Biological Data Processing

Lecturer:

Tutor:

Supervisor:

Department of Cybernetics

Synopsis:

The course covers advanced methods of biomedical signal and data processing. The course consists of three main topics: statistical processing of biomedical data, processing of biomedical signals and medical data mining. In the concrete, the emphasis lies in advanced statistical methods (principal component analysis, factor analysis, logistic regression), advanced methods of stochastic signal processing (wavelet theory, independent component analysis, automatic classification of ECG, advances in EEG processing) and applications of data mining in medicine (mining medical data for predictive and sequential patterns, time series data, dynamic time warping).

Requirements:

Syllabus of lectures:

1.Variable types, variable sampling and quantization.

2.Statistical hypothesis testing, overview of the tests frequently used in medicine.

3.Building of statistical models and their diagnostics.

4.Selected statistical methods (factor analysis, cluster analysis).

5.Fuzzy data in medicine.

6.Signal preprocessing (filtering, trend component, periodical component).

7.Deterministic signals, integral transformations.

8.Stochastic signal processing, time series analysis.

9.Wavelet transformation and its application in biomedical signal processing.

10.Independent component analysis (ICA) and its applications.

11.Specific issues of biomedical signal processing.

12.Predictive and descriptive data mining.

13.Machine learning and its applications in medicine.

14.Mining time and sequential data, time series and their similarity.

Syllabus of tutorials:

1.Practical measurements of physiological variables.

2.Statistical evaluation of measured data (correlation, F-test, confidence intervals).

3.Course students' project - processing of biomedical signals.

4.Signal processing tools - Signal toolbox, Wavelet toolbox, ICA toolbox.

5.Filtration of ECG signal.

6.Removal of trend component.

7.Detection of principal complexes of ECG signal (QRS, P-wave, T-wave).

8.Wavelet transformation.

9.Statistical signal analysis, PCA, F-test.

10.ICA analysis, EEG signal.

11.Segmentation, signal compression.

12.Dynamic Time Warping (DTW).

13.Cluster analysis.

14.Presentations of students' projects.

Study Objective:

Study materials:

[1] Graupe, D.: Time series analysis, identification and adaptive filtering. Krieger R., Malabar, Florida, 1989.

[2] Bronzino, J. D. (ed.): The Biomedical Engineering Handbook. IEEE Press, 1995.

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans: