ROM-based Inference Method Built on Deep Learning for Sleep Stage Classification
Journal: TEM JOURNAL - Technology, Education, Management, Informatics (Vol.8, No. 1)Publication Date: 2019-02-28
Authors : Mohamed H. AlMeer Hanadi Hassen Naveed Nawaz;
Page : 28-40
Keywords : PSG; Sleep stages; Deep Neural Networks; DNN; FFNN;
Abstract
We used a classical deep feedforward neural network (DFFNN) for an automatic sleep stage scoring based on a single-channel EEG signal. We used an open-available dataset, randomly selecting one healthy young adult for both training (β5%) and evaluation (β95%). We also augmented the validation by using 5-fold cross validations for the result comparisons. We introduced a new method for inferring the trained network based on a ROM module (memory concept), so it would be faster than directly inferring the trained Deep Neural Network (DNN). The ROM content is filled after the DNN network is trained by the training set and inferred using the testing set. An accuracy of 97% was achieved in inferring the test datasets using ROM when compared to the classic trained DNN inference process.
Other Latest Articles
- Computer Supported Design of Logistic Production Technology
- Feature Extraction of Low Frequency Oscillation in Power System Using Hilbert-Huang Transform
- Assessment of the Quota of Recuperative Cooling of the Compressed Gas at Turbocharged Reciprocating Internal Combustion Engines
- Maturity Onset Diabetes of the Young: A Rare Monogenic Form of Diabetes
- Assessment of socio-economic factors affecting the utilization of manual screw press for gari production in Kwara state, Nigeria
Last modified: 2019-03-03 01:14:32