Drowsiness/alertness algorithm development and validation using synchronized EEG and cognitive performance to individualize a generalized model

Johnson, Robin; Popovic, Djordje; Olmstead, Richard; Stikic, Maja; Levendowski, Daniel J.; Berka, Chris

doi:10.1016/j.biopsycho.2011.03.003

Cited by 118 publications

(92 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, in addition to the PSD values, each one-second epoch is assigned one of the following states: sleep onset, distraction, low engagement, and high engagement. More information about the validity of this metric can be found in the paper by Johnson et al (2011).…”

Section: Methodsmentioning

confidence: 99%

Assessing a learning process with functional ANOVA estimators of EEG power spectral densities

Gueorguiev

Ramírez-Moreno

2015

Cogn Neurodyn

View full text Add to dashboard Cite

We propose to assess the process of learning a task using electroencephalographic (EEG) measurements. In particular, we quantify changes in brain activity associated to the progression of the learning experience through the functional analysis-of-variances (FANOVA) estimators of the EEG power spectral density (PSD). Such functional estimators provide a sense of the effect of training in the EEG dynamics. For that purpose, we implemented an experiment to monitor the process of learning to type using the Colemak keyboard layout during a twelve-lessons training. Hence, our aim is to identify statistically significant changes in PSD of various EEG rhythms at different stages and difficulty levels of the learning process. Those changes are taken into account only when a probabilistic measure of the cognitive state ensures the high engagement of the volunteer to the training. Based on this, a series of statistical tests are performed in order to determine the personalized frequencies and sensors at which changes in PSD occur, then the FANOVA estimates are computed and analyzed. Our experimental results showed a significant decrease in the power of b and c rhythms for ten volunteers during the learning process, and such decrease happens regardless of the difficulty of the lesson. These results are in agreement with previous reports of changes in PSD being associated to feature binding and memory encoding.

show abstract

Section: Methodsmentioning

confidence: 99%

Assessing a learning process with functional ANOVA estimators of EEG power spectral densities

Gueorguiev

Ramírez-Moreno

2015

Cogn Neurodyn

View full text Add to dashboard Cite

show abstract

“…Researchers believe that EEGbased technologies are "gold standard" in detection of vigilance and alertness with their technological advantages to provide a task independent, non-disruptive method for detection [29]. They also believe that using EEG detection; it is possible to design systems that improve users' vigilance and alertness to provide safety in critical tasks (e.g.…”

Section: Introductionmentioning

confidence: 99%

Investigation of New Statistical Features for BCI Based Sleep Stages Recognition through EEG Bio-signals

Sefik

Elibol

Ince³

et al. 2014

Intelligent Computing in Bioinformatics

View full text Add to dashboard Cite

Abstract. Electroencephalogram (EEG) is one of the oldest techniques available to read brain data. It is a methodology to measure and record the electrical activity of brain using sensitive sensors attached to the scalp. Brain's electrical activity is visualized on computers in form of signals through BCI tools. It is also possible to convert these signals into digital commands to provide human-computer interaction (HCI) through adaptive user interfaces. In this study, a set of statistical features: mean entropy, skew-ness, kurtosis and mean power of wavelets are proposed to enhance human sleep stages recognition through EEG signal. Additionally, an adaptive user interface for vigilance level recognition is introduced. One-way ANOVA test is employed for feature selection. EEG signals are decomposed into frequency sub-bands using discrete wavelet transform and selected statistical features are employed in SVM for recognition of human sleep stages: stage 1, stage 3, stage REM and stage AWAKE. According to experimental results, proposed statistical features have a significant discrimination rate for true classification of sleep stages with linear SVM. The accuracy of linear SVM reaches to 93% in stage 1, 82% in stage 3, 73% in stage REM and 96% in stage AWAKE with proposed statistical features.

show abstract

“…Estudos indicam que até 30% dos acidentes de trânsito envolvendo vítimas fatais são ocasionados por motoristas sonolentos [1] .…”

unclassified

Detecção de sonolência através de aproximação não-linear associada ás transformadas wavelet e de Fourier

Silveira¹,

Kozakevicius²,

Rodrigues³

2014

Proceeding Series of the Brazilian Society of Computational and Applied Mathematics

View full text Add to dashboard Cite

Resumo: Neste estudo, o método de melhor aproximação por m termos, MAmT,é utilizado na classificação de parâmetros de um sinal de EEG relacionadosà sonolência. Esses parâmetros são obtidos através da: (i) série de Fourier do sinal de EEG, considerando as frequências correspondentes aos ritmos alfa e beta; (ii) série wavelet do sinal, considerando determinados níveis da transformada wavelet discreta de Daubechies. Os estados cognitivos são então classificados com base em um conjunto de pesos definidos através da MAmT. Quando aplicadas a sinais reais de EEG e comparadas com a classificação clínica, a metodologia utilizando MAmT e coeficientes wavelet apresentou uma taxa de acerto de 93% e efetividade 47% maior em relaçãoà outra, utilizando coeficientes de Fourier. A associação da MAmTà transformada wavelet de um sinal de EEG mostra-se, portanto, um método bastante efetivo e de baixa complexidade para a detecção de sonolência.Palavras-chave: Detecção de sonolência, melhor aproximação por m-termos, transformada wavelet, transformada de Fourier 1 Introdução A Administração Nacional de Segurança no Trânsito (National Highway Traffic Safety Administration, Estados Unidos), estima que 100.000 ocorrências policiais envolvendo acidentes de trânsito sejam registradas, por ano, decorrente de sonolência em motoristas. Estudos indicam que até 30% dos acidentes de trânsito envolvendo vítimas fatais são ocasionados por motoristas sonolentos [1] .A sonolência pode então ser considerada um problema de saúde pública [2] e justifica o interesse da indústria automobilística em desenvolver dispositivos de bordo capazes de detectar e mitigar sinais de sonolência em condutores. Com base nestas premissas, este estudo visa discutir a detecção de sonolência através da aplicação da melhor aproximação por m-termos (MAmT) na análise de um sinal de eletroencefalografia (EEG) utilizando as transformadas de Fourier e wavelet. Do ponto de vista neurofisiológico, a sonolência pode ser definida como a transição entre a vigília e o sono, caracterizada pelo decréscimo da atenção e por movimentos lentos. Este processo tem início com a ativação e inibição simultânea de grupos de neurônios em diferentesáreas do cérebro. Por ser rítmico e sincronizado, pode ser analisado através da variação da amplitude da corrente elétrica no cérebro, detectável através da eletroencefalografia (EEG). A sonolênciá e então caracterizada por (i) decréscimo de atividade no ritmo beta ([13-30]Hz); (ii) aumento e subsequente redução de atividade no ritmo alfa ([8-13]Hz) e (iii) aumento de atividade no ritmo teta ([4-8]Hz) [3].Desta perspectiva, a sonolênciaé considerada um padrão a ser reconhecido nos sinais cerebrais: a transformada de Fourier ou a transformada wavelet [3] são comumente utilizadas para

show abstract

Drowsiness/alertness algorithm development and validation using synchronized EEG and cognitive performance to individualize a generalized model

Cited by 118 publications

References 60 publications

Assessing a learning process with functional ANOVA estimators of EEG power spectral densities

Assessing a learning process with functional ANOVA estimators of EEG power spectral densities

Investigation of New Statistical Features for BCI Based Sleep Stages Recognition through EEG Bio-signals

Detecção de sonolência através de aproximação não-linear associada ás transformadas wavelet e de Fourier

Contact Info

Product

Resources

About