Marcin Kolodziej

A new method of EEG classification for BCI with feature extraction based on higher order statistics of wavelet components and selection with genetic algorithms

A new method of feature extraction and selection of EEG signal for brain-computer interface design is presented. The proposed feature selection method is based on higher order statistics (HOS) calculated for the details of discrete wavelets transform (DWT) of EEG signal. Then a genetic algorithm is used for feature selection. During the experiment classification is conducted on a single trial of EEG signals. The proposed novel method of feature extraction using HOS and DWT gives more accurate results then the algorithm based on discrete Fourier transform (DFT).

Implementation of selected EEG signal processing algorithms in asynchronous BCI

This paper discusses an asynchronous system of brain-computer interface, operating in real time. In the proposed system, the processing, analysis and classification of EEG signal is implemented using the Matlab programming environment and the BCI2000 package.

A new method of spatial filters design for brain-computer interface based on steady state visually evoked potentials

In the article the authors present their own method of designing spatial filters to use in brain-computer interface, based on steady state visually evoked potentials. The spatial filter is calculated by minimizing a specially created objective function. The developed method allows us to create a dedicated filter for each user, however it demands a calibration session. By using designed spatial filters it is possible to identify visual potentials for very close frequencies of flickering light with good efficiency (information transfer rate at 27-57bit/min).

Emotion recognition using facial expressions

Abstract In the article there are presented the results of recognition of seven emotional states (neutral, joy, sadness, surprise, anger, fear, disgust) based on facial expressions. Coefficients describing elements of facial expressions, registered for six subjects, were used as features. The features have been calculated for three-dimensional face model. The classification of features were performed using k-NN classifier and MLP neural network.

Implementation of automatic feature selection methods for BCI realization

The main task of brain-computer interface is to translate signals generated by neurons of the brain into commands. For the effective operation of BCI, efficient methods of feature selection of EEG signal are needed. In this article authors propose the use of correlation and t-statistics to feature selection.

System for automatic heart rate calculation in epileptic seizures

This article presents a comprehensive system for automatic heart rate (HR) detection. The system is robust and resistant to disturbances (noise, interferences, artifacts) occurring mainly during epileptic seizures. ECG signal filtration (IIR) and normalization due to skewness and standard deviation were used as preprocessing steps. A key element of the system is a reference QRS complex pattern calculated individually for each ECG recording. Next, a cross-correlation of the reference QRS pattern with short, normalized ECG windows is calculated and the maxima of the correlation are found (R-wave locations). Determination of the RR intervals makes possible calculation of heart rate changes and also heart rate variability (HRV). The algorithm was tested using a simulation in which a noise of an amplitude several times higher than ECG standard deviation levels was added. The proposed algorithm is characterized by high QRS detection accuracy, and high sensitivity and specificity. The algorithm proved to be useful in clinical practice, where it was used to automatically determine HR for ECG signals recorded before and during 58 focal seizures in 56 adult patients with intractable temporal lobe epilepsy.

Selection of EEG signal features for ERD/ERS classification using genetic algorithms

The article presents the use of genetic algorithm (GA) to select and classify ERD/ERS patterns. One hundred twenty eight channel EEG signal was used in the experiments. The signal was recorded for 40 people, during the process of imagining right and left hand movements. Feature extraction was performed using frequency analysis (FFT) with the resolution of 1Hz. So the features were spectral lines associated with particular electrodes. The selection of features, calculated for all people, was made with GA. The fitness function used in GA was EEG signal classification error calculated using LDA classifier and 5-CV test. The average accuracy of the classification for all people in 8–30Hz band was 0.85, while for the top 10 results 0.92.

Processing and Analysis of EEG Signal for SSVEP Detection

The aim of the article is to provide a systematic presentation of basic tools that are most commonly used to analyze electroencephalography signals (EEG) in brain–computer interfaces for detection of steady-state visually evoked potentials (SSVEP). We use a database of EEG signals containing SSVEP and demonstrate the desirability of the use of selected methods, showing their benefits. Methods such as independent components analysis (ICA), frequency analysis (DFT), and time-frequency analysis (STFT) are presented. For SSVEP, the features of EEG signal should be stable with time. Short-Time Fourier Transform (STFT) allows to confirm this stability. Independent Component Analysis is used to extract pure SSVEP components. The advantages of each method are described and the obtained results are discussed. Further, source location by the use of low-resolution electromagnetic tomography algorithm is demonstrated.

Automatic identification of experts in visual arts: The use of transitions between regions of interest in the image

The aim of this paper is to investigate the use of oculography signals for the recognition of experts in visual arts. We focused our attention on the number of sight transitions between characteristic image areas (ROIs). In the experiments we used oculographic data recorded at the Department of Experimental Psychology at the Catholic University of Lublin for 29 images and 34 users. The EM method was used to determine the ROIs, and the BIC criterion for determining the optimal number of clusters. The selected values of the matrix of transitions were used for learning and testing of the classifier. Very rigorous testing of the proposed algorithm was carried out approaching the actual operating conditions of the expert system. The presented results indicate that for some images there is a chance of identifying experts in the field of visual arts using transitions as oculographic features.

Classification of emotions from speech signal

The article presents an analysis of the possibility of recognizing speakers emotions from speech signal in Polish language. In order to perform experiments a database containing speech recordings with emotional content was created. On its basis, extraction of features from the speech signals was performed. The most important step was to determine which of the previously extracted features were the most suitable to distinguish emotions and with what accuracy the emotions could be classified. Two feature selection methods — Sequential Forward Search (SFS) and t-statistics were examined. Emotion classification was implemented using k — Nearest Neighbor (k-NN), Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) classifiers. Classification was carried out for pairs of emotions. The best results were obtained for classifying neutral and fear (91.9%) and neutral and joy emotions (89.6%).