Fig 2 - uploaded by Daniel F. Leite
Content may be subject to copyright.
Download
View publication
The bi-dimensional Arousal-Valence model: a framework to describe and categorize human emotions

The bi-dimensional Arousal-Valence model: a framework to describe and categorize human emotions

Source publication
Fig. 1: eGNN-C+: Granular neural network with evolving structure and...
Fig. 2: The bi-dimensional Arousal-Valence model: a framework to...
Fig. 3: Examples of spectra and bands obtained from raw data generated...
Fig. 5: Evolution of the granular structure and performance of the...
EGNN-C+: Interpretable Evolving Granular Neural Network and Application in Classification of Weakly-Supervised EEG Data Streams
Preprint
Full-text available
  • Feb 2024
We introduce a modified incremental learning algorithm for evolving Granular Neural Network Classifiers (eGNN-C+). We use double-boundary hyper-boxes to represent granules, and customize the adaptation procedures to enhance the robust-ness of outer boxes for data coverage and noise suppression, while ensuring that inner boxes remain flexible to cap...
Cite
Download full-text

Context in source publication

Context 1
... upper part of the circle characterizes extreme emotional arousal or behavioral expression, whereas the lower part indicates apathy. We assign numerical values to the quadrants (see Figure 2) to represent the classes: 'bored', 'calm', 'anger', and 'happy'. As players actively influence the game outcome, their mental activity is high. ...