P300 based character recognition using sparse autoencoder with ensemble of SVMs

• Autorzy: Kundu Sourav , Ari Samit

Identyfikatory

DOI

10.1016/j.bbe.2019.08.001

• Języki publikacji: EN

Abstrakty

EN

In this study, a brain–computer interface (BCI) system known as P300 speller is used to spell the word or character without any muscle activity. For P300 signal classification, feature extraction is an important step. In this work, deep feature learning techniques based on sparse autoencoder (SAE) and stacked sparse autoencoder (SSAE) are proposed for feature extraction. Deep feature provides the abstract information about the signal. This work proposes fusion of deep features with the temporal features, which provides abstract and temporal information about the EEG signal. These deep feature and temporal feature are partially complement of each other to represent the EEG signal. For classification of the EEG signal, an ensemble of support vector machines (ESVM) is adopted as it helps to reduce the classifiers variability. In classifier ensemble system, the score of individual classifier is not at the same level. To transform these scores into a common level, min–max normalization is proposed prior to combining them. Min-max normalization scales the classifiers' score between 0 and 1. The experiments are conducted on three standard public datasets, dataset IIb of BCI Competition II, dataset II of the BCI Competition III and BNCI Horizon dataset. The experimental results show that the proposed method yields better or comparable performance compared to earlier reported techniques.

Słowa kluczowe

EN

brain computer interface; deep learning; support vector machine; normalization; P300 speller; sparse autoencoder

PL

interfejs mózg-komputer; uczenie głębokie; maszyna wektorów wsparcia; P300

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 4
• Strony: 956--966
• Opis fizyczny: Bibliogr. 47 poz., rys., tab., wykr.

Twórcy

autor

Kundu Sourav

• Department of Electronics and Communication Engineering, National Institute of Technology Rourkela, Odisha 769008, India

autor

Ari Samit

• Department of Electronics and Communication Engineering, National Institute of Technology Rourkela, Odisha, India

Bibliografia

• [1] Birbaumer N, Cohen LG. Brain–computer interfaces: communication and restoration of movement in paralysis. J Physiol 2007;579(3):621–36.
• [2] Guy V, Soriani M-H, Bruno M, Papadopoulo T, Desnuelle C, Clerc M. Brain computer interface with the P300 speller: usability for disabled people with amyotrophic lateral sclerosis. Ann Phys Rehabil Med 2018;61(1):5–11.
• [3] Utsumi K, Takano K, Okahara Y, Komori T, Onodera O, Kansaku K. Operation of a P300-based brain–computer interface in patients with Duchenne muscular dystrophy. Sci Rep 2018;8(1):1753.
• [4] Rezeika A, Benda M, Stawicki P, Gembler F, Saboor A, Volosyak I. Brain–computer interface spellers: a review. Brain Sci 2018;8(4):57.
• [5] Li Y, Pan J, Wang F, Yu Z. A hybrid BCI system combining P300 and SSVEP and its application to wheelchair control. IEEE Trans Biomed Eng 2013;60(11):3156–66.
• [6] Xu M, Qi H, Wan B, Yin T, Liu Z, Ming D. A hybrid BCI speller paradigm combining P300 potential and the SSVEP blocking feature. J Neural Eng 2013;10(2):026001.
• [7] Lin Z, Zhang C, Zeng Y, Tong L, Yan B. A novel P300 BCI speller based on the triple RSVP paradigm. Sci Rep 2018;8 (1):3350.
• [8] Arvaneh M, Robertson IH, Ward TE. A P300-based brain– computer interface for improving attention. Front Human Neurosci 2018;12.
• [9] Jotheeswaran J, Sushama AS, Pippal S. Hybrid video surveillance systems using P300 based computational cognitive threat signature library. Proc Comput Sci 2018;145:512–9.
• [10] Xu M, Xiao X, Wang Y, Qi H, Jung T-P, Ming D. A brain– computer interface based on miniature-event-related potentials induced by very small lateral visual stimuli. IEEE Trans Biomed Eng 2018;65(5):1166–75.
• [11] Yu T, Yu Z, Gu Z, Li Y. Grouped automatic relevance determination and its application in channel selection for P300 BCIs. IEEE Trans Neural Syst Rehabil Eng 2015;23 (6):1068–77.
• [12] Rakotomamonjy A, Guigue V. BCI competition III: dataset II-ensemble of SVMs for BCI P300 speller. IEEE Trans Biomed Eng 2008;55(3):1147–54.
• [13] Cecotti H, Graser A. Convolutional neural networks for P300 detection with application to brain–computer interfaces. IEEE Trans Pattern Anal Mach Intell 2011;33 (3):433–45.
• [14] Chaurasiya RK, Londhe ND, Ghosh S. Multi-objective binary de algorithm for optimizing the performance of Devanagari script-based P300 speller. Biocybern Biomed Eng 2017;37 (3):422–31.
• [15] Idaji MJ, Shamsollahi MB, Sardouie SH. Higher order spectral regression discriminant analysis (HOSRDA): a tensor feature reduction method for ERP detection. Pattern Recogn 2017;70:152–62.
• [16] Pérez-Vidal A, Garcia-Beltran C, Martínez-Sibaja A, Posada- Gómez R. Use of the stockwell transform in the detection of P300 evoked potentials with low-cost brain sensors. Sensors 2018;18(5):1483.
• [17] Yoon K, Kim K. Multiple kernel learning based on three discriminant features for a P300 speller BCI. Neurocomputing 2017;237:133–44.
• [18] Ramele R, Villar A, Santos J. EEG waveform analysis of P300 ERP with applications to brain computer interfaces. Brain Sci 2018;8(11):199.
• [19] Stehlin SA, Nguyen XP, Niemz MH. EEG with a reduced number of electrodes: where to detect and how to improve visually, auditory and somatosensory evoked potentials. Biocybern Biomed Eng 2018;38(3):700–7.
• [20] Kundu S, Ari S. P300 detection with brain–computer interface application using PCA and ensemble of weighted SVMS. IETE J Res 2018;64(3):406–14.
• [21] Bengio Y, Lamblin P, Popovici D, Larochelle H. Greedy layer-wise training of deep networks. Advances in neural information processing systems. 2007. pp. 153–60.
• [22] Hinton GE, Zemel RS. Autoencoders, minimum description length and Helmholtz free energy. Advances in neural information processing systems. 1994. pp. 3–10.
• [23] Olshausen BA, Field DJ. Sparse coding with an overcomplete basis set: a strategy employed by V1? Vision Res 1997;37(23):3311–25.
• [24] Hinton GE, Osindero S, Teh Y-W. A fast learning algorithm for deep belief nets. Neural Comput 2006;18(7):1527–54.
• [25] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521(7553):436–44.
• [26] Kaper M, Meinicke P, Grossekathoefer U, Lingner T, Ritter H. BCI competition 2003-data set IIb: support vector machines for the P300 speller paradigm. IEEE Trans Biomed Eng 2004;51(6):1073–6.
• [27] Chaurasiya RK, Londhe ND, Ghosh S. An efficient P300 speller system for brain–computer interface. 2015 International Conference on Signal Processing, Computing and Control (ISPCC). IEEE; 2015. p. 57–62.
• [28] Kundu S, Ari S. P300 detection using ensemble of SVM for brain–computer interface application. 2018 9th International Conference on Computing, Communication and Networking Technologies (ICCCNT). IEEE; 2018. p. 1–5.
• [29] Kundu S, Ari S. Score normalization of ensemble SVMs for brain–computer interface P300 speller. 2017 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT). IEEE; 2017. p. 1–5.
• [30] Johnson GD, Krusienski DJ. Ensemble SWLDA classifiers for the P300 speller. International Conference on Human– Computer Interaction. Springer; 2009. p. 551–7.
• [31] Riccio A, Simione L, Schettini F, Pizzimenti A, Inghilleri M, Olivetti Belardinelli M, et al. Attention and P300-based BCI performance in people with amyotrophic lateral sclerosis. Front Human Neurosci 2013;7:732.
• [32] Cavrini F, Bianchi L, Quitadamo LR, Saggio G. A fuzzy integral ensemble method in visual P300 brain–computer interface. Comput Intell Neurosci 2016;2016:49.
• [33] Lee Y-R, Kim H-N. A data partitioning method for increasing ensemble diversity of an ESVM-based P300 speller. Biomed Signal Process Control 2018;39:53–63.
• [34] Liu M, Wu W, Gu Z, Yu Z, Qi F, Li Y. Deep learning based on batch normalization for P300 signal detection. Neurocomputing 2018;275:288–97.
• [35] Kshirsagar GB, Londhe ND. Improving performance of Devanagari script input-based P300 speller using deep learning. IEEE Trans Biomed Eng 2018.
• [36] Shan H, Liu Y, Stefanov T. A simple convolutional neural network for accurate P300 detection and character spelling in brain computer interface. IJCAI. 2018. pp. 1604–10.
• [37] Blankertz B, Muller K-R, Curio G, Vaughan TM, Schalk G, Wolpaw JR, et al. The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. IEEE Trans Biomed Eng 2004;51 (6):1044–51.
• [38] Blankertz B, Muller K-R, Krusienski DJ, Schalk G, Wolpaw JR, Schlogl A, et al. The BCI competition III: validating alternative approaches to actual BCI problems. IEEE Trans Neural Syst Rehabil Eng 2006;14(2):153–9.
• [39] Farwell LA, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalogr Clin Neurophysiol 1988;70 (6):510–23.
• [40] Aminanto ME, Choi R, Tanuwidjaja HC, Yoo PD, Kim K. Deep abstraction and weighted feature selection for Wi-Fi impersonation detection. IEEE Trans Inform Forensics Secur 2017;13(3):621–36.
• [41] Rojas R. The backpropagation algorithm. Neural networks. Springer; 1996. p. 149–82.
• [42] Kullback S, Leibler RA. On information and sufficiency. Ann Math Stat 1951;22(1):79–86.
• [43] Vapnik V. The nature of statistical learning theory. Springer Science & Business Media; 2013.
• [44] Tulyakov S, Jaeger S, Govindaraju V, Doermann D. Review of classifier combination methods. Machine learning in document analysis and recognition. Springer; 2008. p. 361–86.
• [45] Kübler A, Neumann N, Kaiser J, Kotchoubey B, Hinterberger T, Birbaumer NP. Brain–computer communication: self-regulation of slow cortical potentials for verbal communication. Arch Phys Med Rehabil 2001;82(11): 1533–9.
• [46] Iqbal S, Rizvi BA, Shanir PPM, Khan YU, Farooq O. Detecting P300 potential for speller BCI. 2017 International Conference on Communication and Signal Processing (ICCSP). 2017. pp. 0295–8. http://dx.doi.org/10.1109/ICCSP.2017.8286364.
• [47] Huang FJ, LeCun Y. Large-scale learning with SVM and convolutional for generic object categorization. 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1. IEEE; 2006. p. 284–91.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).