Finding Robust Low Dimensional Features for Sleep Detection Using EEG Data

The study of sleep is crucial for understanding how our bodies function., and electroencephalogram (EEG) offers a convenient way to examine sleep. Sleep can be categorized into wakefulness., rapid eye movement (REM) sleep., and stages 1-4, with 4 being the deepest stage of sleep. We strive to study...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 IEEE 2nd International Conference on Data Science and Computer Application (ICDSCA) s. 42 - 45
Hlavní autori: Mao, Helen X., Widjaja, Joseph, Guo, Yifan, Yin, Jijun, Vinjamuri, Ramana
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 28.10.2022
Predmet:
Autoencoder
Computational efficiency
Computer applications
Data science
Electroencephalography
Feature extraction
linear discriminant analysis (LDA)
Machine learning
PCA
Rapid eye movement sleep
sleep stages classification
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The study of sleep is crucial for understanding how our bodies function., and electroencephalogram (EEG) offers a convenient way to examine sleep. Sleep can be categorized into wakefulness., rapid eye movement (REM) sleep., and stages 1-4, with 4 being the deepest stage of sleep. We strive to study how well EEG data help classify brain waves into these stages. The goal of this paper is to construct low dimensional features that are computationally efficient, robust., and effective for sleep detection and analysis. We experiment with EEG band power analysis., principal component analysis (PCA)., and autoencoder to reduce the dimensionality of the EEG data and evaluate their performances in classification. We find that, even when highly compressed., two dimensional features are still sufficient to obtain satisfactory classification accuracies: 89.3%, 88.8%, and 90% from band power analysis (using delta and alpha waves), PCA., and autoencoder, respectively.
DOI:10.1109/ICDSCA56264.2022.9988155