ResearchAI for biosignals & omics
Heart Sound Analysis
Phonocardiogram analysis and machine learning for the automated identification of heart valve disease.
Heart sounds carry diagnostic information about the valves: murmurs between the first and second sounds can indicate disease. We analyse phonocardiogram recordings to support the automated identification of heart valve disorders.
Signals are segmented into cardiac cycles and described by a set of features; classifiers such as support vector machines and rough-set rule generation then separate normal recordings from valve diseases. The same sound-analysis expertise has been applied to detecting sleep breathing disorders from snoring.
- Phonocardiogram feature extraction
- SVM and rough-set classification
- Biomedical sound analysis
Related publications
Selected work from the lab in this area.
Rough Set-Based Identification of Heart Valve Diseases Using Heart Sounds
In Rough Sets and Intelligent Systems – Professor Zdzisław Pawlak in Memoriam. Springer Berlin Heidelberg, pp. 475–491.
Automated sleep breath disorders detection utilizing patient sound analysis
Biomedical Signal Processing and Control, 7(3), pp. 256–264.
MORFEAS: A Non-Invasive System for automated Sleep Apnea Detection utilizing Snore Sound Analysis
In XII Mediterranean Conference on Medical and Biological Engineering and Computing 2010. Springer Berlin Heidelberg, pp. 119–123.
Support Vectors Machine-based identification of heart valve diseases using heart sounds
Computer Methods and Programs in Biomedicine, 95(1), pp. 47–61.