Research On Identity Authentication And Teaching Effect Evaluation Scheme Based On EEG In Distance Education

With the rapid development of the Internet,the distance education model has been promoted,especially in recent years under the impact of the COVID-19 pandemic,and the number of distance teaching videos has grown rapidly.How to protect the distance teaching video resources and evaluate the actual learning effect of these videos objectively and impartially is an urgent problem for the distance education platform.In the current distance education system,static authentication of users’ name and password is mostly used to determine the validity of users’ identity.This authentication method will result password being forgetful,and easily lead to privacy crisis due to password disclosure.As for the video quality evaluation,subjective evaluation is still the main method at present,and there are some cases of malicious distortion and random evaluation,and the evaluation results are not convincing.Therefore,in view of the above problems,this thesis focuses on the following:1.An identity authentication scheme based on taste-induced EEG signal is proposed,which is suitable for distance education environment.In the registration stage,the EEG data and ECG data of the user after taste stimulation are collected,and the optimal EEG characteristic value sequence corresponding to the user is obtained and encoded by correlation coefficient.The DES encryption algorithm key is generated by the user’s ECG signal,and the characteristic value sequence is encrypted and preserved.In the authentication stage,the characteristic sequence of registration is compared.If the difference between the two is within the specified threshold,the authentication passes.The security and effectiveness of the scheme are verified by simulation experiment.The scheme overcomes the disadvantages of forgetting and forging authentication credentials,and encodes and encrypts the features of EEG signals to prevent intruders from destroying them.2.A distance teaching video evaluation scheme based on EEG signal is proposed,which is suitable for distance education environment.In this scheme,the quality of teaching videos is evaluated by the results of learning efficiency of subjects,and the EEG features of subjects under mental load test and concentration test are extracted by discrete wavelet transform,fuzzy entropy,power spectral density frequency domain analysis and other methods.By comparing six machine learning models,the best model for each test is selected.Entropy method is used to determine the weight of learning efficiency of each test,and the overall learning efficiency result is compared with the public review result,and the results within the evaluation range.It is found that the scheme is accurate and reliable.In addition,through the satisfaction test,it is proved that this scheme can also effectively improve the satisfaction of the subjects when they watch teaching videos.