EEG-based emotion recognition using machine learning algorithms
Human emotions are very complex and hard to identify based on their facial expressions and appearance. Humans can hide their emotions with positive appearance and facial expression. Traditional emotion recognition techniques such as conducting questionnaires and facial recognition to analyse emotion...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2024
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/6431/1/21ACB00138_FYP.pdf http://eprints.utar.edu.my/6431/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850177490250629120 |
|---|---|
| author | Lam, Yee Wei |
| author_facet | Lam, Yee Wei |
| author_sort | Lam, Yee Wei |
| building | UTAR Library |
| collection | Institutional Repository |
| content_provider | Universiti Tunku Abdul Rahman |
| content_source | UTAR Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Human emotions are very complex and hard to identify based on their facial expressions and appearance. Humans can hide their emotions with positive appearance and facial expression. Traditional emotion recognition techniques such as conducting questionnaires and facial recognition to analyse emotion is not reliable. The result is varied and it is hard to define a standard as different people have different emotional levels. However, researchers have found out that physiological signals such as brain signal can be used to identify emotion accurately. It is because physiological signals are hard to control and more reliable.
Thus, this project proposed an optimised machine learning algorithms to classify emotion by analysing brain activity using Electroencephalogram (EEG) signals. Throughout this research study, models like Support Vector Machine (SVM), K-Nearest Neighbours (KNN) and Adaptive Boosting (AdaBoost) will be explored. This machine learning model is aimed to be implemented in various industries to overcome real-world challenges. Industries such as medical industry, business analysis in customer interested level, lie detectors and even for future research. In this project, SEED dataset will be used for training and testing purposes. The Electroencephalogram (EEG) signals from SEED dataset will be pre-processed and extracted using feature extraction techniques. Training will be conducted so the model can learn and capture patterns of data. Moreover, fine-tuning of model will be applied to get the optimal performance in machine learning model. An evaluation of overall performance for each machine learning will be carried out accordingly. |
| format | Final Year Project / Dissertation / Thesis |
| id | my-utar-eprints.6431 |
| institution | Universiti Tunku Abdul Rahman |
| publishDate | 2024 |
| record_format | eprints |
| spelling | my-utar-eprints.64312025-11-13T13:11:28Z EEG-based emotion recognition using machine learning algorithms Lam, Yee Wei T Technology (General) Human emotions are very complex and hard to identify based on their facial expressions and appearance. Humans can hide their emotions with positive appearance and facial expression. Traditional emotion recognition techniques such as conducting questionnaires and facial recognition to analyse emotion is not reliable. The result is varied and it is hard to define a standard as different people have different emotional levels. However, researchers have found out that physiological signals such as brain signal can be used to identify emotion accurately. It is because physiological signals are hard to control and more reliable. Thus, this project proposed an optimised machine learning algorithms to classify emotion by analysing brain activity using Electroencephalogram (EEG) signals. Throughout this research study, models like Support Vector Machine (SVM), K-Nearest Neighbours (KNN) and Adaptive Boosting (AdaBoost) will be explored. This machine learning model is aimed to be implemented in various industries to overcome real-world challenges. Industries such as medical industry, business analysis in customer interested level, lie detectors and even for future research. In this project, SEED dataset will be used for training and testing purposes. The Electroencephalogram (EEG) signals from SEED dataset will be pre-processed and extracted using feature extraction techniques. Training will be conducted so the model can learn and capture patterns of data. Moreover, fine-tuning of model will be applied to get the optimal performance in machine learning model. An evaluation of overall performance for each machine learning will be carried out accordingly. 2024-06 Final Year Project / Dissertation / Thesis NonPeerReviewed application/pdf http://eprints.utar.edu.my/6431/1/21ACB00138_FYP.pdf Lam, Yee Wei (2024) EEG-based emotion recognition using machine learning algorithms. Final Year Project, UTAR. http://eprints.utar.edu.my/6431/ |
| spellingShingle | T Technology (General) Lam, Yee Wei EEG-based emotion recognition using machine learning algorithms |
| title | EEG-based emotion recognition using machine learning algorithms
|
| title_full | EEG-based emotion recognition using machine learning algorithms
|
| title_fullStr | EEG-based emotion recognition using machine learning algorithms
|
| title_full_unstemmed | EEG-based emotion recognition using machine learning algorithms
|
| title_short | EEG-based emotion recognition using machine learning algorithms
|
| title_sort | eeg-based emotion recognition using machine learning algorithms |
| topic | T Technology (General) |
| url | http://eprints.utar.edu.my/6431/1/21ACB00138_FYP.pdf http://eprints.utar.edu.my/6431/ |
| url_provider | http://eprints.utar.edu.my |