New generation feature engineering models based emotion classification using EEG signals

Date

2023-1-24

Author

Doğan, Abdullah

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

171
views

78
downloads

Cite This

This thesis presents a solution to automated accurate emotion classification by using two techniques. The first technique, called Clefia pattern-based features, utilizes Clefia encryption algorithm to extract features from EEG signals and classify emotions. This technique has shown low complexity with favorable accuracy in emotion classification. The second technique, PrimePatNet87, utilizes prime pattern and tunable q-factor wavelet transform techniques to extract features from EEG signals and classify emotions. This technique has been tested on two EEG datasets and demonstrated high emotion classification accuracy. Both of these techniques have the potential to be utilized in several applications where accurate emotion recognition is important. In addition, these techniques could be further developed and improved to achieve even higher accuracy in emotion classification. Overall, this thesis presents promising approaches for automated accurate emotion recognition using EEG.

Subject Keywords

Emotion classification, Prime pattern, Clefia pattern, mRMR selector

URI

https://hdl.handle.net/11511/103069

Collections

Graduate School of Natural and Applied Sciences, Thesis