Fuzzy Model on Human Emotions Recognition
This work addresses emotion recognition for human-computer interaction, but it is incremental as it builds on existing fuzzy and non-fuzzy approaches with mixed results.
The paper tackles human emotion recognition from keyboard, mouse, and touchscreen interactions using a fuzzy model, achieving detection of more emotions but with lower accuracy for some compared to non-fuzzy methods, as tested with SVM.
This paper discusses a fuzzy model for multi-level human emotions recognition by computer systems through keyboard keystrokes, mouse and touchscreen interactions. This model can also be used to detect the other possible emotions at the time of recognition. Accuracy measurements of human emotions by the fuzzy model are discussed through two methods; the first is accuracy analysis and the second is false positive rate analysis. This fuzzy model detects more emotions, but on the other hand, for some of emotions, a lower accuracy was obtained with the comparison with the non-fuzzy human emotions detection methods. This system was trained and tested by Support Vector Machine (SVM) to recognize the users' emotions. Overall, this model represents a closer similarity between human brain detection of emotions and computer systems.