A decision support system for automated identification of sleep stages from single-channel EEG signals

Hassan, Ahnaf Rashik; Subaşı, Abdülhamit

doi:10.1016/j.knosys.2017.05.005

Cited by 198 publications

(93 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Entropy metrics, J-means approach [8] 81% Hybrid features, Artificial neural networks [49] 81.55% Energy features, Recurrent neural classifier [50] 87.20% Graph features, SVM [9] 88.90% Spectral Features, Bootstrap aggregating [10] 86.53% Temporal features and hierarchical decision tree [51] 77.98% Fuzzy logic based iterative method [36] 74.50% Multiscale entropy, LDA [22] 83.60% Proposed Method 91.10%…”

Section: Methods Accuracymentioning

confidence: 99%

See 1 more Smart Citation

Ensemble SVM Method for Automatic Sleep Stage Classification

Aličković

Subaşı

2018

IEEE Trans. Instrum. Meas.

Self Cite

228

View full text Add to dashboard Cite

Abstract-Sleep scoring is used as a diagnostic technique in the diagnosis and treatment of sleep disorders. Automated sleep scoring is crucial, since the large volume of data should be analyzed visually by the sleep specialists which is burdensome, time-consuming tedious, subjective, and error-prone. Therefore, automated sleep stage classification is crucial step in sleep research and sleep disorder diagnosis. In the present article, a robust system, consisting of three modules, is proposed for automated classification of sleep stages from single channel EEG. In the first module, signals taken from Pz-Oz electrode were denoised using multiscale principal component analysis. In the second module, the most informative features are extracted using discrete wavelet transform (DWT) and then, statistical values of DWT sub-bands are calculated. In the third module, extracted features were fed into an ensemble classifier, which can be called as rotational support vector machine (RotSVM). The proposed classifier combines advantages of the principal component analysis and SVM to improve classification performances of the traditional SVM. The sensitivity and accuracy values across all subjects were 84.46% and 91.1% respectively for five stage sleep classification with Cohen's kappa coefficient of 0.88. Obtained classification performance results indicate that, it is possible to have an efficient sleep monitoring system with a single channel EEG, and can be used effectively in medical and home-care application.

show abstract

Section: Methods Accuracymentioning

confidence: 99%

“…Many studies have been conducted with the aim to describe and detect different sleep stages [6,7,8,9,10]. In general, any objective, non-biased automated classification system consists of three different modules, namely pre-processing module, feature extraction module and classification module.…”

Section: Introductionmentioning

confidence: 99%

Ensemble SVM Method for Automatic Sleep Stage Classification

Aličković

Subaşı

2018

IEEE Trans. Instrum. Meas.

Self Cite

228

View full text Add to dashboard Cite

show abstract

“…The analysis of the studies on automatic sleep scoring reveals that the number of these studies is increasing in recent years (Hassan & Bhuiyan, 2015, 2016a, 2016b, 2016c, 2017; Hassan, Bashar & Bhuiyan, 2015a, 2015b; Hassan & Subasi, 2017). Moreover, the comparison of previous methods of sleep scoring with the introduced method in the present study showed some interesting points.…”

Section: Discussionmentioning

confidence: 99%

“…Many examples can be mentioned here regarding the application of intelligent techniques in medical diagnostic automation (Hassan & Haque, 2015a, 2016a, 2016b; Bashar, Hassan & Bhuiyan, 2015a; Hassan, 2015a, 2015b, 2016) and EEG analysis (Hassan & Haque, 2015b, 2015c, 2016a, 2017; Bashar, Hassan & Bhuiyan, 2015b; Hassan, Siuly & Zhang, 2016; Hassan & Subasi, 2016, 2017; Hassan & Bhuiyan, 2015, 2016a, 2016b, 2016c, 2017; Hassan, Bashar & Bhuiyan, 2015a, 2015b). In 2011, Kravoska et al achieved 81% accuracy in sleep scoring using various features derived from PSG signals.…”

Section: Introductionmentioning

confidence: 99%

Performance comparison of machine learning techniques in sleep scoring based on wavelet features and neighboring component analysis

Savareh

Bashiri

Behmanesh

et al. 2018

PeerJ

View full text Add to dashboard Cite

IntroductionSleep scoring is an important step in the treatment of sleep disorders. Manual annotation of sleep stages is time-consuming and experience-relevant and, therefore, needs to be done using machine learning techniques.MethodsSleep-EDF polysomnography was used in this study as a dataset. Support vector machines and artificial neural network performance were compared in sleep scoring using wavelet tree features and neighborhood component analysis.ResultsNeighboring component analysis as a combination of linear and non-linear feature selection method had a substantial role in feature dimension reduction. Artificial neural network and support vector machine achieved 90.30% and 89.93% accuracy, respectively.Discussion and ConclusionSimilar to the state of the art performance, the introduced method in the present study achieved an acceptable performance in sleep scoring. Furthermore, its performance can be enhanced using a technique combined with other techniques in feature generation and dimension reduction. It is hoped that, in the future, intelligent techniques can be used in the process of diagnosing and treating sleep disorders.

show abstract

“…Previous studies have also demonstrated that electroencephalograph (EEG) signals vary with sleep progresses, thus EEG has been widely used for assessing sleep stages 5,6 . Hassan et al extracted many features such as tunable-Q factor wavelet transform 7 , spectral features, empirical mode decomposition 8 , Gaussian parameters and statistical features 9 from EEG signals to classify sleep states. Liang et al employed multi-scale entropy and auto-regressive model parameters to classify sleep stages 10 , considering that the characteristics of EEG signals are somewhat chaotic, not only the traditional features, the correlation dimension (CD) derived from nonlinear dynamical analysis are also applied to investigate the dynamic characteristics of EEG.…”

Section: Introductionmentioning

confidence: 99%

Improved GP algorithm for the analysis of sleep stages based on grey model

Li¹,

Xie²,

Zhao³

et al. 2017

ScienceAsia

View full text Add to dashboard Cite

Correlation dimension analysis of EEG signals is widely used to access sleep stages. However, the standard Grassberger-Procaccia (GP) algorithm used to calculate the correlation dimension is very time consuming. To overcome this problem, an algorithm that combines the grey model and GP algorithm (GM-GP) is proposed. The results show that the correlation dimensions computed from GP and GM-GP are highly correlated, and the significance between the CDs in different stages of GM-GP is similar to GP. Furthermore, the computation time of the proposed method is at most 5% of that of the GP. The proposed algorithm is suitable for the real-time monitoring of sleep stages, which can provide a deeper understanding of brain function.

show abstract

A decision support system for automated identification of sleep stages from single-channel EEG signals

Cited by 198 publications

References 37 publications

Ensemble SVM Method for Automatic Sleep Stage Classification

Ensemble SVM Method for Automatic Sleep Stage Classification

Performance comparison of machine learning techniques in sleep scoring based on wavelet features and neighboring component analysis

Improved GP algorithm for the analysis of sleep stages based on grey model

Contact Info

Product

Resources

About