Applied biomedical signal processing
Summary
This course covers state-of-the-art concepts and approaches for biomedical signal processing, applied to diverse sensing modalities, and framed in real applications within the health, wellness, and sports domains.
Content
- Introduction of the basics in anatomy and physiology of the autonomous nervous system, electrical cardiac system, vascular system, brain function and respiratory activity.
- Digital signal processing fundamentals including sampling, Fourier transform, filtering, stochastic signal correlation and power spectral density. Time-frequency analysis including short-term Fourier and wavelet transforms.
- Linear modeling and estimation techniques 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.
- Multivariate signal processing techniques such as singular value decomposition and principal component analysis, blind source separation.
- Machine learning techniques including classification and regression with approaches such as support vector machines, neural network architectures such as CNN and RNN.
- Biomedical applications and exercises related to e.g. cardiac arrythmia detection and classification, central blood pressure estimation, sleep phase classification, heart rate tracking in the presence of motion interferences, epileptic event detection, fall detection, apnoea detection, SpO2 estimation, and respiration tracking and volume estimation. These exercises will be based on biomedical signals such as electrocardiogram, electroencephalogram, movement (accelerometer, gyroscope, and barometer), photoplethysmography, bio-impedance, vocal/audio.
Keywords
biomedical engineering, signal processing, signal modeling, spectral analysis, adaptive filtering, machine learning, algorithm design, cardiovascular, respiratory, neurological
Learning Prerequisites
Recommended courses
- Signal processing COM-202
- Signal processing EE-350
Important concepts to start the course
- Fundamentals of discrete-time signal analysis
- Fundamentals of signal processing programming
Teaching methods
Ex cathedra lectures (approximately 2h per module) and practical work using Python/Matlab (approximately 2h per module). The students will work in groups to provide a report for each of the practical work sessions 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
- Interpreting methodological and physiological results
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
| Assistant.e.s | Yes |
In the programs
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional
- Semester: Fall
- Exam form: Written (winter session)
- Subject examined: Applied biomedical signal processing
- Courses: 2 Hour(s) per week x 14 weeks
- Lab: 2 Hour(s) per week x 14 weeks
- Type: optional