DocumentCode :
3072406
Title :
FPGA-core defibrillator using wavelet-fuzzy ECG arrhythmia classification
Author :
Nambakhsh, Mohammad.Saleh ; Tavakoli, Vahid ; Sahba, Nima
Author_Institution :
Div. of Physics and Engineering, King´´s College London, Strand, WC2R2LS, UK
fYear :
2008
fDate :
20-25 Aug. 2008
Firstpage :
2673
Lastpage :
2676
Abstract :
An electrocardiogram (ECG) feature extraction and classification system has been developed and evaluated using Quartus II 7.1 belong to Altera Ltd. In wavelet domain QRS complexes were detected and each complex was used to locate the peaks of the individual waves. Then, fuzzy classifier block used these features to classify ECG beats. Three types of arrhythmias and abnormalities were detected using the procedure. The completed algorithm was embedded into Field Programmable Gate Array (FPGA). The completed prototype was tested through software-generated signals, in which test scenarios covering several kinds of ECG signals on MIT-BIH Database. For the purpose of feeding signals into the FPGA, a software was designed to read signal files and import them to the LPT port of computer that was connected to FPGA. From the results, it was achieved that the proposed prototype could do real time monitoring of ECG signal for arrhythmia detection. We also implemented algorithm in a sequential structure device like AVR microcontroller with 16 MHZ clock for the same purpose. External clock of FPGA is 50 MHZ and by utilizing of Phase Lock Loop (PLL) component inside device, it was possible to increase the clock up to 1.2 GHZ in internal blocks. Final results compare speed and cost of resource usage in both devices. It shows that in cost of more resource usage, FPGA provides higher speed of computation; because FPGA makes the algorithm able to compute most parts in parallel manner.
Keywords :
Clocks; Concurrent computing; Costs; Electrocardiography; Feature extraction; Field programmable gate arrays; Software prototyping; Software testing; Spatial databases; Wavelet domain; Algorithms; Arrhythmias, Cardiac; Computers; Defibrillators; Electrocardiography; Equipment Design; Fourier Analysis; Fuzzy Logic; Heart Rate; Humans; Models, Theoretical; Reproducibility of Results; Signal Processing, Computer-Assisted;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE
Conference_Location :
Vancouver, BC
ISSN :
1557-170X
Print_ISBN :
978-1-4244-1814-5
Electronic_ISBN :
1557-170X
Type :
conf
DOI :
10.1109/IEMBS.2008.4649752
Filename :
4649752
Link To Document :
بازگشت