Evaluating Classifiers for Emotion Recognition Using EEG

@inproceedings{Sohaib2013EvaluatingCF,
  title={Evaluating Classifiers for Emotion Recognition Using EEG},
  author={Ahmad Tauseef Sohaib and Shahnawaz Qureshi and Johan Hagelb{\"a}ck and Olle Hilborn and Petar Jercic},
  booktitle={HCI},
  year={2013}
}
There are several ways of recording psychophysiology data from humans, for example Galvanic Skin Response (GSR), Electromyography (EMG), Electrocardiogram (ECG) and Electroencephalography (EEG. [] Key Method K-Nearest Neighbor (KNN), Bayesian Network (BN), Artificial Neural Network (ANN) and Support Vector Machine (SVM) are some machine learning techniques that previously have been used to classify EEG data in various experiments. Five different machine learning techniques were evaluated in this paper…
Towards emotion recognition of EEG brain signals using Hjorth parameters and SVM
TLDR
The results showed that it is difficult to train a classifier to be accurate over the high number of emotions but SVM with proposed features were reasonably accurate over smaller emotion group identifying the emotional states with an accuracy up to 70%.
AsEmo: Automatic Approach for EEG-Based Multiple Emotional State Identification
TLDR
Experimental results on real-world EEG emotion recognition tasks demonstrate that AsEmo outperforms other state-of-the-art methods with a 2–8% improvement in terms of classification accuracy.
Classification of EEG-based emotion for BCI applications
TLDR
Using appropriate feature for extraction emotional state such as Discrete Wavelet Transform (DWT) and suitable learner such as Aftificial Neural Network (ANN), recognizer system can be accurately recognized and classify six emotional states such as fear, sad, frustrated, happy, pleasant and satisfied from inner emotion EEG signals.
Emotion recognition using EEG signal and deep learning approach
TLDR
This thesis presents an approach to classify human emotions using EEG signal by Convolutional Neural Network (CNN), and uses the Dataset for Emotion Analysis using Physiological signals (DEAP) dataset to transform the EEG signal from time domain to frequency domain and extract the features to classify the emotions.
Deep learninig of EEG signals for emotion recognition
TLDR
A deep learning algorithm is proposed to simultaneously learn the features and classify the emotions of EEG signals to achieve better recognition accuracy than conventional algorithms.
Combined analysis of GSR and EEG signals for emotion recognition
TLDR
The results of research related to the detection of emotions using combined analysis of galvanic skin response (GSR) and electroencephalographic (EEG) signals and two classifiers were implemented: support vector machine and k-nearest neighbors (k-NN).
Emotion recognition from EEG brain signals based on particle swarm optimization and genetic search
  • R. M. Mehmood, H. Lee
  • Computer Science
    2016 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)
  • 2016
TLDR
Emotion recognition accuracy had shown the possibility of classification of EEG brain activity from human brain signals using electroencephalography (EEG).
EEG-based Classification of the Intensity of Emotional Responses
TLDR
The proposed model excels in classifying emotional intensity and provides superior performance compared to the state-of-the-art emotion classification systems.
A Novel Two-tier Classifier based on K-Nearest Neighbour and Neural Network Classifier for Emotion Recognition using EEG Signals
TLDR
A novel approach to classify human emotions using a two-tier classifier which is a combination of both K-Nearest Neighbour (K-NN) and Neural Network (NN) classifier is presented.
...
...

References

SHOWING 1-10 OF 39 REFERENCES
Lifting scheme for human emotion recognition using EEG
TLDR
Results confirm the possibility of using two different lifting scheme based wavelet transform for assessing the human emotions from EEG signals and use Fuzzy C-Means clustering for classifying the emotions.
Emotion recognition using brain activity
TLDR
This system was designed using prior knowledge from other research, and is meant to assess the quality of emotion recognition using EEG signals in practice, and found that the EEG signals contained enough information to separate five different classes on both the valence and arousal dimension.
Classification of the emotional states based on the EEG signal processing
TLDR
Introverts have lower excitation threshold so the authors are able to detect the differences in their EEG activity with better accuracy, and the use of Kohonen's self-organizing map for visualization is suggested and demonstrated on one subject.
Classification of EEG for Affect Recognition: An Adaptive Approach
TLDR
The results show that affect recognition from EEG signals might be possible and an adaptive algorithm improves the performance of the classification task.
Emotion Recognition from Brain Signals Using Hybrid Adaptive Filtering and Higher Order Crossings Analysis
TLDR
Experimental results from the application of the HAF-HOC scheme clearly surpasses the latter in the field of emotion recognition from brain signals for the discrimination of up to six distinct emotions, providing higher classification rates up to 85.17 percent.
Real-Time EEG-Based Human Emotion Recognition and Visualization
TLDR
Fractal dimension based algorithm of quantification of basic emotions is proposed and its implementation as a feedback in 3D virtual environments adding one more so-called “emotion dimension” to human computer interfaces.
EEG-based emotion recognition in music listening: A comparison of schemes for multiclass support vector machine
TLDR
It is found that using one-against-one scheme of hierarchical binary classifier results in an improvement to performance, but also established an alternative solution for emotion recognition by proposed model-based scheme depending on 2D emotion model.
EEG-based Emotion Recognition The Influence of Visual and Auditory Stimuli
TLDR
A research project to recognize emotion from brain signals measured with the BraInquiry EEG PET device by establishing a suitable approach and determining optimal placement of a limited number of electrodes for emotion recognition.
EEG data classification with several mental tasks
TLDR
The main contribution of this paper is the development of neural network models for classification of temporal data from subjects for analysis of electroencephalogram (EEG) signals.
Toward Machine Emotional Intelligence: Analysis of Affective Physiological State
TLDR
It is found that the technique of seeding a Fisher Projection with the results of sequential floating forward search improves the performance of the Fisher Projections and provides the highest recognition rates reported to date for classification of affect from physiology: 81 percent recognition accuracy on eight classes of emotion, including neutral.
...
...