Deep Learning of Empirical Mean Curve Decomposition-Wavelet Decomposed EEG Signal for Emotion Recognition
Recently, the emotional state recognition of humans via Electroencephalogram (EEG) is one of the emerging topics that grasp the attention of researchers too. This EEG based recognition is normally an effective model for many of the real-time applications, especially for disabled people. A number of researchers are in progress to make the recognition model more effective in terms of accurate emotion recognition. However, it is not so satisfactory in the precise accurate progressing. Hence this paper intends to recognize the human emotional states or affects through EEG signals by adopting advanced features and classifier models. In the first stage of recognition procedure, this paper exploits 2501 (EMCD) and Wavelet Transformation to represent the EEG signal in low dimension as well as descriptive. By EMCD, the EEG redundancy can be neglected, and the significant information can be extracted. The classification processes using the extracted features with the aid of a classifier named Deep Belief Network (DBN). The performance of the proposed Wavelet-EMCD (WE) approach is analyzed in terms of measures such as Accuracy, Sensitivity, Specificity, Precision, False positive rate (FPR), False negative rate (FNR), Negative Predictive Value (NPV), False Discovery Rate (FDR), F1Score and Mathews correlation coefficient (MCC) and proven the superiority of proposed work in recognizing the emotions more accurately.