Title :
Parameter tuning associated with nonlinear dynamics techniques for the detection of cardiac murmurs by using genetic algorithms
Author :
Delgado, E. ; Jaramillo, J. ; Quiceno, A.F. ; Castellanos, G.
Author_Institution :
Control & Digital Signal Process. Group, Nat. Univ. of Colombia, Bogota
fDate :
Sept. 30 2007-Oct. 3 2007
Abstract :
In this study, nonlinear dynamics techniques toward detecting cardiac murmurs from phonocardiograms (PCG) are used. With this purpose, a methodology for tuning parameters (reconstruction delay -tau and embedding dimension -m) involved in the reconstruction of a meaningful state space from scalar time series is presented, using genetic algorithms (GA), as well as constructing a meta-algorithm combined with support vector regression to adjust the GA parameters in order to decrease the computational cost. The forecasting capacity is used as cost function of the GA. The PCG records belong to the National University of Colombia, 360 beats were chosen by specialist, 180 normal and 180 with cardiac murmur evidence. The obtained results show that by using the tuned GA an efficient procedure for the consistent determination of tau and m is achieved. Murmur detection by using nonlinear features was obtained with classification accuracy of 96% using a k nearest neighbor classifier in cross-validation with 10 folds.
Keywords :
acoustic signal detection; bioacoustics; biomedical measurement; cardiology; feature extraction; genetic algorithms; medical signal detection; medical signal processing; signal classification; signal reconstruction; support vector machines; time series; National University of Colombia; PCG; cardiac murmur detection; cost function; forecasting capacity; genetic algorithms; k nearest neighbor classifier; meta algorithm; nonlinear dynamics techniques; nonlinear feature detection; parameter tuning; phonocardiograms; reconstruction delay; scalar time series; support vector regression; Cardiology; Computational efficiency; Cost function; Databases; Delay effects; Digital control; Genetic algorithms; Nonlinear dynamical systems; State-space methods; Valves;
Conference_Titel :
Computers in Cardiology, 2007
Conference_Location :
Durham, NC
Print_ISBN :
978-1-4244-2533-4
Electronic_ISBN :
0276-6547
DOI :
10.1109/CIC.2007.4745507