Gaussian mixture models for classification of neonatal seizures using EEG

Thomas, Eoin; Temko, Andriy; Lightbody, Gordon; Marnane, William P.; Boylan, Geraldine B.

doi:10.1088/0967-3334/31/7/013

Cited by 54 publications

(29 citation statements)

References 36 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, spectral envelope based features are compared to the well established feature set which was developed over years of research, for neonatal seizure detection [6,16]. The results presented here indicate that spectral slope ASR features perform reasonably well on their own as a compact feature set arising from a single domain.…”

Section: Introductionmentioning

confidence: 86%

“…Similarly, the difference between seizure and non-seizure EEG in neonates can be relatively subtle, thus requiring a large set of features to quantify the change. A set of 55 features (Baseline, see Table II), which carry frequency, energetic and structural information (information theory) and which are previously exploited in [6,16,20], is extracted from the frequency and time domains. The majority of these features are taken from three studies on features for neonatal seizure detection.…”

Section: B Featuresmentioning

confidence: 99%

See 1 more Smart Citation

EEG Signal Description with Spectral-Envelope-Based Speech Recognition Features for Detection of Neonatal Seizures

Temko¹,

Nadeu²,

Marnane³

et al. 2011

IEEE Trans. Inform. Technol. Biomed.

View full text Add to dashboard Cite

In this work, features which are usually employed in automatic speech recognition (ASR) are used for the detection of seizures in newborn EEG. In particular, spectral envelope based features, composed of spectral powers and their spectral derivatives are compared to the established feature set which has been previously developed for EEG analysis. The results indicate that the ASR features which model the spectral derivatives, (either full-band or localized in frequency), yielded a performance improvement, in comparison to spectral-power based features. Indeed it is shown here that they perform reasonably well in comparison with the conventional EEG feature set. The contribution of the ASR features was analyzed here using the Support Vector Machines (SVM) recursive feature elimination technique. It is shown that the spectral derivative features consistently appear among the top-rank features. The study shows that the ASR features should be given a high priority when dealing with the description of the EEG signal.

show abstract

Section: Introductionmentioning

confidence: 86%

Section: B Featuresmentioning

confidence: 99%

EEG Signal Description with Spectral-Envelope-Based Speech Recognition Features for Detection of Neonatal Seizures

Temko¹,

Nadeu²,

Marnane³

et al. 2011

IEEE Trans. Inform. Technol. Biomed.

View full text Add to dashboard Cite

show abstract

“…The variance of the first (σ ∆j ) and second (σ ∆2j ) derivatives were used by Thomas et al (2010) for neonatal seizure detection. They are included here as features in the artefact classification task.…”

Section: Variance Of First and Second Derivativesmentioning

confidence: 99%

“…This feature was taken from epilepsy (D'Alessandro et al, 2003;Saab and Gotman, 2005;Faul et al, 2009) and neonatal seizure detection (Greene et al, 2008;Thomas et al, 2010) papers and refers to the total power in the frequency of typically normal EEG. As shown in Figure 3.15 the power in artefact EEG tends be distributed more uniformly than that of the background EEG which has a peak at 0.75 Hz.…”

Section: Total Powermentioning

confidence: 99%

“…The variance of the first (σ ∆j ) and second (σ ∆2j ) derivatives were used by Thomas et al (2010) for EEG seizure detection. They are included here as gyroscope features in the artefact classification task as they were found to provide reasonable separation between gyroscope signals during rest and signals during movements.…”

Section: Variance Of First and Second Derivativesmentioning

confidence: 99%

See 1 more Smart Citation

Artefact Detection and Removal Algorithms for EEG Diagnostic Systems

O’Regan¹

2018

Preprint

View full text Add to dashboard Cite

Type of publicationDoctoral thesis Rights AbstractThe electroencephalogram (EEG) is a medical technology that is used in the monitoring of the brain and in the diagnosis of many neurological illnesses. Although coarse in its precision, the EEG is a non-invasive tool that requires minimal set-up times, and is suitably unobtrusive and mobile to allow continuous monitoring of the patient, either in clinical or domestic environments. Consequently, the EEG is the current tool-of-choice with which to continuously monitor the brain where temporal resolution, ease-of-use and mobility are important.Traditionally, EEG data are examined by a trained clinician who identifies neurological events of interest. However, recent advances in signal processing and machine learning techniques have allowed the automated detection of neurological events for many medical applications. In doing so, the burden of work on the clinician has been significantly reduced, improving the response time to illness, and allowing the relevant medical treatment to be administered within minutes rather than hours.However, as typical EEG signals are of the order of microvolts (µV ), contamination by signals arising from sources other than the brain is frequent. These extra-cerebral sources, known as artefacts, can significantly distort the EEG signal, making its interpretation difficult, and can dramatically disimprove automatic neurological event detection classification performance.This thesis therefore, contributes to the further improvement of automated neurological event detection systems, by identifying some of the major obstacles in deploying these EEG systems in ambulatory and clinical environments so that the EEG technologies can emerge from the laboratory towards real-world settings, where they can have a real-impact on the lives of patients. In this context, the thesis tackles three major problems in EEG monitoring, namely: (i) the problem of head-movement artefacts in ambulatory EEG, (ii) the high numbers of false detections in state-of-the-art, automated, epileptiform activity detection systems and (iii) false detections in state-of-the-art, automated neonatal seizure detection systems. To accomplish this, the thesis employs a wide range of statistical, signal processing and machine learning techniques drawn from mathematics, engineering and computer science.The first body of work outlined in this thesis proposes a system to automatically detect head-movement artefacts in ambulatory EEG and utilises supervised machine learning i classifiers to do so. The resulting head-movement artefact detection system is the first of its kind and offers accurate detection of head-movement artefacts in ambulatory EEG.Subsequently, additional physiological signals, in the form of gyroscopes, are used to detect head-movements and in doing so, bring additional information to the head-movement artefact detection task. A framework for combining EEG and gyroscope signals is then developed, offering improved head-movement artefact detection.The artefact detecti...

show abstract

Machine Learning for EEG Analysis

2021

EEG Signal Processing and Machine Learning

View full text Add to dashboard Cite

Gaussian mixture models for classification of neonatal seizures using EEG

Cited by 54 publications

References 36 publications

EEG Signal Description with Spectral-Envelope-Based Speech Recognition Features for Detection of Neonatal Seizures

EEG Signal Description with Spectral-Envelope-Based Speech Recognition Features for Detection of Neonatal Seizures

Artefact Detection and Removal Algorithms for EEG Diagnostic Systems

Machine Learning for EEG Analysis

Contact Info

Product

Resources

About