Segmentation and tracking of the electro-encephalogram signal using an adaptive recursive bandpass filter

Abstract

An adaptive filtering approach for the segmentation and tracking of electro-encephalogram (EEG) signal waves is described. In this approach, an adaptive recursive bandpass filter is employed for estimating and tracking the centre frequency associated with each EEG wave. The main advantage inherent in the approach is that the employed adaptive filter has only one unknown coefficient to be updated. This coefficient, having an absolute value less than 1, represents an efficient distinct feature for each EEG specific wave, and its time function reflects the non-stationarity behaviour of the EEG signal. Therefore the proposed approach is simple and accurate in comparison with existing multivariate adaptive approaches. The approach is examined using extensive computer simulations. It is applied to computer-generated EEG signals composed of different waves. The adaptive filter coefficient (i.e. the segmentation parameter) is -0.492 for the delta wave, -0.360 for the theta wave, -0.191 for the alpha wave, -0.027 for the sigma wave, 0.138 for the beta wave and 0.605 for the gamma wave. This implies that the segmentation parameter increases with the increase in the centre frequency of the EEG waves, which provides fast on-line information about the behaviour of the EEG signal. The approach is also applied to real-world EEG data for the detection of sleep spindles.

Efficient automatic classifiers for the detection of A phases of the cyclic alternating pattern in sleep

“…A possible idea for a future improvement of the method is that of splitting the EEG signal into windows of different lengths. In fact, here, for ease of computation, all the descriptors have been computed on 1 s-long windows, although, being the EEG a non-stationary signal, it would perhaps be more appropriate to employ segmentation techniques such as that proposed in [9] in order to split it into windows in which it maintains uniform statistical properties, and to compute the features on these new windows.…”

Rules-Based and SVM-Q Methods With Multitapers and Convolution for Sleep EEG Stages Classification

“…The Muscle movement or MM characteristic features were originally defined by the R&K rules [2] and used in many other studies when analysing EEG data for sleep stages classification [23], [7] [24] [8] [10] [35] [23].…”

Biomedical Signal Processing

“…Five outstanding papers were selected for this section [1][2][3][4][5]. The papers are dedicated to the analysis of transcranial Doppler ultrasound data for embolus identification, to the segmentation of the EEG signal waves, to the analysis of spinal somatosensory evoked potentials, to the determination of the complexity of EEG signals for measuring the depth of anesthesia, and to the reconstruction of neural activity from MEG data.…”

“…The work by Gharieb et al [2] involves segmentation of EEG data for tracking the delta, theta, alpha, sigma, beta and the gamma wave. An adaptive recursive bandpass filter is employed for estimating and tracking the center frequency associated with each of these waves.…”

“…On an organ level there are various research areas in which novel methodology is developed [1][2][3][4][5][6][7]. Examples are the imaging of electrical function within the human brain and heart from observations on the body surface (from electric potential (e.g., EEG) or magnetic field mapping (e.g., MEG) data), the non-invasive and real-time beat-to-beat monitoring of stroke volume, blood pressure, total peripheral resistance and for assessment of autonomic function by measuring ECG, blood pressure and thorax impedance, and the classification of biosignals like EEG or MEG.…”