ГРНТИ 50.07 Теоретические основы вычислительной техники
ББК 3297 Вычислительная техника
This paper addresses the problem of motion imagery classification from electroencephalogram signals which related with many difficulties such on human state, measurement accuracy, etc. Artificial neural networks are a good tool to solve such kind of problems. Electroencephalogram is time series signals therefore, a Gramian Angular Fields conversion has been applied to convert it into images. GAF conversion was used for classification EEG with Convolutional Neural Network (CNN). GAF images are represented as a Gramian matrix where each element is the trigonometric sum between different time intervals. Grayscale images were applied for recognition to reduce numbers of neural network parameters and increase calculation speed. Images from each measuring channel were connected into one multi-channel image. This article reveals the possible usage GAF conversion of EEG signals to motion imagery recognition, which is beneficial in the applied fields, such as implement it in brain-computer interface.
motor imagery recognition, electroencephalogram, Gramian Angular Field, Convolutional Neural Network
1. Blankertz B. et al The BCI competition 2003: Progress andperspectives in detection and discrimination of EEG singletrials// IEEE Transactions on Biomedical Engineering. –2004. – №6 (51). – P. 1044–1051.
2. Grubov V.V., Runnova A.E., Kurovskaуa M.K., PavlovA.N., Koronovskii A.A., Hramov A.E. Demonstration ofbrain noise on human EEG signals in perception of bistableimages // Proc. SPIE. 2016. V. 9707. DOI:10.1117/12.2207390
3. Hohyun Cho, Minkyu Ahn, Sangtae Ahn, MoonyoungKwon, Sung Chan Jun, EEG datasets for motor imagerybrain–computer interface, GigaScience, Volume 6, Issue 7,July 2017, gix034,https://doi.org/10.1093/gigascience/gix034
4. Hramov A.E., Koronovskii A.A., Makarov V.A., PavlovA.N., Sitnikova E.Y. Wavelets in Neuroscience.Heidelberg; New York; Dordrecht; London, Springer, 2015.318 p
5. W. Hsu and I. Chiang, ""Application of neural network tobrain-computer interface,"" 2012 IEEE InternationalConference on Granular Computing, Hangzhou, 2012, pp.163-168. doi: 10.1109/GrC.2012.6468559
6. Koronovskii A.A., Hramov A.E., Grubov V.V.,Moskalenko O.I., Sitnikova E.Y., Pavlov A.N. Coexistenceof intermittencies in the neuronal network of the epilepticbrain // Phys. Rev. E. 2016. V. 93. DOI:10.1103/PhysRevE.93.032220
7. van Luijtelaar G., Lüttjohann A., Makarov V.V.,Maksimenko V.A., Koronovskii A.A., Hramov A.E.Methods of automated absence seizure detection,interference bystimulation, and possibilities for predictionin genetic absence models // Journal of NeuroscienceMethods. 2016. V. 260. P. 144.
8. Maksimenko V.A., Heukelum S., Makarov V.V.,Kelderhuis J., Lüttjohann A., Koronovskii A.A., HramovA.E., Luijtelaar G. Absence Seizure Control by a BrainComputer Interface // Scientific Reports. 2017. V. 7. P.2487.
9. K. Nakayama and K. Inagaki, ""A Brain Computer InterfaceBased on Neural Network with Efficient Pre-Processing,""2006 International Symposium on Intelligent SignalProcessing and Communications, Tottori, 2006, pp. 673-676. doi: 10.1109/ISPACS.2006.364745
10. Nima Hatami, Yann Gavet, Johan Debayle. Classificationof Time-Series Images Using Deep Convolutional NeuralNetworks. 2017 The 10th International Conference on Machine Vision (ICMV 2017), ICMV Committees, Nov2017, Vienne, Austria. 10.1117/12.2309486. hal-01743695
11. R. Östberg, ‘Robustness of a neural network used for imageclassification : The effect of applying distortions onadversarial examples’, Dissertation, 2018.
12. Qinglong Wang , Wenbo Guo , Kaixuan Zhang , AlexanderG. Ororbia, II , Xinyu Xing , Xue Liu , C. Lee Giles,Adversary Resistant Deep Neural Networks with anApplication to Malware Detection, Proceedings of the 23rdACM SIGKDD International Conference on KnowledgeDiscovery and Data Mining, August 13-17, 2017, Halifax,NS, Canada
13. Vasilyev A.N., Liburkina S.P., Kaplan A.Y. Lateralizationof EEG patterns in humans during motor imagery of armmovements in the brain-computer interface // ZhurnalVysshei Nervnoi Deyatelnosti Imeni IP Pavlova. 2016. V.66. № 3. P. 302-312.
14. Wang, Z.; Oates, T. Imaging time-series to improveclassification and imputation. In Proceedings of theTwenty-Fourth International Joint Conference on ArtificialIntelligence, Buenos Aires, Argentina, 25–31 July 2015; pp.3939–3945.
15. Wang, Z., Oates, T. Encoding time series as images forvisual inspection and classification using tiledconvolutionalneural networks, Association for the Advancement ofArtificial Intelligence (AAAI) conference,2015.
16. J. Yim and K. Sohn, ""Enhancing the Performance ofConvolutional Neural Networks on Quality DegrdedDatasets,"" 2017 International Conference on Digital ImageComputing: Techniques and Applications (DICTA),Sydney, NSW, 2017, pp. 1-8. doi:10.1109/DICTA.2017.8227427 Nima Hatami, Yann Gavet,Johan Debayle.
17. Zhiguang Wang и Tim Oates. “Spatially EncodingTemporal Correlations to Classify Temporal Data UsingConvolutional Neural Networks”. В: CoRRabs/1509.07481 (2015). url:http://arxiv.org/abs/1509.07481.
