en_GB
Hold Ctrl-tasten nede. Trykk på + for å forstørre eller - for å forminske.

ELE922_1

Biomedical data analysis

This is the study programme for 2019/2020. It is subject to change.


The course starts with an introduction to biomedical signals (or images). Furthermore the following topics are covered: basic concepts from time- frequency domain representation; noise cancellation; detection of events and objects; characterisation of shape- and complexity for waveforms and objects; frequency domain characterisation; machine learning and decision support.

Learning outcome

Knowledge: The subject aims to provide insight into concepts and skills important for handling problems in biomedical data analysis. Furthermore, insight into important applications of data analysis with examples from signal processing, image processing and machine learning. The subject shall provide competencies enabling the candidate to understand and apply research methodology used by researchers with a technological background. This will enable a more efficient collaboration between clinicians and technologists and contribute to translatory research. Skills: The student will also be able to handle basic data analysis tools like MATLAB or Python to handle the type of problems described above. An introduction will give the basics in programming with use of control structures. The completion of the laboratory exercises in the course will depend on the student having acquires adequate programming skills. General competence: At the completion of the course the student will be able to recognize problems which can be handled by data analysis methods. Furthermore, the student will be able to use the subject terminology of the course to define a problem precisely. The solution to the problem implies extraction of relevant information (e.g. for diagnosis) from a biomedical signal (or image) and use this information for decision support. This can be a diagnostic or therapeutic decision.The student also has to be able to handle various techniques for noise reduction and characterization of events and/or states in the biomedical signal (or objects in images).

Contents

Theoretical: Introduction to biomedical signals (or images); basic concepts from time- frequency domain representation; noise cancellation; detection of events and objects; characterisation of shape- and complexity for waveforms and objects; fequency domain characterisation; machine learning and decision support.
Laboratory activities: Introduction to data analysis tools relevant to the theoretical part of the course.

Required prerequisite knowledge

None.

Exam

Weight Duration Marks Aid
Project and oral presentation1/1 Pass - Fail

Course teacher(s)

Course teacher
Stein Ørn, Kjersti Engan
Course coordinator
Trygve Christian Eftestøl
Head of Department
Tom Ryen

Method of work

Guided self-tuition. Lectures can in some instances be arranged.

Open to

Technology and Natural Science - PhD programme

Course assessment

form and/or discussion according to current guidelines.

Literature

R. M. Rangayyan; Biomedical Signal Analysis - A case-study approach; Wiley-Interscience 2002.
R. M. Rangayyan; Biomedical Image Analysis, CRC Press 2005.
L Sörnmo, P. Laguna; Bioelectric signal processing in cardiac and neurological applications; Elsevier Academic Press 2005.
T. Eftestøl; Lecture notes for biomedical data analysis


This is the study programme for 2019/2020. It is subject to change.

Sist oppdatert: 13.11.2019

History