computer interface control in an immersive 3D gaming environment,” EURASIP J. Appl. Signal Process., vol. 19, pp. 3156–3164, 2005.
References (2/3) J. R. Wolpaw et al., “Brain-computer interface technology: A review of the first international meeting,” IEEE Trans. Rehab. Eng., vol. 8, pp. 164–173, June 2000.Towards an SSVEP Based BCI With High ITR, Ivan Volosyak, Diana Valbuena, Thorsten L¨uth, and Axel Gr¨aser, Design and Implementation of a Brain-Computer Interface With High Transfer Rates Ming Cheng*, Xiaorong Gao, Shangkai Gao, Senior Member, IEEE, and Dingfeng Xu Visual stimulus design for high-rate SSVEP BCI Y. Wang, Y.-T. Wang and T.-P. Jung A cell-phone-based brain–computer interface for communication in daily life Yu-Te Wang1, Yijun Wang1 and Tzyy- Ping Jung Swartz Center for Computational Neuroscience, Institute for Neural Computational, University of California, San Diego, La Jolla, CA, USA Developing Stimulus Presentation on Mobile Devices for a Truly Portable SSVEP-based BCI Yu-Te Wang, Student Member, IEEE, Yijun Wang, Member, IEEE, Chung-Kuan Cheng, Fellow, IEEE, and Tzyy-Ping Jung*, Senior Member, IEEE G. Bin, X. Gao, Z. Yan, B. Hong, and S. Gao, “An online multi-channel SSVEP-based brain-computer interface using a canonical correlation analysis method,” Journal of Neural Engineering, vol. 6, no. 4, 2009.
References (3/3) D. Regan, Human brain electrophysiology: evoked potentials and evoked magnetic fields in science and medicine. New York: Elsevier Pubs; 1989. M. De Tommaso, V. Sciruicchio, M. Guido, G. Sasanelli, and F. Puca, “Steady-state visual evoked potentials in headache: diagnostic value in migraine and tension-type headache patients”. Cephalalgia, vol. 19, pp. 23-26, Jan. 1999. Y.-T. Wang, Y. Wang, and T.-P. Jung, “A Cell-phone based Brain Computer Interface for Communication in Daily Life ", Journal of Neural Engineering, vol.8, no.2, pp. 1-5, 2011. E. Lyskov, V. Ponomarev, M. Sandstrom, K. H. Mild, and S. Medvedev, “Steady-State Visual Evoked Potentials to Computer Monitor Flicker,” International Jurnal of Psychophysology, vol. 28, pp. 285-290, 1998.
Grateful of Prof. M.B. Shamsollahi Omid Ghasemsani Sajad Karimi Masih Bahrani Javad Abedi Mohammad Javad Seyed Talebi Who helped me very much during this project
ThanK you iN adVanCe f0r your AtTentiOn