An automated method for sleep staging from EEG signals using normal inverse Gaussian parameters and adaptive boosting

Hassan, Ahnaf Rashik; Bhuiyan, Mohammed Imamul Hassan

doi:10.1016/j.neucom.2016.09.011

Cited by 126 publications

(51 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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%

“…Moreover, features from dual tree complex wavelet transform, tunable Q-factor wavelet transform (Hassan & Bhuiyan, 2016a), normal inverse Gaussian pdf modeling (Hassan & Bhuiyan, 2017), and statistical moments (Hassan & Subasi, 2017) were used in the feature extraction phase.…”

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%

“…In 2016 (Hassan & Haque, 2016c), a combination of methods, based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and bootstrap aggregating (bagging), was applied on PhysioNet data, which achieved 90.69% accuracy. In 2016, Hassan et al worked on a single EEG for sleep scoring using normal inverse Gaussian parameters and achieved 90.01% accuracy (Hassan & Bhuiyan, 2017). Their other remarkable accomplishment was the achievement of 93.69% accuracy, which was obtained by using a tunable Q-wavelet transform (Hassan & Bhuiyan, 2016a).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

show abstract

“…Wavelet transform (WT) [1][2] [3] is preferred and used to classify motor imagery on the left or right side by incorporating fuzzy neural networks. Fast Fourier transform (FFT) [4], Gaussian filtering [5], Laplacian filtering [6], and time-frequency based wavelet transform are used to extract the features from EEG signals.…”

Section: Introductionmentioning

confidence: 99%

Motor Imagery Classification using Wavelet-Based Features and Tensorflow

Lee,

Jang*

2019

IJITEE

View full text Add to dashboard Cite

Abstract: This paper proposes a methodology for making a decision on left and right motor imagery using Tensorflow and wavelet-based feature extraction. Wavelet coefficients are extracted by the Haar wavelet transforms from electroencephalogram (EEG) signals in the first step. In the second step, 60 wavelet-based features are extracted by the frequency distribution and the amount of variability in frequency distribution. In the final step, this paper classified left or right motion imagery using these 60 features as inputs to the Tensorflow.The proposed methodology shows that the performance result is 82.14% with 60 features in accuracy rate. His primary research interests include robot vision, augmented reality, video indexing and retrieval, cluster computing, biometrics and pattern recognition.

show abstract