Georgeta Mihaela Ungureanu

The impact of stress caused by car driving on heart's activity has been extensively studied for over 60 years. In the present paper, we studied the influence of stress on drivers' heart rate. The algorithm was applied on electrocardiographic signals from 6 drivers, and the resulting heart rate variability parameters in the time domain were analyzed comparing those in normal conditions to those in stress conditions. The results show that the stress and heart activity are closely correlated. This finding could be used to create an intelligent system in the car that would monitor the heart rate and adapt the conditions in the cabin in order to relax the driver, or in case of emergency, alert the nearest hospital.

Motor imagery, one of the first investigated neural process for Brain-Computer Interfaces (BCIs) still provides a great challenge nowadays. Aiming a better and more accurate control, multiple researches have been conducted by the scientific community. Nevertheless, there is still no robust and confident application developed. In order to augment the potential referring to motor imagery, and to attract user's interest, we propose multiple motor imagery tasks in combination with different visual or auditory stimuli. We use multi-class classification for discrimination and we observe confident classification performance for the task related to user's background.

Imagining a certain movement produces changes in the subject's EEG motor rhythm in the same manner in which the real execution of the movement does. These variations are reflected by Even-Related Desynchronizations (ERD) and appear asa magnitude decrease of the frequency components comprising the mu band. By monitoring the amplitude and power changes, the automatic detection of imagery or movement can be conducted. Furthermore, features can be extracted and used for real-time classification of these events. It is known that in most cases, the majority of changes are constrained within a narrow frequency interval representing the subject's reactive band. This provides means to increase the efficiency of interpreting desynchronizations by working only with the most representative information. The paper presents three improved methods of adaptively modelling the EEG signal, based on a Band Limited Multiple Fourier Linear Combiner (BMFLC). The time-frequency decomposition thus obtained is subsequently exploited in order to automatically identify the subject's specific reactive band. This process is conducted by detecting the highest decrease in power with the purpose of using a selection of power information as features for the classifier. The final goal of the investigated algorithms is to allow discrimination between left and right hand motor imagery, as demanded by a brain computer interface rehabilitation system.

In this work we investigate an image based algorithm as a reliablemethod to perceive the eye movement and offer new possibilities for the activity recognition. In order to test the effectiveness of the algorithm, the eye movement data was recorded using an electrooculography system. Different patterns of eye movement were analyzed within the conducted study. Three different lighting and three activities were performed in order to evaluate the performance of the algorithm.

This article proposes a pilot study regarding the influence of sounds (music) on EEG activity involved in BCI implementations, based on EEG analysis. The Independent Component Analysis is applied to extract the most relevant ICA components for which the event related (de)synchronization in the alpha/beta bands is furtherly considered for tracking the effect of the musing on brain activity, using on open access EEG dataset. The results are promising, allowing a clear desynchronization in the alpha/beta bands.

Motor imagery and actual movement are both tasks that bring forth a noticeable change in the subject's EEG mu rhythm known as Even-Related Desynchronisation (ERD). They appear as magnitude decreases of the frequencies included in the said band and can be tracked and measured for the automatic real-time detection and classification of the events. It has been proven that an important percent of the changes happen within a narrow frequency band called a reactive band, providing thus the means to significantly improve the efficiency of the interpretation of such events by concentrating the decisive information. The algorithm presented in this paper automatically identifies a subject's specific reactive band by detecting the highest decrease in power. The decision is made after the recorded EEG signal is modeled with a Band-Limited Multiple Fourier Linear Combiner (BMFLC). The method adaptively estimates the amplitude of each frequency component in the given band of interest and produces a precise time-frequency map that can be afterwards used for increasingly accurate classification and BCI applications.

Current trends and needs in Human-Computer Interaction (HCI) are rapidly increasing; however the possibility to estimate user's state remains unchanged. The need to predict user's state and intentions, and to adapt accordingly in real time to her/his decisions could bring benefits in this dual interaction. Following this purpose, we evaluate the state of a user by means of cognitive processing. In this way, we study the feasibility of detecting the level of cognitive processing, in order to be used for controlling or modifying the interface of a HCI application, such as, an information seeking application. We study this feasibility by analyzing the event-related spectral perturbations evoked by two levels of cognitive processing.