The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system
In human communication, expression and understanding of emotions facilitate the mutual sympathy. To approach this level of understanding in human-machine interaction, we need to equip machines with the means to interpret and understand human emotions without the input of the user’s translated intent...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2013
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my-mmu-ep.5533 |
|---|---|
| record_format |
uketd_dc |
| spelling |
my-mmu-ep.55332014-05-20T06:17:49Z The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system 2013-02 Mand, Ali Afzalian TJ Mechanical Engineering and Machinery In human communication, expression and understanding of emotions facilitate the mutual sympathy. To approach this level of understanding in human-machine interaction, we need to equip machines with the means to interpret and understand human emotions without the input of the user’s translated intention. There are a variety of emerging applications that track physiological data associated with emotional states over periods of time using biosensors. Physiological signals have been largely neglected for emotion recognition as compared with audio-visual emotion sensors such as facial expression or speech. Classifiers are important for emotion recognition regardless of the type of signal. This paper presents an effective adaptive neuro-fuzzy classifier using the linguistic hedges (ANFC-LH) in human emotion classification and investigates the potential of physiological signals as reliable channels for this purpose. 2013-02 Thesis http://shdl.mmu.edu.my/5533/ http://library.mmu.edu.my/diglib/onlinedb/dig_lib.php masters Multimedia University Faculty of Information Science and Technology |
| institution |
Multimedia University |
| collection |
MMU Institutional Repository |
| topic |
TJ Mechanical Engineering and Machinery |
| spellingShingle |
TJ Mechanical Engineering and Machinery Mand, Ali Afzalian The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system |
| description |
In human communication, expression and understanding of emotions facilitate the mutual sympathy. To approach this level of understanding in human-machine interaction, we need to equip machines with the means to interpret and understand human emotions without the input of the user’s translated intention. There are a variety of emerging applications that track physiological data associated with emotional states over periods of time using biosensors. Physiological signals have been largely neglected for emotion recognition as compared with audio-visual emotion sensors such as facial expression or speech. Classifiers are important for emotion recognition regardless of the type of signal. This paper presents an effective adaptive neuro-fuzzy classifier using the linguistic hedges (ANFC-LH) in human emotion classification and investigates the potential of physiological signals as reliable channels for this purpose. |
| format |
Thesis |
| qualification_level |
Master's degree |
| author |
Mand, Ali Afzalian |
| author_facet |
Mand, Ali Afzalian |
| author_sort |
Mand, Ali Afzalian |
| title |
The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system |
| title_short |
The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system |
| title_full |
The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system |
| title_fullStr |
The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system |
| title_full_unstemmed |
The application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system |
| title_sort |
application of adaptive neuro-fuzzy classifier using linguistic hedges in emotion recognition system |
| granting_institution |
Multimedia University |
| granting_department |
Faculty of Information Science and Technology |
| publishDate |
2013 |
| _version_ |
1747829578992189440 |