The present study aimed at investigating agerelated differences in prospective memory performance using a paradigm with high ecological validity and experimental control. Thirty old and 30 young adults completed the Dresden Breakfast task; a meal preparation task in the lab that comprises several subtasks including event-and time-based prospective memory tasks. Participants were required to plan how to perform the task. Results showed that young adults outperformed old adults: they completed more subtasks, showed better event-and time-based prospective memory performance and planning quality. In contrast, old adults adhered to their plans more closely than young adults. Further exploratory gender-specific analyses indicated that old women did not differ from young men in time-based prospective memory performance, general task performance and time monitoring in contrast to old men. Possibly, differences in experience in breakfast preparation might account for these differential findings.

No abstract

In this paper, we present and compare the accuracy of two types of classifiers to be used in a Brain-Computer Interface (BCI) based on the P300 waveforms of three post-stroke patients and six healthy subjects. Multilayer Perceptrons (MLPs) and Support Vector Machines (SVMs) were used for single-trial P300 discrimination in EEG signals recorded from 16 electrodes. The performance of each classifier was obtained using a five-fold cross-validation technique. The classification results reported a maximum accuracy of 91.79% and 89.68% for healthy and disabled subjects, respectively. This approach was compared with our previous work also focused on the P300 waveform classification.

A brain-computer interface (BCI) aims to provide their users the capability to interact with machines only through their though processes. BCIs targeted at subjects with mild and severe motor impairments are of special interest since this kind of technology would improve their lifestyles. This paper focuses on the classification of the P300 waveform from single trials in EEG to be used in a BCI using deep belief networks. This deep learning algorithm has the capability to identify relevant features automatically from the subject's EEG data, making its training requiring less preprocessing stages. The network is tested on healthy subjects and post-stroke victims. The highest accuracy achieved was of 91.6% for a healthy subject and 88.1% for a post-stroke victim.

No abstract

Brain-Computer Interface (BCI) allows its user to interact with a computer or other machines by only using their brain activity. People with motor disabilities are potential users of this technology since it could allow them to interact with their surroundings without using their peripheral nerves, helping them regain their lost autonomy. The P300 Speller is one of the most popular BCI applications. Its performance depends on its classifier's capacity to identify and discriminate the presence of the P300 potentials from electroencephalographic (EEG) signals.For the classifier to do this correctly, it is necessary to train it with a balanced data-set. However, as the P300 is usually elicited with an oddball paradigm, only unbalanced distributions can be obtained. This paper applies an under-sampling method based on Self-Organizing Maps (SOMs) on P300 EEG signals looking to increase the classifier's accuracy. Two classifying models, a deep feedforward network (DFN) and a deep belief network (DBN), are tested with data-sets obtained from healthy subjects and poststroke victims. We compared the results with our previous works and observed an increase of 7% in classification accuracy for our most critical subject. The DBN achieved a maximum classification accuracy of 95.53% and 94.93% for a healthy and post-stroke subject, while the DFN, 96.25% and 93.75%.