Optimal channel selection for analysis of EEG-sleep patterns of neonates

Piryatinska, Alexandra; Woyczyński, Wojbor A.; Scher, Mark S.; Loparo, Kenneth A.

doi:10.1016/j.cmpb.2011.08.002

Cited by 22 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[72] robust classification results because at least one EEG channel combined with one electromyography (EMG) and one electrooculography (EOG) are required for manual scoring. Piryatinska et al [75] presented a channel selection method for neonate EEG sleep state classification using a multivariate analysis approach adopting filtering with a complete search strategy for subset channel selection. It has two main stages: scoring of sleep stages based on each combination of EEG channels and selection of the optimal channel combination.…”

Section: Channel Selection For Sleep State Classificationmentioning

confidence: 99%

A review of channel selection algorithms for EEG signal processing

Alotaiby

El‐Samie

Alshebeili

et al. 2015

EURASIP J. Adv. Signal Process.

351

181

View full text Add to dashboard Cite

Digital processing of electroencephalography (EEG) signals has now been popularly used in a wide variety of applications such as seizure detection/prediction, motor imagery classification, mental task classification, emotion classification, sleep state classification, and drug effects diagnosis. With the large number of EEG channels acquired, it has become apparent that efficient channel selection algorithms are needed with varying importance from one application to another. The main purpose of the channel selection process is threefold: (i) to reduce the computational complexity of any processing task performed on EEG signals by selecting the relevant channels and hence extracting the features of major importance, (ii) to reduce the amount of overfitting that may arise due to the utilization of unnecessary channels, for the purpose of improving the performance, and (iii) to reduce the setup time in some applications. Signal processing tools such as time-domain analysis, power spectral estimation, and wavelet transform have been used for feature extraction and hence for channel selection in most of channel selection algorithms. In addition, different evaluation approaches such as filtering, wrapper, embedded, hybrid, and human-based techniques have been widely used for the evaluation of the selected subset of channels. In this paper, we survey the recent developments in the field of EEG channel selection methods along with their applications and classify these methods according to the evaluation approach.

show abstract

Section: Channel Selection For Sleep State Classificationmentioning

confidence: 99%

A review of channel selection algorithms for EEG signal processing

Alotaiby

El‐Samie

Alshebeili

et al. 2015

EURASIP J. Adv. Signal Process.

351

181

View full text Add to dashboard Cite

show abstract

“…Among all of the possible parameters to be measured by polysomnography, the most frequent refer to reviewing the progress and quality of sleep of premature neonates 24,25 . Polysomnography allows the calculation of total sleep time, defined as the total sleep period minus the duration of wakefulness, sleep efficiency given by the ratio of total sleep time over the total sleep period, percentage of QS, percentage of AS and percentage of wakefulness 7,13,17,20,21,22 .…”

Section: Polysomnography and Neurodevelopment Of Premature Neonatesmentioning

confidence: 99%

Sleep deprivation, pain and prematurity: a review study

Bonan

Filho

Tristão

et al. 2015

Arq. Neuro-Psiquiatr.

View full text Add to dashboard Cite

The aim was to describe current reports in the scientific literature on sleep in the intensive care environment and sleep deprivation associated with painful experiences in premature infant. A systematic search was conducted for studies on sleep, pain, premature birth and care of the newborn. Web of Knowledge, MEDLINE, LILACS, Cochrane Library, PubMed, EMBASE, Scopus, VHL and SciELO databases were consulted. The association between sleep deprivation and pain generates effects that are observed in the brain and the behavioral and physiological activity of preterm infants. Polysomnography in intensive care units and pain management in neonates allow comparison with the first year of life and term infants. We have found few references and evidence that neonatal care programs can influence sleep development and reduce the negative impact of the environment. This evidence is discussed from the perspective of how hospital intervention can improve the development of premature infants.Keywords: sleep, pain, prematurity, polysomnography, neonatal intensive care.RESUMO O objetivo foi descrever o estado atual na literatura científica sobre privação do sono associado a experiências dolorosas no prematuro e o papel na evolução do sono em ambiente de terapia intensiva. Realizou-se uma busca sistemática para estudos sobre sono, dor, prematuridade e programas de atenção ao neonato. Foram consultados as bases Web-of-Knowledge, MEDLINE, LILACS, Biblioteca Cochrane, PubMed, EMBASE, Scopus, BVS e SciELO. A associação entre privação do sono e dor gera efeitos que são observados na atividade cerebral, fisiológica e comportamental dos prematuros. A polissonografia nas unidades intensivas e o manejo da dor em neonatos permitem comparação no primeiro ano de vida com crianças nascidas a termo. Encontraram-se poucas evidências de que programas de cuidado neonatal podem influenciar o desenvolvimento do sono e diminuir o impacto negativo do ambiente. Estas evidências são discutidas na perspectiva de como a intervenção hospitalar pode melhorar o desenvolvimento do prematuro.Palavras-chave: sono, dor, prematuridade, polissonografia, terapia intensiva neonatal.In recent decades there has been a considerable increase in the number of premature births and in the survival rate of these babies as a consequence of also increasing the effectiveness of intervention in Neonatal Intensive Care Unit (NICU). This relatively recent phenomenon has opened various fronts of research on the development of the fetus outside the uterus and its challenges. Among the areas that have aroused more interest and generated publications are the investigations on the development of sleep and pain perception and the future implications of sleep deprivation and exposure to pain at early ages. The uterine environment is suitable for the full growth and development of the human fetus site. The challenge of preterm birth and hospitalization in the NICU promotes an abrupt environmental difference for newborns which can bring challenges for future development. The inst...

show abstract

“…Other researchers, see for example Refs , found other characteristics, such as the fractional dimension (FD) of a curve C embedded in ℝ 2 , useful. Fractional dimension is computed using the formula

FD = \lim_{ϵ \to 0} \{\log a (ϵ)\} (\log ϵ {true)}^{- 1},

…”

Section: Automated Sleep Stage Classificationmentioning

confidence: 99%

“…Use of this approach in this context was first suggested in Refs and . It was further developed and applied to the problem of automated detection of the neonate sleep stages using signals from a single channel in Ref , and in multiple channels . The main assumption of this approach was that the EEG signal was piece‐wise stationary.…”

Section: Automated Sleep Stage Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Electroencephalogram‐sleep study

Piryatinska

2013

WIREs Computational Stats

Self Cite

View full text Add to dashboard Cite

The study of sleep, and in particular electroencephalogram (EEG)-sleep recordings, is important in several areas of medicine. Next to pain, sleep anomalies are the most significant indicators of illness. During sleep the human brain goes through several physiological stages; therefore, the problem of automated detection of sleep stages using EEG data naturally arises in neurosciences. A two step procedure of computerized scoring of sleep stages is considered, with the first step involving features extractions via spectral and nonlinear dynamics characteristics and the second step in which sleep classifications can be accomplished.

show abstract

Optimal channel selection for analysis of EEG-sleep patterns of neonates

Cited by 22 publications

References 24 publications

A review of channel selection algorithms for EEG signal processing

A review of channel selection algorithms for EEG signal processing

Sleep deprivation, pain and prematurity: a review study

Electroencephalogram‐sleep study

Contact Info

Product

Resources

About