FPGA implementation of fractal patterns classifier for multiple cardiac arrhythmias detection

Chia-Hung Lin^*, Guo-Wei Lin

Department of Electrical Engineering, Kao-Yuan University, Kaohsiung City.

DOI: 10.4236/jbise.2012.53016                

Abstract

This paper proposes the fractal patterns classifier for multiple cardiac arrhythmias on field-programmable gate array (FPGA) device. Fractal dimension transformation (FDT) is employed to adjoin the fractal features of QRS-complex, including the supraventricular ectopic beat, bundle branch ectopic beat, and ventricular ectopic beat. FDT with fractal dimension (FD) is addressed for constructing various symptomatic patterns, which can produce family functions and enhance features, making clear differences between normal and unhealthy subjects. The probabilistic neural network (PNN) is proposed for recognizing multiple cardiac arrhythmias. Numerical experiments verify the efficiency and higher accuracy with the software simulation in order to formulate the mathematical model logical circuits. FDT results in data self-similarity for the same arrhythmia category, the number of dataset requirement and PNN architecture can be reduced. Its simplified model can be easily embedded in the FPGA chip. The prototype classifier is tested using the MIT-BIH arrhythmia database, and the tests reveal its practicality for monitoring ECG signals.

Keywords

Field-Programmable Gate Array (FPGA); Fractal Dimension Transformation (FDT); Fractal Dimension (FD); Probabilistic Neural Network (PNN)

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Hernandez, A.I., Mora, F., Villegas, M., Passariello, G. and Carrault, G. (2001) Real-time ECG transmission via internet for non-clinical applications. IEEE Transactions on Information Technology in Biomedicine, 5, 253-257. doi:10.1109/4233.945297
[2]	Mori, Y., Yamauchi, M. and Kaneko, K. (2000) Design and implementation of the vital sign box for home healthcare. Proceeding of IEEE EMBS International Conference on Information Technology Applications in Biomedical, 104-108.
[3]	Guillen, J.M., Millet, J. and Cebrian, A. (2001) Design of a prototype for dynamic electrocardiography monitoring using GSM technology: GSM-holter. Proceeding of 23rd Annual International Conference-IEEE/EMBS, Istanbul.
[4]	Chris, D. and Fred, H. (2000) FPGA signal processing using sigma-delta modulation-innovative combinations of techiques and hardware for system designers. IEEE Signal Processing Magazine, January, pp. 20-35.
[5]	Abbes, A. and Shrutisagar, C. (2007) Power modeling and efficient FPGA implementation of FHT for signal processing. IEEE Transactions on Very Large Scale Integration Systems, 15, 286-295. doi:10.1109/TVLSI.2007.893606
[6]	Huang, S.-J., Yang, T.-M. and Huang, J.-T. (2002) FPGA realization of wavelet transform for detection of electric power system disturbances. IEEE Transactions on Power Delivery, 17, 388-394. doi:10.1109/61.997905
[7]	Chilo, J. and Lindblad, T. (2008) Hardware implementation of ID wavelet transform on an FPGA for infrasound signal classification. IEEE Transactions on Nuclear Science, 55, 2008, pp. 9-13. doi:10.1109/TNS.2007.914322
[8]	Tiwari, A. and Tomko, K.A. (2005) Enhanced reliability of finite-state machines in FPGA through efficient fault detection and correction. IEEE Transactions on Reliability, 54, 459-467. doi:10.1109/TR.2005.853438
[9]	Kim, D. (2000) An implementation of fuzzy logic controller on the reconfigurable FPGA system. IEEE Transactions on Industrial Electronics, 47, 703-715. doi:10.1109/41.847911
[10]	Chen, D.R., Chang, R.F., Chen, C.J., Ho, M.F., Kuo, S.J., Chen, S.T., Hung, S.J. and Woo, K.M. (2005) Classification of breast ultrasound images using fractal feature. Clinical Imaging, 29, pp. 235-245. doi:10.1016/j.clinimag.2004.11.024
[11]	Katz, M. (1988) Fractals and the analysis of waveforms. Computing in Biology and Medicine, 18, 145-156. doi:10.1016/0010-4825(88)90041-8
[12]	Mazel, D.S. and Hayes, M.H. (1992) Using iterated function systems to model discrete sequences. IEEE Transaction on Signal Processing, 40, 1724-1734. doi:10.1109/78.143444
[13]	Vines, G. and Hayes, M.H. III (1993) Nonlinear address maps in a one-dimensional fractal model. IEEE Transactions on Signal Processing, 41, 1721-1724. doi:10.1109/78.212754
[14]	Barnsley, M. (1986) Fractal functions and interpolation. Constructive Approximation, 2, 303-329. doi:10.1007/BF01893434
[15]	Seng, T.L., Khalid, M. and Tusof, R. (2002) Adaptive GRNN for the modeling of dynamic plants. Proceedings of the 2002 IEEE International Symposium on Intelligent Control, Vancouver, 27-30 October 2002, 217-222.
[16]	Lin, C.-H. and Wang, C.-H. (2006) Adaptive wavelet networks for power quality detection and discrimination in a power system. IEEE Transactions on Power Delivery, 21, 1106-1113. doi:10.1109/TPWRD.2006.874105
[17]	Lin, C.-H. Du, Y.-C. and Chen, T.S. (2008) Adaptive wavelet network for multiple cardiac arrhythmias recognition. Expert Systems with Applications, 34, 2601-2611. doi:10.1016/j.eswa.2007.05.008
[18]	Fawcett, B.K. (1994) Tools to speed FPGA development. IEEE Spectrum, 31, 88-94. doi:10.1109/6.328732
[19]	Anderson, I.D.L. and Khalid, M.A.S. (2009) SC build: A computer-aided design tool for design space exploration of embedded central processing unit cores for field-programmable gate arrays. IET Computer Digital Techniques, 3, 24-32. doi:10.1049/iet-cdt:20070120
[20]	Arshak, K., Jafer, E., McDonagh, D. and Ibala, C.S. (2007) Modeling and simulation of wireless sensor system for health monitoring using HDL and simulink mixed environment. IET Computer Digital Techniques, 1, 508-518. doi:10.1049/iet-cdt:20050206
[21]	Goldberger, A.L., Amaral, L.A.N., Glass, L., Hausdorff, J.M., lvanov, P.Ch., Mark, R.G., Mietus, J.E., Moody, G.B., Peng, C.K. and Stanley, H.E. (2000) PhysioBank, physio toolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101, e215-e220.
[22]	Urrusti, J.L. and Tompkins, W.J. (1993) Performance evaluation of an ECG QRS complex detection algorithm. Proceedings Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Diego, 28-31 October 1993, 800-801.
[23]	Nambakhsh, M.S., Tavakoli, V. and Sahba, N. (2008) FPGA-core defibrillator using wavelet-fuzzy ECG arrhythmia classification. Proceeding of 30th Annual International IEEE EMBS Conference, Vancouver, 20-24 August 2008, 2673-2676.
[24]	Shukla, A. and Macchiarulo, L. (2008) A fast and accurate FPGA based QRS detection system. Proceeding of 30th Annual International IEEE EMBS Conference, Vancouver, 20-24 August 2008, 4828-4831.
[25]	Rzempoluck, E.J. (1998) Neural networks data analysis using SimulnetTM. Springer-Verlag Inc., New York. doi:10.1007/978-1-4612-1746-6