An Information Fusion Model of Customer Identification Based on ELM-SVM-DS

To solve those problems of the low recognition rate, the slow running speed and poor robustness of the existing customers´ identification system, an information fusion method based on Extreme Leaning Machine (ELM), Support Vector Machine (SVM) and DS evidence theory was proposed. For customer recognition problems, this information fusion model integrates advantages of ELM, SVM and DS, and can solve the shortcomings of models with a single algorithm. We used this model to do experiments with empirical data sets, and the simulation results show that the recognition accuracy of the model can be up to 91%, indicating that the method is feasible, and can effectively improve customer recognition rate and robustness.