Optimal IMF Selection of EMD for Sleep Disorder Diagnosis using EEG Signals

Islam, Rashedul; Rahim, Abdur; Akter, Hafeza; Kabir, Raihan; Shin, Jungpil

doi:10.1145/3274856.3274876

Cited by 17 publications

(17 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our algorithm outperforms the current benchmark by Islam et al [15], who achieved a mean accuracy of 70.4 % using support vector machines. The most important contributions of this paper are: 1.…”

Section: Introductionmentioning

confidence: 60%

See 1 more Smart Citation

High-performance Diagnosis of Sleep Disorders: A Novel, Accurate and Fast Machine Learning Approach Using Electroencephalographic Data

Buettner¹,

Grimmeisen²,

Gotschlich³

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

While diagnosing sleep disorders by physicians using electroencephalographic data is protracted and inaccurate, we report promising results from a novel, fast and reliable machine learning approach. Our approach only needs an electroencephalographic recording snippet of 10 minutes instead of eight hours to correctly classify the disorder with an accuracy of over 90 percent. The Rapid Eye Movement sleep behavior disorder can lead to secondary diseases like Parkinson or Dementia. Therefore, it is important to classify the disorder fast and with a high level of accuracy -which is now possible with our approach.

show abstract

Section: Introductionmentioning

confidence: 60%

“…The analysis of overnight EEG recordings is complex and time-consuming. In addition, there is the fact that different physicians make different diagnoses using the same EEG recording [13][14][15][16].…”

Section: Introductionmentioning

confidence: 99%

High-performance Diagnosis of Sleep Disorders: A Novel, Accurate and Fast Machine Learning Approach Using Electroencephalographic Data

Buettner¹,

Grimmeisen²,

Gotschlich³

2020

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

show abstract

“…No classification performance has been reported. The third study decomposed every time source into frequency-dependent time courses using EMD, as in the first study [36]. The analysis focused on 20 healthy subjects, 20 REMs, 20 PLMs, and 20 patients with Apnea from the same dataset.…”

Section: Discussionmentioning

confidence: 99%

A Sleep Disorder Detection Model based on EEG Cross-Frequency Coupling and Random Forest

Dimitriadis

Salis

Liparas

2020

Preprint

View full text Add to dashboard Cite

Study objectives: Sleep disorders are medical disorders of the sleep architecture of a subject, and based on their severity they can interfere with mental, emotional and physical functioning. The most common ones are insomnia, narcolepsy, sleep apnea, bruxism, etc. There is an increment risk of developing sleep disorders in elderly like insomnia, periodic leg movements, rapid eye movement (REM) behaviour disorders, sleep disorder breathing, etc. Consequently, their accurate diagnosis and classification are important steps towards an early stage treatment that could save the life of a patient. The Electroencephalographic (EEG) signal is the most sensitive and important biosignal, which is able to capture the brain sleep activity that is sensitive to sleep. In this study, we attempt to analyse EEG sleep activity via complementary cross-frequency coupling (CFC) estimates that will further feed a classifier, aiming to discriminate sleep disorders. Methods: We adapted an open EEG Physionet Database with recordings that were grouped into seven sleep disorders and a healthy control. The EEG brain activity from common sensors has been analysed with two basic types of cross-frequency coupling (CFC). Finally, a Random Forest (RF) classification model was built on CFC patterns , that were extracted from non-cyclic alternating pattern (CAP) epochs. Results: Our RFCFC model succeeded a 74% multiclass accuracy (accuracy via random guessing 1/8 = 12.5%). Both types of CFC, PAC and AAC patterns contribute to the accuracy of the RF model , thus supporting their complementary information. Conclusion: CFC patterns, in conjunction with the RF classifier proved a valuable biomarker for the classification of sleep disorders.

show abstract

“…For SVM, the selection of a kernel is significant. The result of the similar training set using SVM with various kernel functions might be completely different [1,15,17]. As far as KNN is concerned, an unsuitable value of

K

can lead to poor output.…”

Section: Bci For Moocs Methodologymentioning

confidence: 99%

Brain–computer interface for assessment of mental efforts in e‐learning using the nonmarkovian queueing model

Balamurugan

Mullai

Soundararajan³

et al. 2020

Comp Applic In Engineering

View full text Add to dashboard Cite

The rapid advancement in information and communication technology has made e‐learning an alternative learning method for many learners. In the last few years, a huge number of learners around the world have registered in massive open online courses (MOOCs) provided by various online learning platforms. However, MOOC platforms have a vital task for the online course provider to provide enhanced students' learning experiences and satisfaction. In this work, we developed a brain–computer interface for gathering data and detecting a learner's mental situation by observing MOOC videos and electroencephalogram (EEG) devices based on John Sweller's Cognitive Load Theory. The acquired EEG signals are preprocessed with two different normalization methods to scale signals. To validate the introduced framework, the system adopted three machine learning algorithms (random forest using non‐Markovian model, support vector machine, and k‐nearest neighbors) to develop a model with preprocessed training data and test the classifiers to validate their ensemble classifiers' performance. Finally, experimental analysis showed that the random forest classifier with the non‐Markovian approach achieved more than the other two techniques in the form of overall accuracy (99.15%) and F‐measures (99.21%).

show abstract

Optimal IMF Selection of EMD for Sleep Disorder Diagnosis using EEG Signals

Cited by 17 publications

References 11 publications

High-performance Diagnosis of Sleep Disorders: A Novel, Accurate and Fast Machine Learning Approach Using Electroencephalographic Data

High-performance Diagnosis of Sleep Disorders: A Novel, Accurate and Fast Machine Learning Approach Using Electroencephalographic Data

A Sleep Disorder Detection Model based on EEG Cross-Frequency Coupling and Random Forest

Brain–computer interface for assessment of mental efforts in e‐learning using the nonmarkovian queueing model

Contact Info

Product

Resources

About