Even with an unprecedented breakthrough of deep learning in electroencephalography(EEG),collecting adequate labelled samples is a critical problem due to laborious and time‐consuming labelling.Recent study proposed t...Even with an unprecedented breakthrough of deep learning in electroencephalography(EEG),collecting adequate labelled samples is a critical problem due to laborious and time‐consuming labelling.Recent study proposed to solve the limited label problem via domain adaptation methods.However,they mainly focus on reducing domain discrepancy without considering task‐specific decision boundaries,which may lead to feature distribution overmatching and therefore make it hard to match within a large domain gap completely.A novel self‐training maximum classifier discrepancy method for EEG classification is proposed in this study.The proposed approach detects samples from a new subject beyond the support of the existing source subjects by maximising the discrepancies between two classifiers'outputs.Besides,a self‐training method that uses unlabelled test data to fully use knowledge from the new subject and further reduce the domain gap is proposed.Finally,a 3D Cube that incorporates the spatial and frequency information of the EEG data to create input features of a Convolutional Neural Network(CNN)is constructed.Extensive experiments on SEED and SEED‐IV are conducted.The experimental evaluations exhibit that the proposed method can effectively deal with domain transfer problems and achieve better performance.展开更多
1 Introduction and main contributions In data-driven applications,such as location based services(LBSs),disease surveillance and social networks,etc.,information fusion is necessary for data owners to obtain better se...1 Introduction and main contributions In data-driven applications,such as location based services(LBSs),disease surveillance and social networks,etc.,information fusion is necessary for data owners to obtain better services.But the aggregated data may contain individuaFs sensi-tive information.Therefore,privacy preserving data fusion has become a substantial issue in data aggregating and mining[1,2].展开更多
基金supported in part by the National Natural Science Foundation of China under Grants 61866039in part by the Natural Science Foundation of Chongqing,China(No.cstc2019jscxmbdxX0021)+1 种基金in part by the Excellent Youths Project for Basic Research of Yunnan Province(No.202101AW070015)in part by the Key Cooperation Project of Chongqing Municipal Education Commission(No.HZ2021008).
文摘Even with an unprecedented breakthrough of deep learning in electroencephalography(EEG),collecting adequate labelled samples is a critical problem due to laborious and time‐consuming labelling.Recent study proposed to solve the limited label problem via domain adaptation methods.However,they mainly focus on reducing domain discrepancy without considering task‐specific decision boundaries,which may lead to feature distribution overmatching and therefore make it hard to match within a large domain gap completely.A novel self‐training maximum classifier discrepancy method for EEG classification is proposed in this study.The proposed approach detects samples from a new subject beyond the support of the existing source subjects by maximising the discrepancies between two classifiers'outputs.Besides,a self‐training method that uses unlabelled test data to fully use knowledge from the new subject and further reduce the domain gap is proposed.Finally,a 3D Cube that incorporates the spatial and frequency information of the EEG data to create input features of a Convolutional Neural Network(CNN)is constructed.Extensive experiments on SEED and SEED‐IV are conducted.The experimental evaluations exhibit that the proposed method can effectively deal with domain transfer problems and achieve better performance.
基金This work was supported in part by the National Natural Science Foundation of China(Grant No.42001398)Natural Science Foundation of Chongqing(cstc2020jcyj-msxmX0635)+4 种基金China Postdoctoral Science Foundation funded project(2021M693929)Science and Technology Research Project of CEC(KJQN201900612)Open Fund of LIESMARS(20S02)PhD Starts Fund of CQUPT(A2019-302)SRTP of CQUPT(A2019-175,A2020-106).
文摘1 Introduction and main contributions In data-driven applications,such as location based services(LBSs),disease surveillance and social networks,etc.,information fusion is necessary for data owners to obtain better services.But the aggregated data may contain individuaFs sensi-tive information.Therefore,privacy preserving data fusion has become a substantial issue in data aggregating and mining[1,2].