Emotion recognition from EEG using Matlab
Amal Naser Emes1, Ms.Anju Iqubal2 (Associate Professor)
Department of Electronics and Communication
YCET College, Kollam, Kerala
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Our brain state is affected by and adapted to our surroundings. Therefore, to study natural states of the brain, it is desirable to measure brain responses in natural environments outside the lab. Among functional brain scanning methods, electroencephalography (EEG) is the most promising method for non-invasive brain monitoring in real-life environments. To enable long-term recordings in real-life, EEG devices must be wearable, user-friendly, and discreet. Ear-EEG is a method where EEG signals are recorded from electrodes placed on an earpiece inserted into the ear. The compact and discreet nature of an ear-EEG device makes it suitable for long-term real-life recordings. In this study, 3 to 5 subjects were recorded with conventional scalp EEG and ear-EEG. All recordings were performed with the same instrumentation and paradigms in both a lab setting and a real-life setting. The ear-EEG recordings were performed with a previously developed dry contact ear-EEG platform. In this research, an emotion recognition system is developed based on valence/arousal model using electroencephalography (EEG) signals. EEG signals are decomposed into the gamma, beta, alpha and theta frequency bands using discrete wavelet transform (DWT), and spectral features are extracted from each frequency band. Principle component analysis (PCA) is applied to the extracted features by preserving the same dimensionality, as a transform, to make the features mutually uncorrelated. Support vector machine (SVM) and artificial neural network (ANN) are used to classify emotional states. performs with 91.3% accuracy for arousal and 91.1% accuracy for valence, both in the beta frequency band. Our approach shows better performance compared to existing algorithms.
Key Words: EEG,PCA,DWT,ANN,SVM