Computing in cardiology · 2018 · 14 citations · 10 references
ComputingData ScienceFeature EngineeringMachine LearningTime Series AnalysisDeep LearningElectroencephalogram AnalysisElectroencephalographyNeural NetworksSleep PhysiologySleep Signal AnalysisArousal DetectionEeg Signal ProcessingElectroencephalography-based Sleep AnalysisFeature Extraction From Sleep SignalsNeural Network ClassificationPower Spectral DensitySleep ArousalsSleep Stages
Our pipeline consists of a hand-crafted preprocessor and a neural network classifier. We applied transformations on the physiologic signals to gain features in both time-and frequency domains. The proposed algorithm was trained on 994 annotated records of polysomnographic signals. Most of the features were generated from the EEG signal such as power spectral density, and entropy. We extracted features from the EOG, EMG, airflow, and ECG signals too. All the features were normalized.
10