Applied biomedical signal processing

EE-512

This file is part of the content downloaded from Applied biomedical signal processing.
Course summary



Course : Applied Biomedical Signal Processing

Teachers: Dr. Mathieu Lemay (responsible), Dr. Philippe Renevey, Dr. João Jorge, Dr. Martin Proença, Dr. Adrian Luca, Dr. Guillaume Bonnier, Dr. Karen Adam, Dr. Ramin Soltani, Dr. Clémentine Aguet

Assistants: Cristina Sainz Martínez, Loïc Jeanningros, Yamane El-Zein

Course description
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.

The main signal processing topics presented will be:

  • Basics on continuous and discrete time Fourier transform
  • Linear filter deisgn
  • Stochastic signals and filtering
  • Power spectral density
  • Autoregressive, Moving average and ARMA signal modeling
  • Basic concpets of time frequency analysis
  • Time frequency distributions
  • Instantaneous frequency
  • Adaptive filter frequency tracking
  • Singular value decomposition
  • Principal component analysis
  • Linear/non-linear regression
  • Classification and feature selection
  • Perceptron, MLP & activation function
  • Gradient descent and backpropagation
  • CNN & RNN

As the course content may evolve over time, the agenda is on a short-term basis.

This course comprises weekly exercise or computer lab sessions. All courses and exercise sessions take place in room INF213, including lab sessions from 17h to 19h. The lab sessions will be computer lab ones, during which experimental biomedical signals will be investigated, with groups of two-to-three students allowed. Students should handle them 7 days after the session at the latest. The corrections will be handled back one week later.

N.B. The date, time and location of the final exam need to be confirmed. All printed/written documents will be allowed, laptops and phones prohibited.

Thursday (15h15-19h)

15h-19h: Lecture on Module 01 - Introduction. ROOM AAC137
Presentation of the course, general context and module structure. Presentation of biomedical signal processing examples and real data (short laboratory exercises on Python).

The course will not be recorded.

Thursday

15h15-17h: Lecture on Module 02 - Basics. ROOM AAC137
17h15-19h: Lab session (Module 02). ROOM AAC137

The course will not be recorded.

Thursday

15h15-17h: Lecture on Module 03 - Basics II. ROOM AAC137
17h15-19h: Lab session (Module 03). ROOM AAC137



Thursday

15h-17h: Lecture on Time-Frequency Analysis (Module 04). ROOM AAC137
17h-19h: Lab session (Module 04). ROOM AAC137

Thursday

15h15-17h: Lecture on Linear Models I (Module 05). ROOM AAC137
17h15-19h: Lab session (Module 05). ROOM AAC137

Thursday

15h15-17h: Lecture on Linear Models II (Module 06). ROOM AAC137
17h15-19h: Lab session (Module 06). ROOM AAC137

Holidays

Thursday

15h-17h: Lecture on Instantaneous Frequency Estimation  (Module 07). ROOM AAC137

17h-19h: Lab session (Module 07). ROOM AAC137

Thursday

15h-19h: Mock Exam - Optional (Module 08). ROOM AAC137



Thursday

15h-17h: Lecture on Singular Value Decomposition (Module 09) -

ROOM AAC137

Thursday

15h-17h: Lecture on Principal Component Analysis  (Module 10) - ROOM AAC137
17h-19h: Lab session (Module 10) - ROOM AAC137


Thursday

15h-17h: Lecture on Regression and Classification (Module 11) - ROOM AAC137
17h-19h: Lab session (Module 11) - ROOM AAC137


Thursday

15h-17h: Introduction to neural networks (Module 12) - ROOM AAC137

17h-19h: Lab session (Module 12) - ROOM AAC137



Thursday

15h-17h: Neural network architectures (Module 13) - ROOM AAC137

17h-19h: Lab session (Module 13) - ROOM AAC137