Automatic detection and classification of artifacts in single-channel EEG

Ambulatory EEG monitoring can provide medical doctors important diagnostic information, without hospitalizing the patient. These recordings are however more exposed to noise and artifacts compared to clinically recorded EEG. An automatic artifact detection and classification algorithm for single-channel EEG is proposed to help identifying these artifacts. Features are extracted from the EEG signal and wavelet subbands. Subsequently a selection algorithm is applied in order to identify the best discriminating features. A non-linear support vector machine is used to discriminate among different artifact classes using the selected features. Single-channel (Fp1-F7) EEG recordings are obtained from experiments with 12 healthy subjects performing artifact inducing movements. The dataset was used to construct and validate the model. Both subject-specific and generic implementation, are investigated. The detection algorithm yield an average sensitivity and specificity above 95% for both the subject-specific and generic models. The classification algorithm show a mean accuracy of 78 and 64% for the subject-specific and generic model, respectively. The classification model was additionally validated on a reference dataset with similar results.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  M van de Velde,et al.  Detection of muscle artefact in the normal human awake EEG. , 1998, Electroencephalography and clinical neurophysiology.

[3]  Mark J. Cook,et al.  Epileptic Seizures and the EEG: Measurement, Models, Detection and Prediction , 2010 .

[4]  Tomás Ward,et al.  Artifact Removal in Physiological Signals—Practices and Possibilities , 2012, IEEE Transactions on Information Technology in Biomedicine.

[5]  R. E. Madsen,et al.  Automatic detection of childhood absence epilepsy seizures: toward a monitoring device. , 2012, Pediatric neurology.

[6]  安藤 寛,et al.  Cross-Validation , 1952, Encyclopedia of Machine Learning and Data Mining.

[7]  Kaleb McDowell,et al.  Detection and classification of subject-generated artifacts in EEG signals using autoregressive models , 2012, Journal of Neuroscience Methods.