This diploma thesis is devoted to segmentation of ECG signal based on its quality and compression of quality segments suitable for diagnostics (in telemedicine). A completely new approach is to use accelerometer data to estimate ECG signal quality. This is possible thanks to the Bittium Faros mobile recorder. It records both the ECG signal motion – accelerometric data. A total of 34 features were extracted from accelerometric data. Using these features the predictive model was taught to classify the ECG signal into 3 quality groups according to the level of noise. Quality segments were compressed. The wavelet transform in combination with high-frequency bands zeroing and length encoding was used as a compression method.
Identifer | oai:union.ndltd.org:nusl.cz/oai:invenio.nusl.cz:400966 |
Date | January 2019 |
Creators | Opravilová, Kamila |
Contributors | Smital, Lukáš, Němcová, Andrea |
Publisher | Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií |
Source Sets | Czech ETDs |
Language | Czech |
Detected Language | English |
Type | info:eu-repo/semantics/masterThesis |
Rights | info:eu-repo/semantics/restrictedAccess |
Page generated in 0.0159 seconds