Automated feature learning using deep convolutional auto-encoder neural network for clustering electroencephalograms into sleep stages

Prabhudesai, Kedar S.; Collins, Leslie M.; Mainsah, Boyla O.

doi:10.1109/ner.2019.8716996

Cited by 8 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, an alternative to performing feature extraction by hand is to have the model extract salient features itself. Recently, autoencoders (AEs) have been shown to be more effective than handcrafted features in their ability to compose meaningful latent features from EEG across various classification tasks [ 57 , 58 , 59 ]. Another recent deep learning innovation is Temporal Convolutional Networks (TCNs), which are a new type of architecture for time-series data.…”

Section: Methodsmentioning

confidence: 99%

Generalized Deep Learning EEG Models for Cross-Participant and Cross-Task Detection of the Vigilance Decrement in Sustained Attention Tasks

Kamrud

Borghetti

Kabban

et al. 2021

Sensors

View full text Add to dashboard Cite

Tasks which require sustained attention over a lengthy period of time have been a focal point of cognitive fatigue research for decades, with these tasks including air traffic control, watchkeeping, baggage inspection, and many others. Recent research into physiological markers of mental fatigue indicate that markers exist which extend across all individuals and all types of vigilance tasks. This suggests that it would be possible to build an EEG model which detects these markers and the subsequent vigilance decrement in any task (i.e., a task-generic model) and in any person (i.e., a cross-participant model). However, thus far, no task-generic EEG cross-participant model has been built or tested. In this research, we explored creation and application of a task-generic EEG cross-participant model for detection of the vigilance decrement in an unseen task and unseen individuals. We utilized three different models to investigate this capability: a multi-layer perceptron neural network (MLPNN) which employed spectral features extracted from the five traditional EEG frequency bands, a temporal convolutional network (TCN), and a TCN autoencoder (TCN-AE), with these two TCN models being time-domain based, i.e., using raw EEG time-series voltage values. The MLPNN and TCN models both achieved accuracy greater than random chance (50%), with the MLPNN performing best with a 7-fold CV balanced accuracy of 64% (95% CI: 0.59, 0.69) and validation accuracies greater than random chance for 9 of the 14 participants. This finding demonstrates that it is possible to classify a vigilance decrement using EEG, even with EEG from an unseen individual and unseen task.

show abstract

Section: Methodsmentioning

confidence: 99%

Generalized Deep Learning EEG Models for Cross-Participant and Cross-Task Detection of the Vigilance Decrement in Sustained Attention Tasks

Kamrud

Borghetti

Kabban

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Moreover, Perslev et al utilized a typical architecture of convolutional autoencoders in another supervised sleep stage classification model (Perslev et al, 2021). Similarly, Prabhudesai et al developed a method to automatically learn features from the raw EEG data with an autoencoder, which were then used to cluster the data to different sleep stages (Prabhudesai, Collins, & Mainsah, 2019). Autoencoders can also be used for unsupervised pre-training before supervised classification as shown by Wei et al (Wei, Zhang, Wang, & Dang, 2018).…”

Section: Related Workmentioning

confidence: 99%

Towards a Deeper Understanding of Sleep Stages through their Representation in the Latent Space of Variational Autoencoders

Biedebach,

Rusanen,

Leppänen

et al. 2023

Proceedings of the Annual Hawaii International Conference on System Sciences

View full text Add to dashboard Cite

Artificial neural networks show great success in sleep stage classification, with an accuracy comparable to human scoring.While their ability to learn from labelled electroencephalography (EEG) signals is widely researched, the underlying learning processes remain unexplored.Variational autoencoders can capture the underlying meaning of data by encoding it into a low-dimensional space. Regularizing this space furthermore enables the generation of realistic representations of data from latent space samples. We aimed to show that this model is able to generate realistic sleep EEG. In addition, the generated sequences from different areas of the latent space are shown to have inherent meaning. The current results show the potential of variational autoencoders in understanding sleep EEG data from the perspective of unsupervised machine learning.

show abstract

“…This is particularly important when trying to uncover novel aspects of neurological and neuropsychiatric disorders. EEG deep learning-based clustering mainly uses autoencoders [7] [8]. Autoencoders can perform automated feature extraction and have been used in EEG classification [9] [10].…”

Section: Introductionmentioning

confidence: 99%

“…Autoencoders can perform automated feature extraction and have been used in EEG classification [9][10]. When used for clustering, autoencoders extract a condensed representation of the original data that is then clustered via traditional algorithms [7][8]. This approach has an important shortcoming.…”

Section: Introductionmentioning

confidence: 99%

A Convolutional Autoencoder-based Explainable Clustering Approach for Resting-State EEG Analysis

Ellis

Miller

Calhoun

2023

Preprint

View full text Add to dashboard Cite

Machine learning methods have frequently been applied to electroencephalography (EEG) data. However, while supervised EEG classification is well-developed, relatively few studies have clustered EEG, which is problematic given the potential for clustering EEG to identify novel subtypes or patterns of dynamics that could improve our understanding of neuropsychiatric disorders. There are established methods for clustering EEG using manually extracted features that reduce the richness of the feature space for clustering, but only a couple studies have sought to use deep learning-based approaches with automated feature learning to cluster EEG. Those studies involve separately training an autoencoder and then performing clustering on the extracted features, and the separation of those steps can lead to poor quality clustering. In this study, we propose an explainable convolutional autoencoder-based approach that combines model training with clustering to yield high quality clusters. We apply the approach within the context of schizophrenia (SZ), identifying 8 EEG states characterized by varying levels of δ activity. We also find that individuals who spend more time outside of the dominant state tend to have increased negative symptom severity. Our approach represents a significant step forward for clustering resting-state EEG data and has the potential to lead to novel findings across a variety of neurological and neuropsychological disorders in future years.

show abstract

Automated feature learning using deep convolutional auto-encoder neural network for clustering electroencephalograms into sleep stages

Cited by 8 publications

References 15 publications

Generalized Deep Learning EEG Models for Cross-Participant and Cross-Task Detection of the Vigilance Decrement in Sustained Attention Tasks

Generalized Deep Learning EEG Models for Cross-Participant and Cross-Task Detection of the Vigilance Decrement in Sustained Attention Tasks

Towards a Deeper Understanding of Sleep Stages through their Representation in the Latent Space of Variational Autoencoders

A Convolutional Autoencoder-based Explainable Clustering Approach for Resting-State EEG Analysis

Contact Info

Product

Resources

About