Complex-valued unsupervised convolutional neural networks for sleep stage classification
J Zhang, Y Wu - Computer methods and programs in biomedicine, 2018 - Elsevier
… brain rhythms, we use EEG to score sleep stage in this paper… waves from the EEG signals
of each segment. Then, the … adjacent phases are difficult to discriminate when only EEG …
of each segment. Then, the … adjacent phases are difficult to discriminate when only EEG …
[HTML][HTML] Proof of concept: Screening for REM sleep behaviour disorder with a minimal set of sensors
N Cooray, F Andreotti, C Lo, M Symmonds… - Clinical …, 2021 - Elsevier
… framework by excluding EEG sensors and exploring only non-EEG sensors to determine the
… to their correlation with REM sleep and specifically detecting rapid eye movement through …
… to their correlation with REM sleep and specifically detecting rapid eye movement through …
Automatic sleep arousals detection from polysomnography using multi-convolution neural network and random forest
Y Liu, H Liu, B Yang - IEEE Access, 2020 - ieeexplore.ieee.org
… ing and obtaining features of EEG signals [10]. They used … In this layer, neurons are only
connected to some adjacent … data point in the entire segment, and then we upsampled the …
connected to some adjacent … data point in the entire segment, and then we upsampled the …
Classification of Obstructive Sleep Apnoea from single-lead ECG signals using convolutional neural and Long Short Term Memory networks
… the human brain functions called artificial neural networks(ANN). … to detect false R peaks by
comparing the sum of adjacent RR … collected by other sensors such as EEG, EMG and SpO2. …
comparing the sum of adjacent RR … collected by other sensors such as EEG, EMG and SpO2. …
A new method for automatic sleep stage classification
J Zhang, Y Wu - IEEE transactions on biomedical circuits and …, 2017 - ieeexplore.ieee.org
… neural network (FDCCNN) is proposed to extract features from raw EEG data and classify
sleep … Discriminating the epochs that occur on adjacent phases is difficult when only EEG is …
sleep … Discriminating the epochs that occur on adjacent phases is difficult when only EEG is …
A review of Hidden Markov models and Recurrent Neural Networks for event detection and localization in biomedical signals
… Epoch extraction algorithms have been used repeatedly in segmentation of many … type of
neural networks that introduces the notion of time by using cyclic edges between adjacent steps…
neural networks that introduces the notion of time by using cyclic edges between adjacent steps…
[HTML][HTML] Multi-scale ResNet and BiGRU automatic sleep staging based on attention mechanism
C Liu, Y Yin, Y Sun, OK Ersoy - Plos one, 2022 - journals.plos.org
… cyclic neural network to learn the time information in EEG … divided into 30 s each segment.
According to R&K guidelines, … combined effects of multiple, adjacent and similar classes. By …
According to R&K guidelines, … combined effects of multiple, adjacent and similar classes. By …
[HTML][HTML] A lightweight automatic sleep staging method for children using single-channel EEG based on edge artificial intelligence
L Zhu, C Wang, Z He, Y Zhang - World Wide Web, 2022 - Springer
… manifold-deep convolutional neural network with hyperbolic … The specific division ratio is
shown in Sections 4.4 and 4.5. … The sleep stages are contiguous in the sleep cycle, therefore …
shown in Sections 4.4 and 4.5. … The sleep stages are contiguous in the sleep cycle, therefore …
[HTML][HTML] SeriesSleepNet: an EEG time series model with partial data augmentation for automatic sleep stage scoring
… neural networks (CNN) and bidirectional long short-term … sample to consider the surrounding
epochs. The reported … to decompose a 30-s EEG segment to represent each epoch as a …
epochs. The reported … to decompose a 30-s EEG segment to represent each epoch as a …
An EEG spectrogram-based automatic sleep stage scoring method via data augmentation, ensemble convolution neural network, and expert knowledge
CE Kuo, GT Chen, PY Liao - Biomedical Signal Processing and Control, 2021 - Elsevier
… each 30-s EEG segment into spectrograms which were … Subjects were recruited from the
public by online advertisements and … Mov was adjacent to the non-Wake (ie, REM or non-REM), …
public by online advertisements and … Mov was adjacent to the non-Wake (ie, REM or non-REM), …