Master of Engineering Science
Electrical and Computer Engineering
An Electroencephalograph (EEG) signal is the recorded brain activity through electrodes on the scalp. In the medical domain, EEG analysis is used to detect conditions such as brain tumors, seizures, epilepsy, and depression. Emotion detection from EEG signals has potential in various applications including marketing, workplace optimization, improvement of human-machine interfaces, and user experience. Recent studies apply different machine learning techniques to detect emotions such as k-nearest neighbors, support vector machine, convolutional and feed forward neural networks. However, the comparison of reported results from different studies is difficult as they use different datasets and evaluation techniques. Examples include a hold-out evaluation with random test set selection from random subjects, individual models or one global model, and various versions of cross-validation. Moreover, most studies have focused on extracting frequency-based features and then using those features for classification. In Contrast, this thesis focuses on automatically extracting features from time series data by directly applying deep learning algorithms, namely, recurrent and convolutional neural networks to classify emotions using EEG data. The results on the DEAP dataset varied from 55.1% to 95.9% in classification accuracy. For comparison purposes, these models were compared to a feed forward neural network model with two commonly used frequency-based features: power spectral density and differential entropy. Extracted features achieved accuracy ranging from 54.5% to 69.6%. Also, this thesis considers two evaluation scenarios based on each subject's data. Results show that the classification performance varies greatly depending on the evaluation technique and highlight the need for a consistent evaluation technique in order to compare different studies.
Summary for Lay Audience
An Electroencephalograph (EEG) signal is the brain activity recorded using a special cap with electrodes. In the medical domain, EEG analysis is used to detect conditions such as brain tumors, seizures, epilepsy, and depression. EEG analysis has also helped with customer satisfaction and improved gameplay experience. Emotion detection from EEG signals has potential in various applications including marketing, workplace optimization, and user experience. There have been several studies on emotion recognition from EEG signals using machine learning algorithms. Most of the studies have focused on extracting handcrafted traditional frequency-based features for emotion classification and exploring the significance of electrodes mounted on different places in the cap. In recent years, deep learning techniques have demonstrated abilities to automatically extract features and, at the same time, achieved tremendous success in many domains. This thesis examines the direct application of deep learning techniques on the EEG data for emotion classification without using handcrafted features. The two approaches, the conventual network and recurrent neural network were used to carry out classification directly from time series data, and then, those approaches were compared to traditional techniques based on extracted features. Results show that the classification performance varies greatly depending on the evaluation technique and highlight the need for a consistent evaluation technique in order to compare different studies.
Gholami, Tina, "Emotion Detection from EEG Signals using Machine Learning Techniques" (2023). Electronic Thesis and Dissertation Repository. 9166.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Available for download on Monday, January 01, 2024