Wavelet Decomposition Based Automatic Sleep Stage Classification Using EEG

Crasto, Nieves; Upadhyay, Richa

doi:10.1007/978-3-319-56148-6_45

Cited by 5 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features capture the overall activity, power, variability, magnitude, asymmetry, and peakedness of the signals. Wavelets have also been used to extract wavelet-based features 31,33 from EEG signals. In this work, the DB4 wavelet is used for the wavelet decomposition of the EEG signals.…”

Section: Technical Validationmentioning

confidence: 99%

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

Mishra,

Kumar,

Gupta

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Noninvasive electroencephalography (EEG) is a method for measuring electrical brain activity from the surface of the scalp. Recent developments in artificial intelligence accelerate the automatic recognition of brain patterns, allowing more reliable and increasingly faster Brain-Computer interfaces, including biometric applications. Biometric research is also focusing on multimodal systems using EEG along with other modalities. This paper presents a new multimodalSignEEG v1.0dataset based on EEG and hand-drawn signatures from 70 subjects. EEG signals and hand-drawn signatures have been collected withEmotiv InsightandWacom Onesensors, respectively. The multimodal data consists of three paradigms with increasing brain functioning: (i) visualizing a signature image, (ii) doing a signature in mind, and (iii) physically drawing a signature. Extensive experiments have been done in order to provide a solid baseline with machine learning classifiers. We release the raw, pre-processed data and easy-to-follow implementation details.

show abstract

Section: Technical Validationmentioning

confidence: 99%

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

Mishra,

Kumar,

Gupta

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Automated sleep staging can be accomplished with a combination of parameters from a PSG [ 5 , 6 , 7 , 8 , 9 ] or a single-channel EEG [ 10 , 11 , 12 , 13 ]. Hong et al.…”

Section: Introductionmentioning

confidence: 99%

“…The at-home study still requires special training to interpret. Automated sleep staging can be accomplished with a combination of parameters from a PSG [5][6][7][8][9] or a single-channel EEG [10][11][12][13]. Hong et al claims support vector machines (SVMs) and artificial neural networks (ANN) are the "tool of choice" for any data that are classified a priori [14].…”

Section: Introductionmentioning

confidence: 99%

REM Sleep Stage Identification with Raw Single-Channel EEG

Toban,

Poudel,

Hong

2023

Bioengineering

View full text Add to dashboard Cite

This paper focused on creating an interpretable model for automatic rapid eye movement (REM) and non-REM sleep stage scoring for a single-channel electroencephalogram (EEG). Many methods attempt to extract meaningful information to provide to a learning algorithm. This method attempts to let the model extract the meaningful interpretable information by providing a smaller number of time-invariant signal filters for five frequency ranges using five CNN algorithms. A bi-directional GRU algorithm was applied to the output to incorporate time transition information. Training and tests were run on the well-known sleep-EDF-expanded database. The best results produced 97% accuracy, 93% precision, and 89% recall.

show abstract

“…By collecting and analyzing electroencephalogram (EEG) signals, the BCIs provide access to a wealth of real-time brain information, including mental states. Through instructional mapping, people are now able to communicate with or operate various devices without muscular movement. , Because of the benefits from their instantaneous, accurate, and movement-independent nature, BCI systems have been intensely studied for multiple purposes (Figure a), including disease diagnosis and treatment, − motion-disabled assistance, − associative learning, driving alertness, and daily health care applications. , One of the most challenging problems of BCIs is reducing the contact impedance between the electrodes and human skin. , Gel-based rigid silver/silver chloride (Ag/AgCl) electrodes are currently the most popular way to sense EEG signals due to their stable electrode potential, sufficiently low impedance (<10 kΩ), and wide availability of the required materials (Figure b,c). To establish firm and low-impedance contact, a special conductive electrode gel is applied between the electrodes and the skin .…”

mentioning

confidence: 99%

A Flexible, Robust, and Gel-Free Electroencephalogram Electrode for Noninvasive Brain-Computer Interfaces

et al. 2019

View full text Add to dashboard Cite

Brain–computer interfaces (BCIs) enable direct and near-instant communication between the brain and electronic devices. One of the biggest remaining challenges is to develop an effective noninvasive BCI that allows the recording electrodes to avoid hair on human skin without the inconveniences and complications of using a conductive gel. In this study, we developed a cost-effective, easily manufacturable, flexible, robust, and gel-free silver nanowire/polyvinyl butyral (PVB)/melamine sponge (AgPMS) electroencephalogram (EEG) electrode that circumvents problems with hair. Because of surface metallization by the silver nanowires (AgNWs), the sponge has a high conductivity of 917 S/m while its weight remains the same. The flexible sponge framework and self-locking AgNWs combine to give the new electrode remarkable mechanical stability (the conductivity remains unchanged after 10 000 cycles at 10% compression) and the ability to bypass hair. A BCI application based on steady-state visual evoked potential (SSVEP) measurements on hairless skin shows that the BCI accuracy of the new electrode (86%) is approximately the same as that of conventional electrodes supported by a conductive gel (88%). Most importantly, the performance of the AgPMS on hairy skin is not significantly reduced, which indicates that the new electrode can replace conventional electrodes for both hairless and hairy skin BCIs and other EEG applications.

show abstract

Wavelet Decomposition Based Automatic Sleep Stage Classification Using EEG

Cited by 5 publications

References 23 publications

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

SignEEG v1.0 : Multimodal Dataset with Electroencephalography and Hand-written Signature for Biometric Systems

REM Sleep Stage Identification with Raw Single-Channel EEG

A Flexible, Robust, and Gel-Free Electroencephalogram Electrode for Noninvasive Brain-Computer Interfaces

Contact Info

Product

Resources

About