In this study, an analysis system embedding neuron-fuzzy prediction in feature extraction is proposed for brain–computer interface (BCI) applications. Wavelet-fractal features combined with neuro-fuzzy predictions are applied for feature extraction in motor imagery (MI) discrimination. The features are extracted from the electroencephalography (EEG) signals recorded from participants performing left and right MI. Time-series predictions are performed by training 2 adaptive neuro-fuzzy inference systems (ANFIS) for respective left and right MI data. Features are then calculated from the difference in multi-resolution fractal feature vector (MFFV) between the predicted and actual signals through a window of EEG signals. Finally, the support vector machine is used for classification. The proposed method estimates its performance in comparison with the linear adaptive autoregressive (AAR) model and the AAR time-series prediction of 6 participants from 2 data sets. The results indicate that the proposed method is promising in MI classification.
NicolaouNGeorgiouJ. The use of permutation entropy to characterize sleep electroencephalograms. Clin EEG Neurosci. 2011;42(1):24–28.
2.
WolpawJRBirbaumerNMcFarlandDJPfurtschellerGVaughanTM. Brain–computer interfaces for communication and control. Clin Neurophysiol. 2002;113(6):767–791.
3.
XuJZhaoSZZhangHSZhengCX. Decreased delta event-related synchronization in patients with early vascular dementia. Clin EEG Neurosci. 2011;42(1):53–58.
4.
AhmadlouMAdeliH. Fuzzy synchronization likelihood with application to attention-deficit/hyperactivity disorder. Clin EEG Neurosci. 2011;42(1):6–13.
5.
HsuWY. Continuous EEG signal analysis for asynchronous BCI application. Int J Neural Syst. 2011;21(4):335–350.
6.
LinCTLinFCChenSALuSWChenTCKoLW.EEG-based brain–computer interface for smart living environment auto-adjustment. J Med Biol Eng. 2010;30(4):237–245.
7.
HsuWY. EEG-based motor imagery classification using neuro-fuzzy prediction and wavelet fractal features. J Neurosci Methods. 2010;189(2):295–302.
8.
HsuWY. Application of competitive Hopfield neural network to brain–computer interface systems. Int J Neural Syst. 2012;22(1):51–62.
9.
TorresMSMCelesteWCBastos-FilhoTF. Brain–computer interface based on visual evoked potentials to command autonomous robotic wheelchair. J Med Biol Eng. 2010;30(6):407–415.
10.
HsuWY. Enhanced active segment selection for single-trial EEG classification. Clin EEG Neurosci. 2012;43(2):87–96.
11.
PfurtschellerGLopes da SilvaFH. Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin Neurophysiol. 1999;110(11):1842–1857.
12.
ShumwayRHStofferDS.Times Series Analysis and Its Application. New York, NY: Springer-Verlag; 2000.
13.
HuXProkhorovDVWunschIIDonaldC. Time series prediction with a weighted bidirectional multi-stream extended Kalman filter. Neurocomputing. 2007;70(13-15):2392–2399.
14.
StamatisNParthimosDGriffithTM. Forecasting chaotic cardiovascular time series with an adaptive slope multilayer perceptron neural network. IEEE Tran Biomed Eng. 1999;46(12):1441–1453.
15.
RongHJSundararajanNHuangGBSaratchandranP. Sequential Adaptive Fuzzy Inference System (SAFIS) for nonlinear system identification and prediction. Fuzzy Sets Systems. 2006;157(9):1260–1275.
16.
Jang RogerJS. ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans SMC. 1993;23(3):665–685.
17.
ObermaierBNeuperCGugerCPfurtschellerG. Information transfer rate in a five-classes brain–computer interface. IEEE Trans Neural Syst Rehabil Eng. 2001;9(3):283–288.
18.
GugerCEdlingerGHarkamWNiedermayerIPfurtschellerG. How many people are able to operate an EEG-based brain–computer interface (BCI)?IEEE Trans Neural Syst Rehabil Eng. 2003;11(2):145–147.
19.
BurkeDPKellySPChazal dePReillyRBFinucaneC. A parametric feature extraction and classification strategy for brain–computer interfacing. IEEE Trans Neural Syst Rehabil Eng. 2005;13(1):12–17.
20.
GugerCSchlöglANeuperCWalterspacherDStreinTPfurtschellerG.Rapid prototyping of an EEG-based brain–computer interface (BCI). IEEE Trans Neural Syst Rehabil Eng. 2001;9(1):49–58.
21.
MandelbrotBB. Fractal Geometry of Nature. San Francisco, CA: Freeman Press; 1982.
22.
HsuWY. Improved watershed transform for tumor segmentation: application to mammogram image compression. Expert Syst Appl. 2012;39(4):3950–3955.
23.
LeeWLChenYCHsiehKS. Ultrasonic liver tissues classification by fractal feature vector based on M-band wavelet transform. IEEE Trans Med Imaging. 2003;22(3):382–392.
24.
HsuWY. EEG-based motor imagery classification using enhanced active segment selection and adaptive classifier. Comput Biol Med. 2011;41(8):633–639.
25.
HsuWYLinCHHsuHJChenPHChenIR. Wavelet-based envelope features with automatic eog artifact removal: application to single-trial eeg data. Expert Syst Appl. 2012;39(3):2743–2749.
26.
BoserBEGuyonIMVapnikV.A training algorithm for optimal margin classifiers. Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory. 1992;144–152.
27.
HsuWYKuoWF. Unsupervised Fuzzy C-Means clustering for motor imagery EEG recognition. IJICIC. 2011;7(8):4965–4976.
28.
HsuWY. Fuzzy Hopfield neural network clustering for single-trial motor imagery EEG classification. Expert Syst Appl. 2012;39(1):1055–1061.
29.
AngKKGuanCChuaKS. A large clinical study on the ability of stroke patients to use EEG-based motor imagery brain–computer interface. Clin EEG Neurosci. 2011;42(4):253–258.
SchloglAKeinrathCSchererRPfurtschellerG. Estimating the mutual information of an EEG-based brain computer interface. Biomed Tech (Berl). 2002;47(1-2):3–8.
32.
SchloglALeeFBischofHPfurtschellerG. Characterization of four-class motor imagery EEG data for the BCI-competition 2005. J Neural Eng. 2005;2(4):L14–L22.
33.
HaselsteinerEPfurtschellerG. Using time-dependent neural networks for EEG classification. IEEE Trans Rehabil Eng. 2000;8(4):457–463.
HsuWYLinCCJuMSSunYN. Wavelet-based fractal features with active segment selection: application to single-trial EEG data. J Neurosci Methods. 2007;163(1):145–160.
37.
JasperH. Report of committee on methods of clinical exam in EEG. Electroencephalogr Clin Neurophysiol. 1958;10:370–375.
38.
LianKYSuCHHuangCS. Performance enhancement for T–S fuzzy control using neural networks. IEEE Trans Fuzzy Systems. 2006;14(5):619–627.
39.
DaubechiesI. Orthonormal bases of compactly supported wavelets. Comm Pure Appl Math. 1988;41:909–996.
40.
HsuWYPoonPWFSunYN. Automatic seamless mosaicing of microscopic images: enhancing appearance with colour degradation compensation and wavelet-based blending. J Microsc. 2008;231(3):408–418.
41.
HsuWY. Analytic differential approach for robust registration of rat brain histological images. Microsc Res Tech. 2011;74(6):523–530.
42.
HsuWYLiYCHsuCYLiuCTChiuHW. Application of multiscale amplitude modulation features and FCM clustering to brain–computer interface. Clin EEG Neurosci. 2012;43(1):32–38.
43.
LinCHChaoMWChenJYYuCWHsuWY.A high-capacity distortion-free information hiding algorithm for 3D polygon models. IJICIC. 2013;9(1): In press.
44.
HsuWYSunYN.EEG-based motor imagery analysis using weighted wavelet transform features. J Neurosci Methods. 2009;176(2):310–318.
45.
HsuWY.Wavelet-coherence features for motor imagery EEG analysis posterior to EOG noise elimination. IJICIC. 2013;9(1): In press.
