A hybrid double-density dual-tree discrete wavelet transformation and marginal Fisher analysis for scoring sleep
Yan Liu1,2, Jie Gao3, Wei Cao4
1Department of Nuclear Medicine, The Second Affiliated Hospital of Air Force Medical University, Xi'an 710038, China.
Background:
We demonstrate an innovative approach of automated sleep recording formed on the electroencephalogram (EEG) with one channel.
Methods:
In this study, double-density dual-tree discrete wavelet transformation (DDDTDWT) was used for decomposing the image, and marginal Fisher analysis (MFA) was used for reducing the dimension. A proposed model on unprocessed EEG models was used on monitored training of 5-group sleep phase forecasting.
Results:
Our network includes a 14-row structure, and a 30-s period was extracted as input in order to be categorized which is followed by second and third period prior to the first 30-s period. Another consecutive period for temporal tissue was added which is not required to a signal preprocess and attribute data derivation phase. Our means of evaluating and improving our approach was to use input from the Sleep Heart Health Study (SHHS), which is a large study field aimed at using research from numerous centers and people and which studies the records of specialist-rated polysomnography (PSG). Performance measures could reach the desired level, which is a precision of 0.87 and a Cohen's kappa of 0.81.
Conclusions:
The use of a large, collaborative study of specialist graders can enhance the likelihood of good globalization. Overall, the novel approach learned by our network showcases the models based on each category.
