Jović, Alan

Intelligent Biosignal Analysis Methods - Basel, Switzerland MDPI - Multidisciplinary Digital Publishing Institute 2021 - 1 electronic resource (256 p.)

Open Access

This book describes recent efforts in improving intelligent systems for automatic biosignal analysis. It focuses on machine learning and deep learning methods used for classification of different organism states and disorders based on biomedical signals such as EEG, ECG, HRV, and others.


Creative Commons


English

books978-3-0365-1691-2 9783036516929 9783036516912

10.3390/books978-3-0365-1691-2 doi


Information technology industries

sleep stage scoring neural network-based refinement residual attention T-end annotation signal quality index tSQI optimal shrinkage emotion EEG DEAP CNN surgery image disgust autonomic nervous system electrocardiogram galvanic skin response olfactory training psychophysics smell wearable sensors wine sensory analysis accuracy convolution neural network (CNN) classifiers electrocardiography k-fold validation myocardial infarction sensitivity sleep staging electroencephalography (EEG) brain functional connectivity frequency band fusion phase-locked value (PLV) wearable device emotional state mental workload stress heart rate eye blinks rate skin conductance level emotion recognition electroencephalogram (EEG) photoplethysmography (PPG) machine learning feature extraction feature selection deep learning non-stationarity individual differences inter-subject variability covariate shift cross-participant inter-participant drowsiness detection EEG features drowsiness classification fatigue detection residual network Mish spatial transformer networks non-local attention mechanism Alzheimer’s disease fall detection event-centered data segmentation accelerometer window duration n/a