A hierarchical classification system for sleep stage scoring via forehead EEG signals

Huang, Chih-Fang; Lin, Chun‐Ling; Ko, Li-Wei; S, Liu; Sua, Tung-Ping; Lin, Chin-Teng

doi:10.1109/ccmb.2013.6609157

Cited by 33 publications

(20 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sleep is the primary function of the brain and plays an essential role in an individual's performance, learning ability and physical movement [1][2][3][4][5][6][7][8][9]. Sleep is a reversible state in which the eyes are closed and several nervous system centers are inactive.…”

Section: Background and Motivationmentioning

confidence: 99%

“…The purpose of this component is to reduce the number of features and to generate low-dimensional features that are derived from the input features. A wide range of machine learning-based methods such as Linear Discriminant Analysis (LDA) [50,56], Artificial Neural Networks (ANN) [57,58], Support Vector Machine (SVM) [4,34,53], K-Nearest Neighbor (KNN) [32,37] and Decision Trees (DT) [15,17,43] have been proposed for classification problems, which have also been widely used for sleep stage classification.…”

Section: Background and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Sleep Stage Classification Using EEG Signal Analysis: A Comprehensive Survey and New Investigation

Aboalayon

Faezipour

Almuhammadi

et al. 2016

Entropy

291

124

View full text Add to dashboard Cite

Sleep specialists often conduct manual sleep stage scoring by visually inspecting the patient's neurophysiological signals collected at sleep labs. This is, generally, a very difficult, tedious and time-consuming task. The limitations of manual sleep stage scoring have escalated the demand for developing Automatic Sleep Stage Classification (ASSC) systems. Sleep stage classification refers to identifying the various stages of sleep and is a critical step in an effort to assist physicians in the diagnosis and treatment of related sleep disorders. The aim of this paper is to survey the progress and challenges in various existing Electroencephalogram (EEG) signal-based methods used for sleep stage identification at each phase; including pre-processing, feature extraction and classification; in an attempt to find the research gaps and possibly introduce a reasonable solution. Many of the prior and current related studies use multiple EEG channels, and are based on 30 s or 20 s epoch lengths which affect the feasibility and speed of ASSC for real-time applications. Thus, in this paper, we also present a novel and efficient technique that can be implemented in an embedded hardware device to identify sleep stages using new statistical features applied to 10 s epochs of single-channel EEG signals. In this study, the PhysioNet Sleep European Data Format (EDF) Database was used. The proposed methodology achieves an average classification sensitivity, specificity and accuracy of 89.06%, 98.61% and 93.13%, respectively, when the decision tree classifier is applied. Finally, our new method is compared with those in recently published studies, which reiterates the high classification accuracy performance.

show abstract

Section: Background and Motivationmentioning

confidence: 99%

Section: Background and Motivationmentioning

confidence: 99%

Sleep Stage Classification Using EEG Signal Analysis: A Comprehensive Survey and New Investigation

Aboalayon

Faezipour

Almuhammadi

et al. 2016

Entropy

291

124

View full text Add to dashboard Cite

show abstract

“…However, adopting sleep questionnaire is not possible to measure the sleep quality and physiological state directly and objectively. In order to overcome the hair problems in EEG measurement, the study of automatic sleep classification was developed to classify the sleep stages by only forehead EEG channels, such as FP1 and FP2 [3]. In this study, we adopted the developed sleep classification system [3] to develop a JAVA-based sleep GUI software.…”

Section: Introductionmentioning

confidence: 99%

“…In order to overcome the hair problems in EEG measurement, the study of automatic sleep classification was developed to classify the sleep stages by only forehead EEG channels, such as FP1 and FP2 [3]. In this study, we adopted the developed sleep classification system [3] to develop a JAVA-based sleep GUI software. In addition, we use a portable EEG recording device (Mindo-4s) with foam sensors to record the FP1 and FP2 EEG signals for overcoming the conductive adhesive of EEG [4,5].…”

Section: Introductionmentioning

confidence: 99%

Automatic Sleep Stage Classification GUI with a Portable EEG Device

Huang

Lin

et al. 2013

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

Abstract. In this study, a developed automatic sleep stage classification system with a portable EEG recording device, (Mindo-4s) is implemented by JAVAbased sleep graphical user interface (GUI) in android platform. First, the parameters of the developed sleep stage classification system, including extracting effective sleep features and a hierarchical classification structure consisting of preliminary wake detection rule, adaptive adjustment scheme, and support vector machine, were trained by our existing sleep database, which collected using polysomnogram (PSG), in MATLAB program. Finally, this classification system would be reedited by JAVA language, and the corresponding JAVA-based sleep GUI software was working in android platform and Mindo-4s. The connection between JAVA-based sleep GUI software and the portable Mindo-4s was through Bluetooth communication. The performance of this JAVA-based sleep GUI can reach 72.43% average accuracy comparing to the result from manual scoring. This JAVA-based sleep GUI can on-line display, record and analyze the forehead EEG signals simultaneously. After sleep, the user can received a complete sleep report, including sleep efficiency, sleep stage distribution, from JAVA-based sleep GUI. Thus, this system can provide a preliminary result in sleep quality estimation, and help the sleep doctor to decide someone needs to have a complete PSG testing in hospital. Using this system is more convenient for long-term and home-based daily caring than traditional PSG measurement.

show abstract

“…The main scope of this step is to reduce the dimension of the estimated features. A wide range of machine learning-based classification methods such as Linear Discriminant Analysis (LDA) (Sousa et al, 2015 ;Weiss et al, 2011), Artificial Neural Networks (ANN) (Liu et al, 2010 ;Dursun et al, 2012), Support Vector Machine (SVM) (Huang et al, 2013 ;Brignol et al, 2012 ;Yu et al, 2012 ;Lainef et al, 2015), K-Nearest Neighbor (KNN) (Kuo and Liang, 2011 ;Liu et al, 2010), Decision Trees (DT) (Schaltenbrand et al, 1996 ;Pan et al, 2012) and SVMs-DT (Lan et al, 2015) have been adopted for sleep stage classification.…”

Section: Introductionmentioning

confidence: 99%

A Novel, Fast and Efficient Single-Sensor Automatic Sleep-Stage Classification Based on Complementary Cross-Frequency Coupling Estimates

Dimitriadis

Salis

Linden

2017

Preprint

View full text Add to dashboard Cite

ObjectiveLimitations of the manual scoring of polysomnograms, which include data from electroencephalogram (EEG), electrooculogram (EOG), electrocardiogram (ECG) and electromyogram (EMG) channels, have long been recognised. Manual staging is resource-intensive and time-consuming and considerable efforts have to be spent to ensure inter-rater reliability. There is thus great interest in techniques based on signal processing and machine learning for a completely Automatic Sleep Stage Classification (ASSC).MethodsIn this paper, we present a single EEG-sensor ASSC technique based on dynamic reconfiguration of different aspects of cross-frequency coupling (CFC) estimated between predefined frequency pairs over 5s epoch lengths. The proposed analytic scheme is demonstrated using the PhysioNet Sleep European Data Format (EDF) Database using 20 healthy young adults with repeat recordings.ResultsWe achieved very high classification sensitivity, specificity and accuracy of 96.2 ± 2.2%, 94.2 ± 2.3%, and 94.4 ± 2.2% across 20 folds, respectively and high mean F1-score (92%, range 90–94%) when multi-class Bayes Naive classifier was applied.ConclusionsOur method outperformed the accuracy of previous studies on different datasets but also on the same database.SignificanceSingle-sensor ASSC makes the whole methodology appropriate for longitudinal monitoring using wearable EEG in real world and lab-oriented environments.

show abstract

A hierarchical classification system for sleep stage scoring via forehead EEG signals

Cited by 33 publications

References 13 publications

Sleep Stage Classification Using EEG Signal Analysis: A Comprehensive Survey and New Investigation

Sleep Stage Classification Using EEG Signal Analysis: A Comprehensive Survey and New Investigation

Automatic Sleep Stage Classification GUI with a Portable EEG Device

A Novel, Fast and Efficient Single-Sensor Automatic Sleep-Stage Classification Based on Complementary Cross-Frequency Coupling Estimates

Contact Info

Product

Resources

About