Removal of EOG artifacts from EEG using a cascade of sparse autoencoder and recursive least squares adaptive filter

• Published in: Neurocomputing (Amsterdam) Vol. 214; pp. 1053 - 1060
• Main Authors: Yang, Banghua, Duan, Kaiwen, Zhang, Tao
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 19.11.2016
• Subjects: Brain computer interfaces (BCIs); Electroencephalogram (EEG); Electrooculogram (EOG); Recursive least squares (RLS) adaptive filtering; Sparse autoencoder (SAE); Electrooculogram (EOG); Recursive least squares (RLS) adaptive filtering; Brain computer interfaces (BCIs); Electroencephalogram (EEG); Sparse autoencoder (SAE)
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2016.06.067

Electrooculogram (EOG) artifacts are the most important form of interferences in electroencephalogram (EEG) based brain computer interfaces (BCIs). In traditional methods for EOG artifacts removal, either an additional EOG recording in real time or multi-channel (more than three channels) EEG recording is required. To address these limitations of existing methods, a method using a cascade of sparse autoencoder (SAE) and recursive least squares (RLS) adaptive filter is proposed to remove the EOG artifacts from EEG. The proposed approach consists of offline stage and online stage. The high-order statistical moments information in the EOG artifacts can be learned automatically by using only EOG signals during offline stage and so an SAE model is obtained. In the online stage, the learned SAE model is firstly used to identify and extract preliminary EOG artifacts from a given raw EEG signal. Then an RLS adaptive filter uses the identified EOG artifacts as reference signal to remove interference without parallel EOG recordings. Compared with the exiting methods, the proposed method has the following advantages: (i) nonuse of an additional EOG recording in removal process, (ii) few number of EEG channels being used in removal process, and (iii) time-saving. The performance of the proposed method is evaluated by EEG classification accuracy and time consumption. Compared with traditional methods, the proposed method is proven to be more effective and faster. Moreover, experiment results also show good generalization ability in cross-subject testing scenarios. •The proposed method does not need an additional EOG recording, which is portable for online using.•The proposed method is suitable for any number of EEG channels.•Compared with traditional methods, the proposed method is more time saving and effective.