Loading...

Designing an Emotion Capturing System Using Eeg Signals and Human-obot Interaction Platform Based on the Captured Emotion

Nazemi Harandi, Hamed | 2022

178 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55559 (08)
  4. University: Sharif University of Technology
  5. Department: Mechanical Engineering
  6. Advisor(s): Taheri, Alireza; Meghdari, Ali; Ghazizadeh, Ali
  7. Abstract:
  8. Emotions are one of the most important issues which affects daily life and activities. On the other hand, robots play an increasing role in human life and play a fundamental role in meeting our needs. One of these basic roles is empathy and verbal interaction between the robot and human. In this research, participant's emotions were stimulated in two ways: by using OASIS and GAPED image data sets and by instructing the participants to remind about their good or bad memories. During emotional stimulation, EEG signals have been recorded for the training and testing process. The preprocessing of training data includes filtering, removing bad parts of data, removing bad channels and interpolating them, division into trials, removing baseline activity and implementing ICA algorithm. Time domain, frequency domain and time-frequency domain features were extracted and classified using classic classifiers and neural network. The average accuracies were reported for use of different frequency bands, use of different classifiers, for different epoch lengths and the number of different hidden layers for neural network. There are three classes which include neutral, happy and sad emotional state. Finally, the best trained classifier is used for real-time simulation. The test data has been used for real-time classification. The test data preprocessing includes the steps mentioned for the training data preprocessing without performing ICA algorithm and removing damaged parts and bad channels of the data. After classification of emotions a virtual social robot interacts with the user. This interaction is based on the emotional state which classifier has detected. In interaction, the robot tries to improve the emotional state of the user by showing clips, playing songs, showing pictures and offering some activities. The result of interacting with the robot has been extracted using the UTAUT questionnaire.
  9. Keywords:
  10. Human Robot Interaction (HRI) ; Social Robotics ; Brain Signal ; Emotion Recognition ; Brain-Computer Interface (BCI)

 Digital Object List

 Bookmark

No TOC