Recognition of sleep apnoea events out of a combined-recording (BSc, MSc)

Type: Bachelor Thesis (BSc, MSc)


Objective  / Ziel 

The overall goal of this work is to develop a software system for the recognition of apnoea events out of recording, obtained with the use of pressure sensors. Signal acquisition is not a part of the work.


Description / Beschreibung

Sleep study is nowadays an actual research topic worldwide. Although a sleep study itself is a medical matter, hardware and software components are unavoidable for its performing. Ubiquitous Computing Laboratory possesses a wide experience in this area of knowledge. 

The aim of this work is to develop a software system for extracting the breathing signal and identification of the apnoea events out of mixed-recording (see Fig. 1) containing movement (incl. caused by breathing). The visualisation of the initial and extracted signal as well as of apnoea events is also a part of a work.

Detailed work definition will be determined together with the student based on her/his background and experiences. The developed system will be used for the further research work of the laboratory. 


 Figure 1. The example of a non-processed non-filtered visualisation of the available signal.


Task / Aufgabe

  • Extract the breathing signal and Identify sleep apnoea events out of available recordings, store the results in a database

  • Visualize the breathing signal with highlighted apnoea events on a graph

  • Find start and end points of apnoea events

  • Calculate the breathing rate for every 30-seconds epoch of the recording


Requirements / Voraussetzungen:

Programming skills.



M.Sc. Maksym Gaiduk, Email: This email address is being protected from spambots. You need JavaScript enabled to view it.