Automatic sleep staging using state machine-controlled decision trees

Imtiaz, Syed Anas; Rodriguez‐Villegas, Esther

doi:10.1109/embc.2015.7318378

Cited by 31 publications

(33 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our recent work, however, demonstrated reliable detection of REM sleep from a single EEG channel which allows using only this channel to perform full sleep staging [11].…”

Section: Sleep Monitoring and Polysomnographymentioning

confidence: 99%

“…Since wearable systems have very limited power budget and computational resources, it is not feasible to run complex algorithms on such systems. Hence, in our previous work [11], a sleep staging algorithm was specifically developed to be used in wearable systems. This is a contextually aware algorithm that uses a set of spectral features and a combination of small decision trees to determine the next sleep stage based on the current stage.…”

Section: Automatic Sleep Staging Algorithmmentioning

confidence: 99%

“…Hence, regardless of the chosen architecture, there is a definite need for low-complexity sleep staging algorithms that can be run on a sensor node or a smartphone. It is for this reason the sleep staging algorithm in [11] was developed. The rest of this paper focuses on the implementation of this algorithm as a complete system-on-chip (SoC).…”

Section: Wearable Sleep Staging Systemmentioning

confidence: 99%

See 2 more Smart Citations

An Ultralow Power System on Chip for Automatic Sleep Staging

Imtiaz

Jiang

Rodriguez‐Villegas

2017

IEEE J. Solid-State Circuits

Self Cite

View full text Add to dashboard Cite

This paper presents an ultra-low power SoC for automatic sleep staging using a single electroencephalography (EEG) channel. The system integrates an analog front-end for EEG data acquisition and a digital processor to extract spectral features from this data and classify them into one of the sleep stages.The digital processor consists of multiple blocks implementing an automatic sleep staging algorithm that uses a set of contextual decision trees controlled by a state machine. The processor is designed to stay in idle mode at most times waking up only when computations are required. In addition, the mathematical operations are implemented in a way such that the number of datapath components needed is very small. The SoC is implemented in AMS 0.18 µm CMOS technology and is powered using a single 1.25V supply. Its power consumption is measured to be 575µW while its classification accuracy using real EEG data is 98.7%.

show abstract

“…Our recent work, however, demonstrated reliable detection of REM sleep from a single EEG channel which allows using only this channel to perform full sleep staging [11].…”

Section: Sleep Monitoring and Polysomnographymentioning

confidence: 99%

Section: Automatic Sleep Staging Algorithmmentioning

confidence: 99%

Section: Wearable Sleep Staging Systemmentioning

confidence: 99%

See 1 more Smart Citation

An Ultralow Power System on Chip for Automatic Sleep Staging

Imtiaz

Jiang

Rodriguez‐Villegas

2017

IEEE J. Solid-State Circuits

Self Cite

View full text Add to dashboard Cite

show abstract

“…This ability to perform automatic sleep staging in comfortable environments (e.g. homes) improves scoring reliability, reduces time and cost of sleep staging, subsequently making sleep disorder diagnosis accessible to a larger population [19].…”

Section: Introductionmentioning

confidence: 99%

Studying the Effects of Compression in EEG-Based Wearable Sleep Monitoring Systems

Liu

Imtiaz

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Long-term sleep monitoring through the use of wearable EEG-based systems generates large volumes of data that need to be either locally stored or wireless transmitted. Compression of data can play a vital role to reduce the power consumption of these already resource-constrained systems. While compression methods can result in significantly reduced data storage and transmission requirements, the loss in signal information can have an impact on the algorithms used to extract the key sleep parameters. This paper studies the impact of six different state-of-the-art compression methods, including wavelet, SPIHT, filter and predictor-based methods, analysing their effects on the reconstructed signal quality particularly for automatic sleep staging applications. It looks at how the overall sleep staging accuracy as well as the detection accuracy of different sleep stages is reduced as a result of different EEG compression methods. It shows that the SPIHT and predictor-based compression methods outperform wavelet and filter-based methods in preserving the relevant signal features. It also shows that compression ratios of up to 65 can be achieved using the QSPIHT method with less than 10% loss in overall sleep staging accuracy. INDEX TERMS Sleep disorders, Electroencephalogram (EEG) compression, lossy compression, wearables, brain monitoring, sleep staging.

show abstract

“…It can be used for noninvasive measurement. Therefore, EEG signals have been used to study brain activity of different sleep stages [1] . The traditional classification of sleep stages is the classification criteria developed by experts according to Rechtschaffen and Kales (R & K) [2] .…”

Section: Introductionmentioning

confidence: 99%

Anomaly detection for sleep EEG signal with Mahalanobis-Taguchi-Gram-Schmidt method

Peng¹,

Zheng²,

Liu³

et al. 2018

Proceedings of the 2018 7th International Conference on Energy, Environment and Sustainable Development (ICEESD 2018)

View full text Add to dashboard Cite

Abstract：Considering the tedious steps, the poor accuracy and over-subjectivity of human sleep quality judgment artificially, this paper presents an automatic detection algorithm of sleep quality based on Mahalanobis-Taguchi system method. Based on the modeling and analysis of the human brain dual channel EEG signals, the normalized vector of each channel is obtained under different sleep stages. At the same time, the linear independent vector group is subjected to Gram-Schmidt orthogonalization, and the mean value of the signal-to-noise ratio of each sleep stage is calculated by using the Mahalanobis-Taguchi-Gram-Schmidt method. Through analyzing the waveform of the mean signal-to-noise ratio on different sleep stages, the normal and the abnormal sleep quality can be identified.

show abstract

Automatic sleep staging using state machine-controlled decision trees

Cited by 31 publications

References 19 publications

An Ultralow Power System on Chip for Automatic Sleep Staging

An Ultralow Power System on Chip for Automatic Sleep Staging

Studying the Effects of Compression in EEG-Based Wearable Sleep Monitoring Systems

Anomaly detection for sleep EEG signal with Mahalanobis-Taguchi-Gram-Schmidt method

Contact Info

Product

Resources

About