Advertisement

Wireless Brain-Computer Interface for Wheelchair Control by Using Fast Machine Learning and Real-Time Hyper-Dimensional Classification

  • Valerio F. Annese
  • Giovanni Mezzina
  • Daniela De VenutoEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10544)

Abstract

This paper presents a noninvasive brain-controlled P300-based wheelchair driven by EEG signals to be used by tetraplegic and paralytic users. The P300 - an Evoked Related Potential (ERP) - is induced for purpose by visual stimuli. The developed Brain-Computer Interface is made up by: (i) acquisition unit; (ii) processing unit and (iii) navigation unit. The acquisition unit is a wireless 32-channel EEG headset collecting data from 6 electrodes (parietal-cortex area). The processing unit is a dedicated µPC performing stimuli delivery, data gathering, Machine Learning (ML), real-time hyper-dimensional classification leading to the user intention interpretation. The ML stage is based on a custom algorithm (t-RIDE) which trains the following classification stage on the user-tuned P300 reference features. The real-time classification performs a functional approach for time-domain features extraction, which reduce the amount of data to be analyzed. The Raspberry-based navigation unit actuates the received commands and support the wheelchair motion using peripheral sensors (USB camera for video processing, ultrasound sensors). Differently from related works, the proposed protocol for stimulation is aware of the environment. The experimental results, based on a dataset of 5 subjects, demonstrate that: (i) the implemented ML algorithm allows a complete P300 spatio-temporal characterization in 1.95 s using only 22 target brain visual stimuli (88 s/direction); (ii) the complete classification chain (from features extraction to validation) takes in the worst case only 19.65 ms ± 10.1, allowing real-time control; (iii) the classification accuracy of the implemented BCI is 80.5 ± 4.1% on single-trial.

Keywords

BCI Machine learning Classification EEG ERP P300 

References

  1. 1.
    Graimann, B., Allison, B., Pfurtscheller, G.: Brain–Computer Interfaces: A Gentle Introduction. Springer, Heidelberg (2009)Google Scholar
  2. 2.
    Grychtol, B., Lakany, H., Valsan, G., Conway, B.A.: Human behavior integration improves classification rates in real-time BCI. Neural Syst. Rehabil. Eng. 8(4), 362–368 (2010).  https://doi.org/10.1109/TNSRE.2010.2053218 CrossRefGoogle Scholar
  3. 3.
    De Venuto, D., Vincentelli, A.S.: Dr. Frankenstein’s dream made possible: Implanted electronic devices. In: Proceedings of Design, Automation and Test in Europe, DATE, pp. 1531–1536 (2013). Art. no. 6513757Google Scholar
  4. 4.
    De Venuto, D., Annese, V.F., Mezzina, G.: An embedded system remotely driving mechanical devices by P300 brain activity. In: Proceedings of the 2017 Design, Automation and Test in Europe Conference and Exhibition, DATE (2017). ISBN 978-3-9815370-8-6Google Scholar
  5. 5.
    Ortner, R., et al.: An SSVEP BCI to control a hand orthosis for persons with tetraplegia. IEEE Trans. Neural Syst. Rehabil. Eng. 19(1), 1–5 (2011)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Barnes, N.: Visual processing for the bionic eye: Research and development of visual processing for low vision devices and the bionic eye (2012)Google Scholar
  7. 7.
    Farwell, L.A., Donchin, E.: Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroenceph Clin. Neurophysiol. 70(6), 510–523 (1988)CrossRefGoogle Scholar
  8. 8.
    Hochberg, L.R., et al.: Neuronal ensemble control of prosthetic devices by a human with tetraplegia. Nat. J. 442, 164–171 (2006)CrossRefGoogle Scholar
  9. 9.
    Nijholt, A.: BCI for games: a ‘state of the art’ survey. In: Stevens, Scott M., Saldamarco, Shirley J. (eds.) ICEC 2008. LNCS, vol. 5309, pp. 225–228. Springer, Heidelberg (2008).  https://doi.org/10.1007/978-3-540-89222-9_29 CrossRefGoogle Scholar
  10. 10.
    Fernando, L., Alonso, N., Gomez-Gil, J.: Brain computer interfaces, a review. Sensors 12(2), 1211–1264 (2012)Google Scholar
  11. 11.
    De Tommaso, M., Vecchio, E., Ricci, K., Montemurno, A., De Venuto, D., Annese, V.F.: Combined EEG/EMG evaluation during a novel dual task paradigm for gait analysis. In: Proceedings of the 2015 6th IEEE International Workshop on Advances in Sensors and Interfaces, IWASI 2015, pp. 181–186. (2015). art. no. 7184949.  https://doi.org/10.1109/iwasi.2015.7184949
  12. 12.
    De Venuto, D., Annese, V.F., Mezzina, G.: Remote Neuro-Cognitive Impairment Sensing based on P300 Spatio-Temporal Monitoring. IEEE Sens. J. 16(23), 8348–8356 (2016). PP (99), art. no. 7562544, https://doi.org/10.1109/jsen.2016.2606553 CrossRefGoogle Scholar
  13. 13.
    Annese, V.F., Mezzina, G., De Venuto, D.: Towards mobile health care: Neurocognitive impairment monitoring by BCI-based game. In: Proceedings of IEEE Sensors (2017). art. no. 7808745 2017.  https://doi.org/10.1109/icsens.2016.7808745
  14. 14.
    De Venuto, D., Annese, V.F., Mezzina, G., Ruta, M., Sciascio, E.D.: Brain-computer interface using P300: A gaming approach for neurocognitive impairment diagnosis. In: 2016 IEEE International High Level Design Validation and Test Workshop, HLDVT 2016, pp. 93–99 (2016). art. no. 7748261.  https://doi.org/10.1109/hldvt.2016.7748261
  15. 15.
    Fernández-Rodríguez, Á., Velasco-Álvarez, F., Ron-Angevin, R.: Review of real brain-controlled wheelchairs. J. Neural Eng. 13(6), (2016). 061001Google Scholar
  16. 16.
    Annese, V.F., De Venuto, D.: Gait analysis for fall prediction using EMG triggered movement related potentials. In: Proceedings of 2015 10th IEEE International Conference on Design and Technology of Integrated Systems in Nanoscale Era, DTIS 2015 (2015). art. no. 7127386.  https://doi.org/10.1109/dtis.2015.7127386
  17. 17.
    De Venuto, D., Annese, V.F., Ruta, M., Di Sciascio, E., Sangiovanni Vincentelli, A.L.: Designing a cyber-physical system for fall prevention by cortico-muscular coupling detection. IEEE Des. Test 33(3), 66–76 (2016). art. no. 7273831. https://doi.org/10.1109/mdat.2015.2480707 CrossRefGoogle Scholar
  18. 18.
    Annese, V.F., De Venuto, D.: Fall-risk assessment by combined movement related potentials and co-contraction index monitoring. In: Proceedings of IEEE Biomedical Circuits and Systems Conference: Engineering for Healthy Minds and Able Bodies, BioCAS 2015 (2015). art. no. 7348366.  https://doi.org/10.1109/biocas.2015.7348366
  19. 19.
    Annese, V.F., De Venuto, D.: FPGA based architecture for fall-risk assessment during gait monitoring by synchronous EEG/EMG. In: Proceedings of 2015 6th IEEE International Workshop on Advances in Sensors and Interfaces, IWASI 2015, pp. 116–121 (2015). art. no. 7184953.  https://doi.org/10.1109/iwasi.2015.7184953
  20. 20.
    Annese, V.F., Crepaldi, M., Demarchi, D., De Venuto, D.: A digital processor architecture for combined EEG/EMG falling risk prediction. In: Proceedings of the 2016 Design, Automation and Test in Europe Conference and Exhibition, DATE 2016, pp. 714–719 (2016). art. no. 7459401Google Scholar
  21. 21.
    Annese, V.F., De Venuto, D.: The truth machine of involuntary movement: FPGA based cortico-muscular analysis for fall prevention. In: IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2015, pp. 553–558 (2015). art. no. 7394398.  https://doi.org/10.1109/isspit.2015.7394398
  22. 22.
    De Venuto, D., Annese, V.F., Sangiovanni-Vincentelli, A.L.: The ultimate IoT application: a cyber-physical system for ambient assisted living. In: Proceedings of IEEE International Symposium on Circuits and Systems, pp. 2042–2045, July 2016. art. no. 7538979.  https://doi.org/10.1109/iscas.2016.7538979
  23. 23.
    De Venuto, D., Annese, V.F., Defazio, G., Gallo, V.L., Mezzina, G.: Gait analysis and quantitative drug effect evaluation in parkinson disease by jointly EEG-EMG monitoring. In: Proceedings of 2017 12th IEEE International Conference on Design and Technology of Integrated Systems in Nanoscale Era, DTIS 2017 (2017)Google Scholar
  24. 24.
    Patel, S.H., Azzam, P.N.: Characterization of N200 and P300: Selected Studies of the Event-Related Potential. International Journal of Medical Sciences 2(4), 147–154 (2005)CrossRefGoogle Scholar
  25. 25.
    Annese, V.F., De Venuto, D., Martin, C., Cumming, D.R.S.: Biodegradable pressure sensor for health-care. In: 2014 21st IEEE International Conference on Electronics, Circuits and Systems, ICECS 2014, pp. 598–601 (2014). art. no. 7050056.  https://doi.org/10.1109/icecs.2014.7050056
  26. 26.
    Annese, V.F., Martin, C., Cumming, D.R.S., De Venuto, D.: Wireless capsule technology: Remotely powered improved high-sensitive barometric endoradiosonde. In: Proceedings of IEEE International Symposium on Circuits and Systems, pp. 1370–1373. July 2016. art. no. 7527504.  https://doi.org/10.1109/iscas.2016.7527504
  27. 27.
    Annese, V.F., De Venuto, D.: On-line shelf-life prediction in perishable goods chain through the integration of WSN technology with a 1st order kinetic model. In: 2015 IEEE 15th International Conference on Environment and Electrical Engineering, EEEIC 2015, pp. 605–610 (2015). art. no. 7165232.  https://doi.org/10.1109/eeeic.2015.7165232
  28. 28.
    Annese, V.F., Biccario, G.E., Cipriani, S., De Venuto, D.: Organoleptic properties remote sensing and life-time prediction along the perishables goods supply-chain. In: Proceedings of the International Conference on Sensing Technology, ICST, pp. 130–135. Jan 2014Google Scholar
  29. 29.
    De Venuto, D., Annese, V.F., de Tommaso, M., Vecchio, E., Vincentelli, A.S.: Combining EEG and EMG signals in a wireless system for preventing fall in neurodegenerative diseases. Ambient Assisted Living, pp. 317–327. Springer, Cham (2015)Google Scholar
  30. 30.
    Biccario, G.E., Annese, V.F., Cipriani, S., De Venuto, D.: WSN-based near real-time environmental monitoring for shelf life prediction through data processing to improve food safety and certification. In: Proceedings of the 11th International Conference on Informatics in Control, Automation and Robotics, ICINCO 2014, vol. 1, pp. 777–782 (2014)Google Scholar
  31. 31.
    De Venuto, D., Carrara, S., Ricco, B.: Design of an integrated low-noise read-out system for DNA capacitive sensors. Microelectron. J. 40(9), 1358–1365 (2009).  https://doi.org/10.1016/j.mejo.2008.07.071 CrossRefGoogle Scholar
  32. 32.
    De Venuto, D., Castro, D.T., Ponomarev, Y., Stikvoort, E.: Low power 12-bit SAR ADC for autonomous wireless sensors network interface. In: 3rd International Workshop on Advances in Sensors and Interfaces, IWASI 2009, pp. 115–120 (2009). art. no. 5184780.  https://doi.org/10.1109/iwasi.2009.5184780
  33. 33.
    De Venuto, D., Ohletz, M.J., Ricco, B.: Automatic repositioning technique for digital cell based window comparators and implementation within mixed-signal DfT schemes. In: Proceedings of International Symposium on Quality Electronic Design, ISQED, pp. 431–437. Jan 2003. art. no. 1194771.  https://doi.org/10.1109/isqed.2003.1194771
  34. 34.
    De Venuto, D., Ohletz, M.J., Ricco, B.: Digital window comparator DfT scheme for mixed-signal ICs. J. Electron. Test. Theory Appl. (JETTA) 18(2), 121–128 (2002).  https://doi.org/10.1023/A:1014937424827 CrossRefGoogle Scholar
  35. 35.
    De Venuto, D., Ohletz, M.J., Ricco, B.: Testing of analogue circuits via (standard) digital gates. In: Proceedings of International Symposium on Quality Electronic Design, ISQED, pp. 112–119. Jan 2002. art. no. 996709.  https://doi.org/10.1109/isqed.2002.996709

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.School of EngineeringUniversity of GlasgowGlasgowUK
  2. 2.Department of Electrical and Information EngineeringBariItaly

Personalised recommendations