ABSTRACT
In this work we discuss, analyze and compare results regarding a new compression method for electroencephalographic signals aimed at P300 detection spelling paradigm based on the concept of compressed sensing (CS). The method uses a universal mega-dictionary which has been found not to be patient-specific. The impact of the size dictionary on the results is analyzed and optimal dimensions of the proposed dictionary (in terms of computing time vs. resulting compromise reconstruction) are determined.
To validate the proposed method, electroencephalography recordings from the competition for Spelling BCI Competition III Challenge 2005 -Dataset II have been used. The reconstructed EEG signal is analyzed both in terms of reconstruction errors and spelling accuracy. The classification rate for the observed characters based on P300 detection in the case of the spelling paradigm applied on the reconstructed electroencephalography signals were made using the winning scripts reported by Alain Rakotomamonjy and Vincent Guigue.
- Davenport M. A., Duarte M. F., Eldar Y. C., and Kutyniok G., 2012, Introduction to Compressed Sensing, in Compressed Sensing: Theory and Applications, Cambridge University Press.Google Scholar
- Blankertz, B. BCI competition III webpage {Online}. Available: http://ida.first.fraunhofer.de/projects/bci/competition IIIGoogle Scholar
- Blankertz, B., Mueller, K. R., Curio, G., Vaughan, T., Schalk, G., Wolpaw, J., Schloegl, A., Neuper, C., Pfurtscheller, G., Hinterberger, T., Schroeder, M.,and Birbaumer, N. 2004. The BCI competition 2003: Progress and perspectives in detection and discrimination of EEG single trials, IEEE Trans. Biomed. Eng, 51(6): 1044--1051.Google Scholar
- Rakotomamonjy A. and Guigue V. 2008. BCI Competition III: Dataset II- Ensemble of SVMs for BCI P300 Speller, IEEE Transactions on Biomedical Engineering, 55(3): 1147--1154.Google ScholarCross Ref
- Farwell, L. A. and Donchin, E. 1988. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalography & Clinical Neurophysio. 70(6):510--23, 1988Google Scholar
- Data Acquired Using BCI2000's P3 Speller Paradigm (http://www.bci2000.org).Google Scholar
- Donoho, D. L. and Elad, M. 2003. Optimally sparse representation in general (nonorthogonal) dictionaries via l1 minimization, Proceedings of the National Academy of Sciences, 100(5): 2197--2202.Google Scholar
- Donoho, D., Elad, M., and Temlyakov, V. 2006. Stable recovery of sparse overcomplete representations in the presence of noise, IEEE Transactions on Information Theory, 52(1): 6--18. Google ScholarDigital Library
- Natarajan, B. K. 1995. Sparse approximate solutions to linear systems, SIAM J. Comput., 24(2): pp. 227--234. Google ScholarDigital Library
- Candes, E. and Tao, T. 2005. Decoding by linear programming, IEEE Transactions on Information Theory, 51, 4203--4215. Google ScholarDigital Library
- Fira, M. 2016. Compressed Sensing of Multi-Channel EEG Signals: quantitative and qualitative evaluation with Speller Paradigm, International Journal of Advanced Computer Science and Applications (IJACSA), 7( 6).Google Scholar
- Fira, M. and Goras, L. 2016. Comparison of inter-and intra-subject variability of P300 spelling dictionary in EEG compressed sensing, International Journal of Advanced Computer Science and Applications (IJACSA), 7(10).Google Scholar
Index Terms
- On the Size of the Universal Dictionaries Used in EEG P300 Spelling Paradigm Based on Compressed Sensing
Recommendations
EEG data analysis based on EMD for coma and quasi-brain-death patients
Advances in knowledge discovery and data analysis for artificial intelligenceElectroencephalography (EEG) is widely used in evaluating the absence of cerebral cortex function for the determination of brain death. Since EEG recorded signal is always corrupted by some artefacts and various interfering noise, extracting active or ...
Trends in Machine Learning and Electroencephalogram (EEG): A Review for Undergraduate Researchers
HCI International 2023 – Late Breaking PapersAbstractThis paper presents a systematic literature review on Brain-Computer Interfaces (BCIs) in the context of Machine Learning. Our focus is on Electroencephalography (EEG) research, highlighting the latest trends as of 2023. The objective is to ...
Data-Driven Frequency Bands Selection in EEG-Based Brain-Computer Interface
PRNI '11: Proceedings of the 2011 IEEE International Workshop on Pattern Recognition in NeuroImagingIn this paper, we propose a novel method of frequency bands selection based on the analysis of a channel-frequency map, which we call 'channel-frequency map'. The spatial filtering, feature extraction, and classification processes are operated in each ...
Comments