Content
Pepole
CV
(Department) Biomedical Engineering (Division) Bioelectric
(Level and Major)
(Level and Major)
Course Title Blind Source Separation and Its Applications in Medicine
Number of Credits 3 Prerequisite Signals & Systems, Statistics
Course Description:
Course Topics:
- Introduction
- Random Vectors, Independence, Gradient and Optimization Methods, Estimation Theory, and Information Theory
- Principal Component Analysis and Whitening
- Independent Component Analysis Introduction
- Non-Gaussianity Maximization
- Likelihood Maximization
- Mutual Information Maximization
- Tensorial Methods
- Non-linear PCA and Non-linear Correlation
- Comparison of ICA Methods
- Non-linear ICA
- Noise Effect
- ECG Signal Separation
- Brain Mapping, EEG & MEG Signal Processing, fMRI Signal Processing
- EMG Signal Decomposition
- Noise Elimination and Interface-Effect Elimination in Multi-Sensor Bio-signals
- Speech Signal Separation (Cocktail Party Problem)
- Other Applications: Digital Communication Systems, Feature Extraction, Image Reconstruction, etc
Reading Resources:
Aapo Hyvarinen, Juha Karhunen Erkki Oja, “Independent Component Analysis”, John Wiley & Sons, 2001
Andrzej CICHOCKI & Shunichi AMARI, “Adaptive Blind Signal and Image Processing”, John Wiley & Sons, Ltd, 2003
Ganesh R. Naik .Wenwu Wang Editors, “Signals and Communication Technology”, Springer-Verlag Berlin Heidelberg, 2014
Xianchuan Yu, Dan Hu, and Jindong Xu, “Blind Source Separation Theory And Applications”, P.R. China Science Press, 2014
Scott Makeig and Julie Onton, “ERP Features and EEG Dynamics: An ICA Perspective”, S. Luck & E. Kappenman (2009). Oxford Handbook of Event-Related Potential Components. New York, Oxford University Press2009
Evaluation
Midterm and final exams.
View: 116 Time(s) |
Print: 37 Time(s) |
Email: 0 Time(s) |
0 Comment(s)