eduzhai > Applied Sciences > Engineering >

Classification and Recognition of Encrypted EEG Data Neural Network

  • Save

... pages left unread,continue reading

Document pages: 18 pages

Abstract: With the rapid development of Machine Learning technology applied inelectroencephalography (EEG) signals, Brain-Computer Interface (BCI) hasemerged as a novel and convenient human-computer interaction for smart home,intelligent medical and other Internet of Things (IoT) scenarios. However,security issues such as sensitive information disclosure and unauthorizedoperations have not received sufficient concerns. There are still some defectswith the existing solutions to encrypted EEG data such as low accuracy, hightime complexity or slow processing speed. For this reason, a classification andrecognition method of encrypted EEG data based on neural network is proposed,which adopts Paillier encryption algorithm to encrypt EEG data and meanwhileresolves the problem of floating point operations. In addition, it improvestraditional feed-forward neural network (FNN) by using the approximate functioninstead of activation function and realizes multi-classification of encryptedEEG data. Extensive experiments are conducted to explore the effect of severalmetrics (such as the hidden neuron size and the learning rate updated byimproved simulated annealing algorithm) on the recognition results. Followed bysecurity and time cost analysis, the proposed model and approach are validatedand evaluated on public EEG datasets provided by PhysioNet, BCI Competition IVand EPILEPSIAE. The experimental results show that our proposal has thesatisfactory accuracy, efficiency and feasibility compared with othersolutions.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×