Catálogo de publicaciones - libros

Real-time assessment of mental workload from EEG plays an important role in enhancing symbiotic interaction of human operators in immersive environments. In this study we thus aimed at predicting the difficulty level of a video game a person is playing at a particular moment from the ongoing EEG activity. Therefore, we made use of power modulations in the theta (4–7 Hz) and alpha (8–13 Hz) frequency bands of the EEG which are known to reflect cognitive workload. Since the goal was to predict from multiple difficulty levels, established binary classification approaches are futile. Here, we employ a novel spatial filtering method (SPoC) that finds spatial filters such that their corresponding bandpower dynamics maximally covary with a given target variable, in this case the difficulty level. EEG was recorded from 6 participants playing a modified Tetris game at 10 different difficulty levels. We found that our approach predicted the levels with high accuracy, yielding a mean prediction error of less than one level.

The core characteristics of tactile stimuli, i.e., recognition reliability and tolerance to ambient interference, make them an ideal candidate to be integrated into a symbiotic system. The selection of the appropriate stimulation is indeed important in order not to hinder the interaction from the user’s perspective. Here we present the process of selecting the most adequate tactile stimulation delivered by a tactile vest while users were engaged in an absorbing activity, namely playing a video-game. A total of 20 participants (mean age 24.78;  = 1.57) were involved. Among the eight tactile stimuli selected, we found that the most frequently chosen stimulus was the one stimulating the back of the participant from the upper to the lower area.

In the frame of an experiment dealing with quantified-self and reflexivity, we collected audio-video data that provide us with material to discuss the ways in which the participants would work out social synergy through co-presence management and epistemic balance – accounting for their orientation towards the familiar symbiotic nature of human interactions. Following a Conversational Analysis perspective, we believe that detailed analysis of interactional behaviors offers opportunities for socially interactive robots design improvements, that is: identify and reproduce human ordinary skills in order to make the machines more adaptable.

Our lives are getting increasingly digital; much of our personal interactions are digitally mediated. A side effect of this is a growing digital footprint, as every action is logged and stored. This data can be very powerful, e.g., a person’s actions can be predicted, and deeply personal information mined. Hence, the question of who controls the digital footprint is becoming a pressing technological and social issue. We believe that the solution lies in human-centric personal data, i.e., the individuals themselves should control their own data. We claim that in order for human-centric data management to work, the individual must be supported in understanding their data. This paper introduces a personal data storage system Digital Me (DiMe). We describe the design and implementation of DiMe, and how we use state-of-the-art machine learning for visualisation and interactive modelling of the personal data. We outline several applications that can be built on top of DiMe.

A brain-computer interface (BCI) measures and interprets brain signals enabling people to communicate without the use of peripheral muscles. One of the common BCI paradigms are steady state visual evoked potentials (SSVEPs), brain signals induced by gazing at a constantly flickering target. The choice of stimulation frequencies and the number of simultaneously used stimuli highly influence the performance of such SSVEP-based BCI. In this article, a dictionary-driven four class SSVEP-based spelling application is presented, tested, and evaluated. To enhance classification accuracy, frequencies were determined individually with a calibration software for SSVEP-BCIs, enabling non-experts to set up the system. Forty-one healthy participants used the BCI system to spell English sentences (lengths between 23 and 37 characters). All participants completed the spelling task successfully. A mean accuracy of 97.92% and a mean ITR of 23.84 bits/min were achieved, 18 participants even reached 100% accuracy. On average the number of commands needed to spell the example sentences with four classes, without dictionary support is higher by a factor of 1.92. Thanks to the implemented dictionary the time needed to spell typical everyday sentences can be drastically reduced.