A Nonstationary Model of Newborn EEG

Abstract

Abstract-The detection of seizure in the newborn is a critical aspect of neurological research. Current automatic detection techniques are difficult to assess due to the problems associated with acquiring and labelling newborn electroencephalogram (EEG) data. A realistic model for newborn EEG would allow confident development, assessment and comparison of these detection techniques. This paper presents a model for newborn EEG that accounts for its self-similar and nonstationary nature. The model consists of background and seizure submodels. The newborn EEG background model is based on the short-time power spectrum with a time-varying power law. The relationship between the fractal dimension and the power law of a power spectrum is utilized for accurate estimation of the short-time power law exponent. The newborn EEG seizure model is based on a well-known time-frequency signal model. This model addresses all significant time-frequency characteristics of newborn EEG seizure which include; multiple components or harmonics, piecewise linear instantaneous frequency laws and harmonic amplitude modulation. Estimates of the parameters of both models are shown to be random and are modelled using the data from a total of 500 background epochs and 204 seizure epochs. The newborn EEG background and seizure models are validated against real newborn EEG data using the correlation coefficient. The results show that the output of the proposed models have a higher correlation with real newborn EEG than currently accepted models (a 10% and 38% improvement for background and seizure models, respectively).

A new neonatal seizure detection technique based on the time-frequency characteristics of the electroencephalogram

“…For the simulated data (see [7] for details) 400 epochs were realised. For the real data, a set of 100 epochs were taken from 6 different babies.…”

“…The main feature of neonatal EEG seizure identified in the TF domain is the presence of a dominant quasi-linear frequency modulated (LFM) or quasi-PWLFM signal component with or without additional harmonics [5,6,7] (henceforth collectively described as LFM-type components). It is was found that these LFM-type components are present and continuous for the seizure event, with their slope values ranging from approximately −0.1 → 0.1Hz/sec [5].…”

“…In order to ensure that these scenarios do not produce a large η j value, the sliding window applied to the data needs to have a significant overlap (larger than 75% of T e ). This can be achieved by setting b < 1/4, for the epoch start time t Although the seizure LFM-type components can have a slope as large as ±0.1Hz/sec, the rate of slope change is rather small over an epoch of less than 20 seconds [5,7]. Therefore, a penalisation measure should be added to the detection method to prevent false detections of components that do not conform to this signal type.…”

Neuro-Fuzzy Prediction for Brain-Computer Interface Applications

“…Since fractal dimension is relatively insensitive to signal scaling and shows a strong correlation with human judgment of surface roughness [20], it is chosen as the feature extraction method. A variety of approaches were proposed to estimate fractal dimension from signals or images [21][22][23][24]. A differential box counting (DBC) method covering a wide dynamic range with a low computational complexity is modified and used in this study [33].…”

“…Fractal dimension is a statistical quantity that effectively extracts fractal features. In the last decade, feature extraction characterized by fractal dimension has been widely applied in various kinds of biomedical image and signal analyses, such as texture extraction [21], seizure onset detection in epilepsy [22], routine detection of dementia [23], and EEG analyses of sleeping newborns [24]. In this study, discrete wavelet transform (DWT) together with modified fractal dimension is utilized for feature extraction.…”