Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/475808Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.advisor | Ahmed Patel, Prof. Dr. | - |
| dc.contributor.author | Kaveh Bakhtiyari (P53603) | - |
| dc.date.accessioned | 2023-10-05T06:42:01Z | - |
| dc.date.available | 2023-10-05T06:42:01Z | - |
| dc.date.issued | 2012-01-03 | - |
| dc.identifier.other | ukmvital:120180 | - |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/475808 | - |
| dc.description | Nowadays, emotions play an important role among human interactions. These emotions can be integrated into the computer system to make more effective interactions with users. Human Emotions Recognition (HER) is an innovative software-based method for detecting user’s emotions to determine proper responses in human-computer interaction. There are several methods to recognize the emotions like processing the facial expressions, human voice, body gestures and Electroencephalography (EEG) machines. However, there are still some challenges such as the accuracy of recognition, the number of supported emotions by the system, real-time processing, and recognition of emotions without any direct interaction between the user and computer. This thesis research aims to provide two solutions to increase the accuracy of recognition and to detect the emotion without direct interaction between human and computer. It is conducted in two phases. The first phase provides a solution based on HCI. It performs analysis on collected data of the users’ emotions and interactions with various input devices such as the mouse, keyboard and touch-screen. The system is trained in a supervised mode by Artificial Neural Network (ANN) and Support Vector Machine (SVM) techniques. Further analysis is applied to find the collaboration of various emotions, which may happen at a same time with different emotion scales. Moreover, the data are plotted on a fuzzy model since each emotion data are collected in diverse scales with overlapping crisp spectrums. The second phase, proposes a solution to recognize the emotion when the user is not interacting with the machine. This solution is based on HCI studies and un-concentrated recognition by processing the environment and surrounding area. For this purpose, it is suggested that environment features can be collected, tagged and trained for the system to recognize the users’ emotions at the same environment. The result of the first solution shows an increase of around 5% in accuracy by comparing with the existing methods. Furthermore, this result also shows that the cultural and language backgrounds can make different emotional expressions for the same emotion. The result of the second solution proves the recognition possibility, but with less accuracy. These results are significant contributions to show new directions of future research in this topical area of emotion recognition in computer.,Certification of Master's / Doctoral Thesis" is not available | - |
| dc.language.iso | eng | - |
| dc.publisher | UKM, Bangi | - |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | - |
| dc.rights | UKM | - |
| dc.subject | Artificial intelligence | - |
| dc.subject | Human-computer interaction | - |
| dc.subject | Universiti Kebangsaan Malaysia -- Dissertations | - |
| dc.subject | Dissertations, Academic -- Malaysia | - |
| dc.title | Intelligent human emotions recognition system in human computer interaction | - |
| dc.type | Theses | - |
| dc.format.pages | 132 | - |
| dc.identifier.callno | QA76.9.H85B337 2012 3 tesis | - |
| dc.identifier.barcode | 005361(2021)(PL2) | - |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.