Indicators of Sleepiness in an ambulatory EEG study of night driving

Papadelis, Christos; Kourtidou‐Papadeli, Chrysoula; Bamidis, Panagiotis D.; Chouvarda, Ioanna; Koufogiannis, Dimitrios; Bekiaris, Evangelos; Maglaveras, Nikolaos

doi:10.1109/iembs.2006.259614

Cited by 66 publications

(35 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work presented a mobile intelligent context collection system and an accompanying healthcare scenario that can be generalized to represent a context information collection to support other mobile self-wellness monitoring systems such as respiration, glucose levels and EEG [21]. It can also in principle be applied to other time series signals in power signature analysis, and weather reporting.…”

Section: Discussionmentioning

confidence: 99%

A mobile ECG monitoring system with context collection

Li¹,

Berry²,

Hayes³

2009

IFMBE Proceedings

View full text Add to dashboard Cite

Abstract-Preventative health management represents a shift from the traditional approach of reactive treatment-based healthcare towards a proactive wellness-management approach where patients are encouraged to stay healthy with expert support when they need it, at any location and any time. This work represents a step along the road towards proactive, preventative healthcare for cardiac patients. It seeks to develop a smart mobile ECG monitoring system that requests and records context information about what is happening around the subject when an arrhythmia event occurs. Context information about the subject's activities of daily living will, it is hoped, provide an enriched data set for clinicians and so improve clinical decision making. As a first step towards a mobile cardiac wellness guideline system, the authors present a system which can receive bio-signals that are wirelessly streamed across a body area network from Bluetooth enabled electrocardiographs. The system can store signals as they arrive while also responding to significant changes in Electrocardiogram activity. The authors have developed a prototype on a handheld computer that detects and responds to changes in the calculated heart rate as detected in an ECG signal. Although the general approach taken in this work could be applied to a wide range of bio-signals, the work focuses on ECG signals. The components of the system are, -A Bluetooth receiver, data collection and storage module -A real-time ECG beat detection algorithm. -An Event-Condition-Action (E-C-A) rule base which decides when to request context information from the user. -A simple user interface which can request additional information from the user. A selection of real-time ECG detection algorithms were investigated for this work and one algorithm was tested in MATLAB and then implemented in Java. In order to collect ECG signals (and in principle any signals), the generalised data collection architecture has also been developed using Java and Bluetooth technology. An Event-Condition-Action (ECA) rule based expert system evaluates the changes in heart beat interval to decide when to interact with the user to request context information.

show abstract

Section: Discussionmentioning

confidence: 99%

A mobile ECG monitoring system with context collection

Li¹,

Berry²,

Hayes³

2009

IFMBE Proceedings

View full text Add to dashboard Cite

show abstract

“…In the current work, as in [4,15,16], the EEG preprocessing is performed through the application of the fast Fourier transform (FFT) [17] on only one channel of the many possibilities of a PSG, namely the Pz-Oz channel. Thus, as one relevant contribution, the proposed sleep staging method relies on the selection of a reduced and fixed set of spectral-based features, which here are the first, third, and fourth statistical moments (mean, skewness and kurtosis, respectively) from Fourier coefficients corresponding to sleep-related frequencies of the brain (delta, theta, alpha, sigma, beta, and gamma).…”

Section: Introductionmentioning

confidence: 99%

Sleep Stages Classification Using Spectral Based Statistical Moments as Features

Braun

Kozakevicius

Silveira

et al. 2018

RITA

View full text Add to dashboard Cite

Abstract:In the pursuit of portable, efficient and effective sleep staging systems, researchers have been testing a massive number of combinations of EEG features and classifiers. State of the art sleep classification ensembles achieve accuracy in the order of 90%. However, there is presently no consensus regarding the best set of features for identifying sleep stages with a single EEG channel, leading researchers to modify the feature selection according to the number of classification stages. This paper introduces a reduced set of frequency-domain features capable of yielding high classification accuracy (90.9%, 91.8%, 92.4%, 94.3% and 97.1%) for all 6-to 2-state sleep stages. The proposed system uses fast Fourier transform (FFT) to convert data from Pz-Oz EEG channel into the frequency domain. Afterwards, eight statistical features are extracted from specific frequency ranges associated to brain rhythms, feeding a random forest classifier. Keywords: sleep stage classification -random forest -FFT -statistical momentsResumo: Na busca por sistemas portáveis, eficientes e efetivos para classificação de sono, pesquisadores têm testado um grande número de combinações de atributos de sinais EEG e classificadores. O estado da arte dos aplicativos de classificação para estágios de sono atinge taxas de acerto na ordem de 90%. Contudo, não existe um consenso em relação ao melhor grupo de atributos para identificar estágios de sono em sinais EEG de umúnico canal, levando pesquisadores a modificar a seleção dos atributos de acordo com o número de estágios a serem classificados. Este trabalho apresenta um conjunto reduzido de atributos, capaz de produzir uma classificação com taxas elevadas de acerto (90.9%, 91.8%, 92.4%, 94.3% and 97.1%) para todos os agrupamentos de estágios de sono (de 6 a 2 estágios). O sistema proposto utiliza a transformada rápida de Fourier (FFT) para converter os dados do canal de EEG Pz-Oz para o domínio da frequência. Posteriormente, oito atributos estatísticos são extraídos de faixas de frequência específicas associadas a ritmos cerebrais, alimentando um classificador do tipo floresta aleatória. Palavras-Chave: classificação de estágios de sono -floresta aleatória -FFT -momentos estatísticos

show abstract

“…Therefore, an adaptive threshold should be used for detection of drowsiness in different people. The adaptive threshold which is shown by T s was obtained according to equation (5). …”

Section: Eye Closurementioning

confidence: 99%