Special Session on Challenges in Neuroengineering 2011 Abstracts


Full Papers
Paper Nr: 1
Title:

DEVELOPMENT OF A LOW-COST SVM-BASED SPONTANEOUS BRAIN-COMPUTER INTERFACE

Authors:

Fernando Flórez, José M. Azorín, Eduardo Iáñez, Andrés Úbeda and Eduardo Fernández

Abstract: This paper describes a spontaneous non-invasive Brain-Computer Interface (BCI) using an inexpensive EEG device. The aim of this work is to determine the feasibility of using the Emotiv Epoc device in a BCI. BCIs provide a method for interaction with a computer for people with severe communication disabilities. The EEG signals of five healthy users have been registered and preprocessed. The Fast Fourier Transform (FFT) has been used to extract the relevant characteristics of the EEG signals. Frequency spectrum between 8 Hz - 30 Hz has been calculated. An offline analysis to the recorded data has been performed using a Support Vector Machine (SVM) as a classification algorithm in order to differentiate three and four mental tasks. Results of up to 71% classification accuracy for three tasks and 64% classification accuracy for four tasks were obtained, showing that the Emotiv Epoc is suitable to be used in a Brain-Computer Interface.

Paper Nr: 5
Title:

SELF-ORGANIZING MAPS AS DATA CLASSIFIERS IN MEDICAL APPLICATIONS

Authors:

Jana Tuckova, Marek Bartu, Petr Zetocha and Pavel Grill

Abstract: Many researchers use mathematical-engineering methods in different domains of life, and medical research is no exception. One area for application of such methods is to assist people with different forms of disabili-ties. The methods described in the following text are oriented towards the analysis of disordered children’s speech with the diagnosis of Specific Language Impairment (SLI), also named as Developmental Dyspha-sia (DD), and the analysis of the expressive speech. Both methods make use of Kohonen Self-Organizing Maps (KSOM) or Supervised Self-Organizing Maps (SSOM) for the analysis and the classification of featu-res from utterances of healthy and ill children, or adult speakers for emotions analysis. The possibility of cluster visualisation is used for monitoring of disorder trends and therapy success. These experiments also demonstrate the ability of the KSOM or SSOM to classify emotions.

Paper Nr: 7
Title:

STATISTICAL ANALYSIS OF FUNCTIONAL MRI DATA USING INDEPENDENT COMPONENT ANALYSIS

Authors:

M. Bartés-Serrallonga, J. Solé-Casals, A. Adan, C. Falcón, N. Bargalló and J. M. Serra-Grabulosa

Abstract: Functional magnetic resonance imaging (fMRI) is a technique to map the brain, anatomically as well as physiologically, which does not require any invasive analysis. In order to obtain brain activation maps, the subject under study must perform a task or be exposed to an external stimulus. At the same time a large amount of images are acquired using ultra-fast sequences through magnetic resonance. Afterwards, these images are processed and analyzed with statistical algorithms. This study was made in collaboration with the consolidated Neuropsychology Research Group of the University of Barcelona, focusing on applications of fMRI for the study of brain function in images obtained with various subjects. This group performed a study which analyzed fMRI data, acquired with various subjects, using the General Linear Model (GLM). The aim of our work was to analyze the same fMRI data using Independent Component Analysis (ICA) and compare the results with those obtained through GLM. Results showed that ICA was able to find more active networks than GLM. The activations were found in frontal, parietal, occipital and temporal areas.

Paper Nr: 8
Title:

EFFECTIVE SELECTION OF ELECTRODE SUBSETS IN BCI EXPERIMENTS

Authors:

Andrey Eliseyev, Cecile Moro, Jean Faber, Alexander Wyss, Napoleon Torres, Corinne Mestais, Tetiana Aksenova and Alim-Louis Benabid

Abstract: Recently N-way Partial Least Squares (NPLS) were reported as an effective tool for neuronal signal decoding and BCI system calibration. This method simultaneously analyses data in several domains. It is based on the projection of a data tensor to a low dimensional space using all variables to create a final model. In the present paper the L1-Penalized NPLS is proposed for sparse BCI system calibration allowing to combine the projection technique with an effective selection of subset of features. The L1-Penalized NPLS was applied for binary self-paced BCI system calibration providing a subset of electrodes selection. Our BCI system is designed for animal research in particular for research in non-human primates.

Paper Nr: 9
Title:

CONCATENATION METHOD FOR HIGH-TEMPORAL RESOLUTION SSVEP-BCI

Authors:

Yohei Tomita, Antoine Gaume, Hovagim Bakardjian, Monique Maurice, Andrzej Cichocki, Yoko Yamaguchi, Gérard Dreyfus and François-Benoît Maurice

Abstract: Electroencephalographic (EEG) signals are generally non-stationary, however, nearly stationary brain responses, such as steady-state visually evoked potentials (SSVEP), can be recorded in response to repetitive stimuli. Although Fourier transform has precise resolution with long time windows (5 or 10 s for instance) to extract SSVEP response (1-100 Hz ranges), its resolution with shorter windows decreases due to the Heisenberg-Gabor uncertainty principle. Therefore, it is not easy to extract evoked responses such as SSVEP within short EEG epochs. This limits the information transfer rate of SSVEP-based brain-computer interfaces. In order to circumvent this limitation, we concatenate EEG signals recorded simultaneously from different channels, and we Fourier analyze the resulting sequence. From this constructed signal, high frequency resolution can be obtained with time epochs as small as only 1 s, which improves SSVEPs classification. This method may be effective for high-speed brain computer interfaces (BCI).

Short Papers
Paper Nr: 4
Title:

APPLICATION OF MULTIVARIATE EMPIRICAL MODE DECOMPOSITION FOR CLEANING EYE BLINKS ARTIFACTS FROM EEG SIGNALS

Authors:

Esteve Gallego-Jutglà, Jordi Solé-Casals, Tomasz M. Rutkowski and Andrzej Cichocki

Abstract: Eye movements and eye blinks are present in most of the electroencephalography (EEG) recordings, making it difficult to interpret or analyze the data. In this paper an extension of empirical mode decomposition (EMD) is proposed in order to clean EEG data of eye blinks artifacts. This is achieved by applying two cleaning methods to EEG simulated data. One of these methods is presented only for illustrative purposes, whereas the second one can be applied to real EEG data. The results show that the cleaned data with both these methods presents high correlation (|r|>0.8) with the simulated EEG clean data.

Paper Nr: 6
Title:

NEURODYNAMICS OF EMOTIONAL JUDGMENTS IN THE HUMAN BRAIN

Authors:

K. Hiyoshi-Taniguchi, F. B. Vialatte, M. Kawasaki, H. Fukuyama and A. Cichocki

Abstract: The purpose of this study is to clarify multi-modal brain processing related to human emotions. This study aimed to induce a controlled perturbation in the emotional system of the brain by multi-modal stimuli, and to investigate whether such emotional stimuli could induce reproducible and consistent changes in EEG signals. We exposed two subjects to auditory, visual, or combined audio-visual stimuli. Audio stimuli consisted of voice recordings of the Japanese word ‘arigato’ (thank you) pronounced with three different intonations (Angry - A, Happy - H or Neutral - N). Visual stimuli consisted of faces of women expressing the same emotional valences (A, H or N). Audio-visual stimuli were composed using either congruent combinations of faces and voices (e.g. H x H) or non-congruent (e.g. A x H). The data was collected with EEG system and analysis was performed by computing the topographic distributions of EEG signals in the theta, alpha and beta frequency ranges. We compared the conditions stimuli (A or H) vs. control (N), and congruent vs. non-congruent. Topographic maps of EEG power differed between those conditions on both subjects. The obtained results suggest that EEG could be used as a tool to investigate emotional valence and discriminate various emotions.

Paper Nr: 10
Title:

IMMERSIVE NEUROFEEDBACK - A New Paradigm

Authors:

Mohamed Elgendi, Francois Vialatte, Martin Constable and Justin Dauwels

Abstract: Healthcare organizations continue to pursue ways of offering higher-quality care to face the demand and expectations in promoting and maintaining health and in disease prevention. Currently, in neuroscience, there is an undergoing paradigm shift towards immersive neurofeedback mechanism. This will improve the user’s (or patient’s) ability to control brain activity, medical diagnoses, and rehabilitation of neurological or psychiatric disorders. Indeed, several psychological and medical studies have confirmed that virtual immersive activity is enjoyable, stimulating, and can have a healing effect. The new paradigm consists of an immersive room and three input devices: Emotiv headset (wireless non-invasive acquisition of brain waves), Kinect camera (gesture recognition), and wireless microphone (voice/speech recognition); towards immersive treatment and better quality health system in the near future.