Applied biomedical signal processing
Summary
The goal of this course is twofold: (1) to introduce physiological basis, signal acquisition solutions (sensors) and state-of-the-art signal processing techniques, and (2) to propose concrete examples of applications for vital sign monitoring and diagnosis purposes.
Content
- Introduction on the basics in anatomy and physiology of autonomous nervous system, electrical cardiac system, hemodynamic basis, brain and respiratory activities as well as location.
- Digital signal processing basics including sampling, Fourier transform, filtering, stochastic signal correlation and power spectral density. Time-frequency analysis including short-term Fourier and wavelet transforms. Linear modelling including autoregressive models, linear prediction, parametric spectral estimation, and criteria for model selection. Adaptive filtering including adaptive prediction and estimations of transfer functions as well as adaptive interference cancellation.
- Digital signal processing miscellaneous techniques including polynomial models, singular value decomposition and principal component analysis, phase-rectified signal averaging, source separation, support vector regression, and neural network structures such as CNN and RNN.
- Applications and exercises related to cardiac arrythmia detection and classification, central blood pressure estimation, sleep phase classification, heart rate tracking robust against motion artefacts, epilepsy event detection, fall detection, apnoea detection, SpO2 estimation, and respiration tracking and volume estimation. These exercises will be based on biomedical signals such as bio-impedance, electrocardiogram, electroencephalogram, hypnogram, movement (accelerometer, gyroscope, and barometer), photoplethysmography, vocal/audio.
Keywords
signal processing, biomedical engineering, signal modelling, spectral analysis, adaptive filtering, algorithm design
Learning Prerequisites
Recommended courses
Signal processing for telecommunications COM-303
Signal processing EE-350
Important concepts to start the course
basics of discrete-time signal analysis
basics in signal processing programming
Teaching methods
Ex cathedra lectures (approx.. 2h per module) and practical work using Matlab/Python (approx.. 2h per module). The student should provide a separate report for each of the practical work session for evaluation. Grades are based on the practicals and a final exam.
Expected student activities
- Attending lectures
- Processing and analysing human data
- Testing signal processing techniques
Assessment methods
1.75 points in total for the lab/exercise sessions reports during the semester (35% of the final total grade)
3.25 points for the final exam during the examination period (65% of the final total grade)
Supervision
| Assistants | Yes |
In the programs
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Lecture: 2 Hour(s) per week x 14 weeks
- Project: 2 Hour(s) per week x 14 weeks
- Type: optional