Integration of similarity measurement and dynamic SVM for electrically evoked potentials prediction in visual prostheses research

► Attempts to take the advantages of similarity measurement (SM) and support vector machine (SVM) to generate a high performance electrical evoked potentials (EPPs) predictor in visual prostheses research. ► Apply SM and SVM to calculate the similarities of experimental cases and to predict EEPs behavior in terms of the temporal input, respectively. ► Add the similarities and temporal weights into SVM to indicate that recent data from similar experimental cases could provide more information than distant data from dissimilar ones.