Dynamic Fuzzy Neural Network Based Learning Algorithms for Ocular Artefact Reduction in EEG Recordings

• Published in: Neural processing letters Vol. 39; no. 1; pp. 45 - 67
• Main Authors: Mateo, J., Torres, A. M., García, M. A.
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01.02.2014; Springer; Springer Nature B.V
• Subjects: Algorithms; Applied sciences; Artificial Intelligence; Artificial neural networks; Biological and medical sciences; Brain; Clustering; Complex Systems; Computational Intelligence; Computer Science; Computer science; control theory; systems; Connectionism. Neural networks; Electric fields; Electrodes; Electrodiagnosis. Electric activity recording; Electroencephalography; Exact sciences and technology; Eye movements; Frequencies; Fuzzy logic; Investigative techniques, diagnostic techniques (general aspects); Kalman filters; Machine learning; Medical sciences; Methods; Nervous system; Neural networks; Pattern recognition. Digital image processing. Computational geometry; Radial basis function; Reduction; Support vector machines; Ocular artefact; Electroencephalogram; Biomedical signals; Eye blink; Neural networks; Eye movement; Brain; Input output; Error estimation; Central nervous system; Artefact; Electroencephalography; Dynamical system; Fuzzy neural nets; Encephalon; Biomedical data processing; Frequency band; Least squares method; Classification; Dynamic model; Filtering; Independent component analysis; Cluster; Neural network; Radial basis function; Recursive method; High frequency
• ISSN: 1370-4621; 1573-773X
• DOI: 10.1007/s11063-013-9289-6

Frequent occurrence of ocular artefacts leads to serious problems in reading and analysing the electroencephalogram (EEG) signal. These artefacts have high amplitude and overlapping frequency band with the physiological signal or real brain signal. Hence, it is difficult to reduce this type of artefacts by traditional filtering methods. In this paper, a novel ocular artefact removal method using artificial neural networks is described. In the proposed method, the number of radial basis function (RBF) neurons and input output space clustering are adaptively determined. Furthermore, the structure of the system and the parameters of the corresponding RBF units are trained automatically and relatively fast adaptation is attained. By the recursive least square error estimator techniques, the proposed system is suitable for real EEG applications. The advantages of the proposed method are demonstrated on EEG recordings by comparing with systems based on ICA. Our results demonstrate that this new system is preferable to other methods for ocular artefact reduction, achieving a better trade-off between removing artefacts and preserving inherent brain activities.