Information Technology Reference
In-Depth Information
5.7
Questions
1. How can the theoretical landscape of emotion theories be described?
2. What are the predictions about the emotional experience evoked by music that
one can formulate from a discrete emotion perspective? From a dimensional
perspective? From an appraisal perspective?
3. What are the practical implications of favouring one theory over an other for
the application of machine learning techniques to neural signals in the emo-
tional experience evoked by music?
4. What are the advantages of using the self-assessment manikin for assessing
emotional states of individuals? Are there any disadvantages?
5. Describe an experimental paradigm which would bene
t more from a contin-
uous self-assessment tool than a discrete approach, explain your reasons?
6. What information you would need to collect during experiments aimed at
assessing EEG correlates of emotional states in order to use supervised tech-
niques to learn to recognise the brain emotional states?
7. What class of the machine learning techniques is suitable for EEG analysis if
one does not have objective information about the emotional states of the
subject?
8. What are the advantages of generative classi
ers over the discriminative ones?
Can you list also some of their disadvantages?
9. An EEG experiment is conducted to measure neurological activity during a
music listening task. The experimental hypothesis is that listening to music
with a faster tempo may increase the power spectral density in the alpha
frequency band recorded from the prefrontal cortex. Describe the types of
features that may be extracted from (1) the EEG and (2) the music, to test this
hypothesis.
10. How might ICA be applied to identify neural correlates of emotional responses
to stimuli in the EEG?
References
Albrecht R, Ewing S (1989) Standardizing the administration of the pro
le of mood states
(POMS): development of alternative word lists. J Pers Assess 53(1):31
39
-
Aloise F, Schettini F, Aric
P et al (2012) A comparison of classi
cation techniques for a gaze-
independent P300-based brain
รณ
computer interface. J Neural Eng 9(4):045012
Alpaydin E (2004) Introduction to machine learning. MIT Press, Cambridge
Bradley MM, Lang PJ (1994) Measuring emotion: the self-assessment manikin and the semantic
differential. J Behav Ther Experim Psychiatry 25(1):49
-
59
Bradley MM, Lang PJ, Margaret M et al (2007) The international affective digitized sounds
affective ratings of sounds and instruction manual. Technical report B-3, University of Florida,
Gainesville, Fl
Christensen T (2002) The Cambridge history of western music theory. Cambridge University
Press, Cambridge
-
