http://hdl.handle.net/10468/625 2013-05-21T17:16:42Z http://hdl.handle.net/10468/836 A nonparametric feature for neonatal EEG seizure detection based on a representation of pseudo-periodicity Stevenson, Nathan J.; O'Toole, John M.; Rankine, Luke J.; Boylan, Geraldine B.; Boashash, Boualem Automated methods of neonatal EEG seizure detection attempt to highlight the evolving, stereotypical, pseudo-periodic, nature of EEG seizure while rejecting the nonstationary, modulated, coloured stochastic background in the presence of various EEG artefacts. An important aspect of neonatal seizure detection is, therefore, the accurate representation and detection of pseudo-periodicity in the neonatal EEG. This paper describes a method of detecting pseudo-periodic components associated with neonatal EEG seizure based on a novel signal representation; the nonstationary frequency marginal (NFM). The NFM can be considered as an alternative time-frequency distribution (TFD) frequency marginal. This method integrates the TFD along data-dependent, time-frequency paths that are automatically extracted from the TFD using an edge linking procedure and has the advantage of reducing the dimension of a TFD. The reduction in dimension simplifies the process of estimating a decision statistic designed for the detection of the pseudo-periodicity associated with neonatal EEG seizure. The use of the NFM resulted in a significant detection improvement compared to existing stationary and nonstationary methods. The decision statistic estimated using the NFM was then combined with a measurement of EEG amplitude and nominal pre- and post-processing stages to form a seizure detection algorithm. This algorithm was tested on a neonatal EEG database of 18 neonates, 826 hrs in length with 1389 seizures, and achieved comparable performance to existing second generation algorithms (a median receiver operating characteristic area of 0.902; IQR 0.835-0.943 across 18 neonates). 2012-05-01T00:00:00Z http://hdl.handle.net/10468/629 A nonlinear model of newborn EEG with nonstationary inputs Stevenson, Nathan J.; Mesbah, Mostefa; Boylan, Geraldine B.; Colditz, Paul B.; Boashash, Boualem McIntire, Larry V. Newborn EEG is a complex multiple channel signal that displays nonstationary and nonlinear characteristics. Recent studies have focussed on characterizing the manifestation of seizure on the EEG for the purpose of automated seizure detection. This paper describes a novel model of newborn EEG that can be used to improve seizure detection algorithms. The new model is based on a nonlinear dynamic system; the Duffing oscillator. The Duffing oscillator is driven by a nonstationary impulse train to simulate newborn EEG seizure and white Gaussian noise to simulate newborn EEG background. The use of a nonlinear dynamic system reduces the number of parameters required in the model and produces more realistic, life-like EEG compared with existing models. This model was shown to account for 54% of the linear variation in the time domain, for seizure, and 85% of the linear variation in the frequency domain, for background. This constitutes an improvement in combined performance of 6%, with a reduction from 48 to 4 model parameters, compared to an optimized implementation of the best performing existing model. 2010-09-01T00:00:00Z http://hdl.handle.net/10468/630 Multiple-view time-frequency distribution based on the empirical mode decomposition Stevenson, Nathan J.; Mesbah, Mostefa; Boashash, Boualem This study proposes a novel, composite time-frequency distribution (TFD) constructed using a multiple-view approach. This composite TFD utilises the intrinsic mode functions (IMFs) of the empirical mode decomposition (EMD) to generate each view that are then combined using the arithmetic mean. This process has the potential to eliminate the inter-component interference generated by a quadratic TFD (QTFD), as the IMFs of the EMD are, in general, monocomponent signals. The formulation of the multiple-view TFD in the ambiguity domain results in faster computation, compared to a convolutive implementation in the time-frequency domain, and a more robust TFD in the presence of noise. The composite TFD, referred to as the EMD-TFD, was shown to generate a heuristically more accurate representation of the distribution of time-frequency energy in a signal. It was also shown to have performance comparable to the Wigner-Ville distribution when estimating the instantaneous frequency of multiple signal components in the presence of noise. 2010-08-01T00:00:00Z