Single feature spatio-temporal architecture for EEG Based cognitive load assessment.

The study of electroencephalography (EEG) data for cognitive load analysis plays an important role in identification of stress-inducing tasks. This can be useful in applications such as optimal work allocation, increasing efficiency in the workplace and ensuring safety in difficult work environments. In order for such systems to be realistically deployable, easy acquisition and processing of the data on a wearable device is imperative. Current techniques primarily perform offline processing to analyse a multi-channel EEG to make a post facto assessment. This work focusses on building a new deep learning architecture that performs a single feature based spatio-temporal analysis of EEG data. This is achieved by creating a brain topographic map based on a single feature followed by spatio-temporal analysis using the developed network architecture. Data from two cognitive load experiments on the Physionet EEGMAT dataset were used to validate the performance. The network achieves an accuracy of 98.3% which is better than similar state-of-the-art approaches. Moreover, the proposed approach facilitates analysis of the spatial propagation of a signal, which is not possible through conventional EEG signal representations.

Affective response to tunes synthesized with musical pitch curves.

Tunes perceived as happy may help a user reach an affective state of positive valence. However, a user with negative valence may not be ready to listen to such a tune immediately. In this paper, we consider nudging a user from their current affective state to a target affective state in small steps. We propose a technique to generate a gradation of tunes between an initial-reference tune and a target-reference tune, to achieve the affect transition. The two-dimensional gradation is realized in time and in pitch, respectively, by varying the tempo and by the use of musical pitch curves, i.e. pitch transients or simply 'transients'. We exploit the duration and scaling of transients observed in South Indian music (Carnatic) to introduce transients into existing tunes. In our experiment, we have introduced the transients into Western music tunes. The results of perceptual evaluation show that the affective response to transients is likely to be higher at slow tempos than at fast tempos. Further, when felt, transient-tunes are twice as likely to be associated with positive valence than with negative valence, irrespective of tempo.