A study on the universal method of EEG and ECG prediction

摘要: As one of the most important attribute nonlinear dynamic system, chaotic time series include electroencephalogram (EEG) and electrocardiogram (ECG) have been widely studied for decades. However, universal prediction method them is still unexplored due to their inherent random feature complexity. Considering high-layer information images time-correlation data, traditional support vector machine (SVM), convolution neural network (CNN) bi-directional recurrent (BRNN) are main models being used. In this work, by combining CNN with BRNN, we developed a model (BRCNN) high accurate two problems (CTSPs), EEG ECG. For comparison, three SVM, CNN, BRCNN simultaneously performed on dataset signal ECG signal, results demonstrated superior classification quality (i.e., ∼0.90 ∼0.85 AUC, respectively). Such accuracy provides possibility applying