Realization of a cue based motor imagery brain computer interface with its potential application to a wheelchair

Akıncı, Berna
This thesis study focuses on the realization of an online cue based Motor Imagery (MI) Brain Computer Interface (BCI). For this purpose, some signal processing and classification methods are investigated. Specifically, several time-spatial-frequency methods, namely the Short Time Fourier Transform (STFT), Common Spatial Frequency Patterns (CSFP) and the Morlet Transform (MT) are implemented on a 2-class MI BCI system. Distinction Sensitive Learning Vector Quantization (DSLVQ) method is used as a feature selection method. The performance of these methodologies is evaluated with the linear and nonlinear Support Vector Machines (SVM), Multilayer Perceptron (MLP) and Naive Bayesian (NB) classifiers. The methodologies are tested on BCI Competition IV dataset IIb and an average kappa value of 0.45 is obtained on the dataset. According to the classification results, the algorithms presented here obtain the 4th level in the competition as compared to the other algorithms in the competition. Offline experiments are performed in METU Brain Research Laboratories and Hacettepe Biophysics Department on two subjects with the original cue-based MI BCI paradigm. Average prediction accuracy of the methods on a 2-class BCI is evaluated to be 76.26% in these datasets. Furthermore, two online BCI applications are developed: the ping-pong game and the electrical wheelchair control. For these applications, average classification accuracy is found to be 70%. During the offline experiments, the performance of the developed system is observed to be highly dependent on the subject training and experience. According to the results, the EEG channels P3 and P4, which are considered to be irrelevant with the motor imagination, provided the best classification performance on the offline experiments. Regarding the observations on the experiments, this process is related to the stimulation mechanism in the cue based applications and consequent visual evoking effects on the subjects.


Electro-magnetic source imaging using realistic head models
Akalın Acar, Zeynep; Gençer, Nevzat Güneri; Department of Electrical and Electronics Engineering (2005)
Electro-Magnetic Source Imaging (EMSI) is the estimation of the position, orientation and strength of active electrical sources within the brain from electrical and magnetic measurements. For an accurate source localization, the head model must correctly represent the electrical and geometrical properties of the head. To solve the forward problem using realistic head models numerical techniques must be used. This work uses the Boundary Element Method (BEM) for solving the forward problem. The accuracy of th...
Analysis and design of a compliant variable stroke mechanism
TANIK, ENGİN; Söylemez, Eres (Elsevier BV, 2010-10-01)
In this paper, analysis and design of an underactuated compliant variable stroke mechanism are presented by employing its pseudo-rigid-body model (PRBM). During the design two cases are considered: prescribed output loading and constant input torque. It is shown that this mechanism is suitable where variable stroke is required corresponding to variable output loading. It is also observed that this mechanism is capable of providing nearly constant force over a wide range of input. The analysis and design app...
Evaluating working memory capacity and cognitive load in learning from goal based scenario centered 3D multimedia
Kilic, Eylem; Yıldırım, Zahide (2010-02-08)
The purpose of this study is to investigate working memory capacity and cognitive load in learning from Goal Based Scenario centered 3D multimedia learning environment (GBSc3DM) designed based on Cognitive Load Theory (CLT). GBSc3DM was developed in two versions. In the designed of the first version (+CLT) cognitive load principles were applied. In the second version (-CLT), however, the principles were violated. 47 11(th) grade high school students were selected based on their working memory capacity (WMC)...
Prediction of slip in cable-drum systems using structured neural networks
KILIÇ, Ergin; Dölen, Melik (SAGE Publications, 2014-02-01)
This study focuses on the slip prediction in a cable-drum system using artificial neural networks for the prospect of developing linear motion sensing scheme for such mechanisms. Both feed-forward and recurrent-type artificial neural network architectures are considered to capture the slip dynamics of cable-drum mechanisms. In the article, the network development is presented in a progressive (step-by-step) fashion for the purpose of not only making the design process transparent to the readers but also hig...
Application of Wiener Deconvolution Model in P300 Spelling Paradigm
Erdogan, Balkar; Gençer, Nevzat Güneri (2009-01-01)
Spelling Paradigm first introduced by Farwell and Donchin, is one of the Brain Computer Interface (BCI) applications that enables paralyzed people to communicate with their environment. In such a problem, user needs to focus on the characters which are randomly flashed row or column-wise on the computer screen in a small period of time. The accuracy in spelling words is the main problem in this scheme and the duration of the correct prediction is quite important. The purpose of this work is twofold: to anal...
Citation Formats
B. Akıncı, “Realization of a cue based motor imagery brain computer interface with its potential application to a wheelchair,” M.S. - Master of Science, Middle East Technical University, 2010.