DTSC - G2PI - Comunicaciones en congresos y otros eventos

Permanent URI for this collection

https://hdl.handle.net/10016/6745

Browse

Recent Submissions

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    New approach in features extraction for EEG signal detection
    (IEEE, 2009-11) Guerrero Mosquera, Carlos Andrés; Navia Vázquez, Ángel
    This paper describes a new approach in features extraction using time-frequency distributions (TFDs) for detecting epileptic seizures to identify abnormalities in electroencephalogram (EEG). Particularly, the method extracts features using the Smoothed Pseudo Wigner-Ville distribution combined with the McAulay-Quatieri sinusoidal model and identifies abnormal neural discharges. We propose a new feature based on the length of the track that, combined with energy and frequency features, allows to isolate a continuous energy trace from another oscillations when an epileptic seizure is beginning. We evaluate our approach using data consisting of 16 different seizures from 6 epileptic patients. The results show that our extraction method is a suitable approach for automatic seizure detection, and opens the possibility of formulating new criteria to detect and analyze abnormal EEGs.
  • No Thumbnail Available
    Publication
    Automatic removal of ocular artifacts from EEG data using adaptive filtering and independent component analysis
    (European Association for Signal, Speech, and Image Processing (EURASIP), 2009-08) Guerrero Mosquera, Carlos Andrés; Navia Vázquez, Ángel
    A method to eliminate eye movement artifacts based on Independent Component Analysis (ICA) and Recursive Least Squares (RLS) is presented. The proposed algorithm combines the effective ICA capacity of separating artifacts from brain waves, together with the online interference cancellation achieved by adaptive filtering. The method uses separate electrodes localized close to the eyes (Fp1, Fp2, F7 and F8), that register vertical and horizontal eye movements, to extract a reference signal. Each reference input is first projected into ICA domain and then the interference is estimated using the RLS algorithm. This interference estimation is subtracted from the EEG components in the ICA domain. Results from experimental data demonstrate that this approach is suitable for eliminating artifacts caused by eye movements, and the principles of this method can be extended to certain other sources of artifacts as well. The method is easy to implement, stable, and presents a low computational cost.