Sleep EEG signal analysis based on correlation graph similarity coupled with an ensemble extreme machine learning algorithm

Abdulla, Shahab; Diykh, Mohammed; Laft, Raid Luaibi; Saleh, Khalid; Deo, Ravinesh C.

doi:10.1016/j.eswa.2019.07.007

Cited by 51 publications

(26 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The best performance for the proposed method for identifying the awake and sleep (AWA-Sleep) pair was obtained when . For the other pairs of (S3, S4), ((S1, S2), SWS), (S1, S2), (S1, REM), (AWA-REM), the best recorded results were achieved when the values of were set as (10, 1), (2, 1), (10, 10) (10, 10), (1,1) respectively.…”

Section: Least Square Support Vector Machine (Ls-svm)mentioning

confidence: 99%

“…From the literature, the automatic sleep stages classification methods were mainly developed depending on analysing EEG signals recorded from a single EEG channel [15,16,17,24,49] instead of multiple-channels [42]. Various types of approaches from time domain [44], frequency domain [59,9], time-frequency domain [16], and graphs domain [1,14,15,16,72] were utilized for extracting the key features from EEG signals.…”

Section: Introductionmentioning

confidence: 99%

“…Then the LSTAR with a tensor locality preserving projection was utilised to pull out and select a set of EEG features. Abdulla et al [1] applied a correlation graphs similarity concept to analyse EEG sleep signals. in that study, an ensemble machine learning algorithm was developed to classify graph features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

EEG sleep stages identification based on weighted undirected complex networks

Diykh

Abdulla

2020

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

Section: Least Square Support Vector Machine (Ls-svm)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

EEG sleep stages identification based on weighted undirected complex networks

Diykh

Abdulla

2020

Computer Methods and Programs in Biomedicine

Self Cite

View full text Add to dashboard Cite

“…Recently, transforming physiological signals into graphs such as correlation graphs and visibility graphs has been considered for machine learning applications [46], [47]. Visibility algorithms are usually used to transform a time series or a set of data points to a graph [48].…”

Section: ) Horizontal Visibility Graph (Hvg)mentioning

confidence: 99%

Transfer Learning Convolutional Neural Network for Sleep Stage Classification Using Two-Stage Data Fusion Framework

et al. 2020

View full text Add to dashboard Cite

The most important part of sleep quality assessment is the classification of sleep stages, which helps to diagnose sleep-related disease. In the traditional sleep staging method, subjects have to spend a night in the sleep clinic for recording polysomnogram. Sleep expert classifies the sleep stages by monitoring the signals, which is time consuming and frustrating task and can be affected by human error. New studies propose fully automated techniques for classifying sleep stages that makes sleep scoring possible at home. Despite comprehensive studies have been presented in this field the classification results have not yet reached the gold standard due to the concentration on the use of a limited source of information such as single channel EEG. Therefore, this article introduces a new method for fusing two sources of information, including electroencephalogram (EEG) and electrooculogram (EOG), to achieve promising results in the classification of sleep stages. In the proposed method, extracted features from the EEG and EOG signals, are divided into two feature sets consisting of the EEG features and fused features of EEG and EOG. Then, each feature set transformed into a horizontal visibility graph (HVG). The images of the HVG are produced in a novel framework and classified by proposed transfer learning convolutional neural network for data fusion (TLCNN-DF). Employing transfer learning at the training stage of the model has accelerated the training process of the CNN and improved the performance of the model. The proposed algorithm is used to classify the Sleep-EDF and Sleep-EDFx benchmark datasets. The algorithm can classify the Sleep-EDF dataset with an accuracy of 93.58% and Cohen's kappa coefficient of 0.899. The results show proposed method can achieve superior performance compared to state-of-the-art studies on classification of sleep stages. Furthermore, it can attain reliable results as an alternative to conventional sleep staging. INDEX TERMS Convolutional neural network, data fusion, horizontal visibility graph, Sleep stage classification, transfer learning.

show abstract

“…Petrosian et al showed that using long-term EEG signals recurrent neural networks can recognize Alzheimer disease symptoms [17]. Abdulla et al performed EEG signal analysis with extreme machine learning algorithm to develop a technique to detect the sleep stages based on EEG signals [18]. Hussain et al used five different supervised learning algorithms and performed k-fold cross-validation to detect the student difficulties using session data [19].…”

Section: Related Workmentioning

confidence: 99%

Classification of Student's Confusion Level in E-Learning using Machine Learning

2019

IJITEE

View full text Add to dashboard Cite

With the advancement of technology, the traditional mode of teaching-learning pedagogy has evolved into online education system as it is easily accessible. But, it is very difficult to detect whether the students are ‘confused’ or ‘not confused’ while watching online videos. Getting confused while watching online videos is one of the root causes of less performance of the students. Keeping in mind the above statements, we would like to investigate whether the students are ‘confused’ or ‘not confused’ while watching Massive Open Online Course (MOOC) videos. There are a lot of studies that prove electroencephalogram (EEG) signals behave differently as we are in different conditions such as happy, sad, angry, etc. So, in this paper, we have applied several supervised learning algorithms to detect if the students are ‘confused’ or ‘not confused’ while watching MOOC videos using EEG data. The results of this paper show that machine learning is a potential technique, for the analysis of EEG data that can detect the confusion level of the students which is comparable to human observation for predicting the confusion level of the students that can improve the quality of online education system.

show abstract

Sleep EEG signal analysis based on correlation graph similarity coupled with an ensemble extreme machine learning algorithm

Cited by 51 publications

References 44 publications

EEG sleep stages identification based on weighted undirected complex networks

EEG sleep stages identification based on weighted undirected complex networks

Transfer Learning Convolutional Neural Network for Sleep Stage Classification Using Two-Stage Data Fusion Framework

Classification of Student's Confusion Level in E-Learning using Machine Learning

Contact Info

Product

Resources

About