An emotional recognition system based on physiological signals. We adopt the seven basic emotions that are: neutral, joy, sadness, fear, anger, disgust and surprise. An experiment was conducted to verify the feasibility of the proposed system. This experience has allowed us to acquire EEG signals and to create an emotional database. For this, we used the Emotive EPOC headset. Thereafter, we choose the fuzzy logic techniques to classify the EEG signals and to analyze the results.
In existing work EEG signals are classified into four emotional states happy, relax, sad and fear. We have used pre-processed dataset of EEG signals to build an emotion recognition system. To evaluate classification performance, Support Vector Machines is used and for feature extraction AR (Auto Regression) and FFT (Fast Fourier Transform) is used.
• The most of existing methods has recognized four emotions and using SVM classification.
• More complexity to recognition.
Our proposed method is first step consists in the recording of EEG signals, then the processing of these signals by applying the FFT and the band pass filter. The following step consists on the extraction of the emotion features, followed by the classification by fuzzy logic techniques.
We are trying to establish a protocol for induction of emotions by the recording of EEG signals.The possibility of inducing complex emotions and we lean for that on the dimensional approach of emotions. This approach proposes to model the emotions from the following three dimensions: arousal, valence, and dominance.
Finally we are going to classifying use fuzzy logic controller to recognize emotion and also find accuracy for each emotion.
• High accuracy.
• More emotion going to classify.
• High efficiency.
1. Fuzzy logic
2. Wavelet transform
Processor Type : Pentium -IV
Speed : 2.4 GHZ
Ram : 128 MB RAM
Hard disk : 20 GB HD
Operating System : Windows 7
Software Programming Package : Matlab R2014a
H. Zhang, S. Zheng, and J. Yuan, “A personalized TV guide system compliant with MHP," IEEE Trans. Consumer Electronics, vol. 51, no.2, May 2005, pp. 731-737.