An EEG-based Identity Authentication System With Audiovisual Paradigm

With the continuous increment of security risks and the limitations of traditional modes,it is necessary to design a universal and trustworthy identity authentication system for intelligent IoT applications such as intelligent entrance guard.Recently,The characteristics of EEG(electroencephalography)have gained the confidence of researchers due to its uniqueness,stability and universality.However,the limited usability of experimental paradigm and the unsatisfactory classification accuracy have so far prevented the identity authentication system based on EEG to become commonplace in IoT scenario.To address these problems,we propose a new biometric authentication system based on the EEG visual and auditory paradigm,which can not only increase the intensity of stimulation based on a single induced paradigm,but also achieve good identity authentication for people who have obstacles in one of vision or hearing.On the research of the existing technology of EEG identity authentication at domestic and abroad,an audiovisual presentation paradigm is proposed to record the EEG signals of subjects.In the pre-processing stage,the reference electrode,ensemble averaging and independent component analysis methods are used to remove artifact.In the feature extraction stage,we propose an adaptive selection method of optimal channel and optimal time interval to avoid extracting invalid feature information.At the same time,In order to avoid blindly search,we apply the Best-First and CfsSubsetEval method,In the set selection,the best feature subsets are identified,and bagging ensemble learning algorithms is proposed to establish the optimal classification model.In terms of experimental simulation and performance evaluation,this thesis proposes three classification indicators: average classification accuracy,precision and false positive rate,the two classifiers bases: ROC curve and AUC area to judge the classification performance of the base learner,and the experimental result shows that our proposal achieves the best classification accuracy when compared with other paradigms and typical EEG-based authentication methods.At last,this thesis designs a prototype system based on the visual and auditory paradigm identity authentication,and completes the switch of the intelligent access gate through the intelligent gateway and the microcontroller.The login tests the legal rate and attack success rate of real users and counterfeiters.The experimental results show the feasibility,security and effectiveness of the proposed EEG identity authentication system.