Fig 1 - uploaded by Anas Fattouh
Content may be subject to copyright.
Source publication
Steady-state visual evoked potential (SSVEP) is a well-established paradigm of brain computer interface (BCI) where the interaction between the user and a controlled device is achieved via brainwave activities and visual stimuli. Although SSVEP-based BCIs are known to have high information transfer rate (ITR), wrong feedback reduces the performance...
Contexts in source publication
Context 1
... are divided into training and test groups using 10-fo ld cross-validation method. The training samples are used to train a linear classifier and the test samples are used to test the trained classifier. The obtained classificat ion accuracy is 70% (which corresponds to error rate 30%). The trained classifier is applied in online experiment. Fig. 10 shows snapshots of online experiment in two cases, correct command and wrong command. The output of the online experiment is shown in Fig. 11. The blue continuous line shows the desired direction of the car, i.e. the direction that the car should follow to reach the final destination. The red dashed line shows the actual direction of ...
Context 2
... and the test samples are used to test the trained classifier. The obtained classificat ion accuracy is 70% (which corresponds to error rate 30%). The trained classifier is applied in online experiment. Fig. 10 shows snapshots of online experiment in two cases, correct command and wrong command. The output of the online experiment is shown in Fig. 11. The blue continuous line shows the desired direction of the car, i.e. the direction that the car should follow to reach the final destination. The red dashed line shows the actual direction of the car obtained from user SSVEPs. Co mparing the actual direction with the desired one, one can find that the averaged online error is 36.65%, ...
Context 3
... direction of the car, i.e. the direction that the car should follow to reach the final destination. The red dashed line shows the actual direction of the car obtained from user SSVEPs. Co mparing the actual direction with the desired one, one can find that the averaged online error is 36.65%, which is near to the trained error rate (30%). Fro m Fig. 13, we can notice that the zero errors correspond to change in arousal and valence values. The arousal value decreases while the valence value increases and this corresponds to satisfaction emo tion according to bi- dimension arousal-valence emotion model shown in Fig. 4. On the other hand, the nonzero errors correspond to increase in ...
Citations
... One of common EEG stimulus methods is steady-state visual evoked potential (SSVEP). SSVEP is oscillation of EEG signal evoked in the visual cortex when someone focuses on periodically flickered stimulus [3]. To produce a SSVEP response, a visual stimulus must be presented to the subject. ...
... Each table shows the classification results using decomposed EEG signal for D 1 , D 2 , and D 3 , respectively. 3 . The accuracy of testing is not high enough. ...
This paper presents a classification method of EEG signal for eye focuses which consists of three eyes movement left, top, and right. The electroencephalography (EEG) data were recorded from eight volunteers including males and females. The volunteers were stimulated using designed steady-state visual evoked potential (SSVEP) to gaze the designed SSVEP. The acquired EEG data were processed using wavelet decomposition and reconstruction. The reconstructed and decomposed signals were used as features to the input of artificial neural network (ANN). Based on the classification results, the decomposed signals of D1 give the best performance with the average accuracy of 98 % for validation, 67.19 % for validation, and 60.94 % for testing. Index Terms— Classification; EEG; Artificial neural networks (ANN); Steady-state visual evoked potential (SSVEP); Wavelet.
... lt is understood that different causes result in different emotions and hence different actions, and vise versa. Therefore, understading emtions can improve the usability of human machine interaction systems [1][2]. According to the lslamic faith, Quran is the speech of Allah, revealed to Prophet Muhammad. ...
Emotions play an important role in our thinking and behavior and hence contribute in shaping up of our personality. Many theoretical and experimental researches have been conducted to recognize the emotions from verbal or non-verbal behaviors. It is well known that the electroencephalogram (EEG) signals contain rich information about the activities of the brain and they can reliably enable us to estimate the emotions if they are properly interpreted. In this paper, we propose a model to discriminate the emotional state of a person by analyzing his brain signals recorded during listening to the Quran and using a machine learning approach. It is assumed that listening to the Quran brings reverence, and hence two types of emotions emerge which are distinguished as happy and unhappy. In our analysis, we used the Power Spectral Density (PSD) of different bands as features and the Support Vector Machine (SVM) as a classifier. Experiments were conducted by 14 participants and they gave a classification accuracy rate 85.86%.
... One of common EEG stimulus methods is steady-state visual evoked potential (SSVEP). SSVEP is oscillation of EEG signal evoked in the visual cortex when someone focuses on periodically flickered stimulus [3]. To produce a SSVEP response, a visual stimulus must be presented to the subject. ...
... Each table shows the classification results using decomposed EEG signal for D 1 , D 2 , and D 3 , respectively. 3 . The accuracy of testing is not high enough. ...
