KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Real-Time Automated Cardiac Health Monitoring by Combination of Active Learning and Adaptive Feature Selection

  • Bashir, Mohamed Ezzeldin A. (Faculty of Computer Science & Information Technology, University of Medical Sciences & Technology) ;
  • Shon, Ho Sun (School of Electrical & Computer Engineering, Chungbuk National University) ;
  • Lee, Dong Gyu (School of Electrical & Computer Engineering, Chungbuk National University) ;
  • Kim, Hyeongsoo (School of Electrical & Computer Engineering, Chungbuk National University) ;
  • Ryu, Keun Ho (School of Electrical & Computer Engineering, Chungbuk National University)
  • Received : 2012.05.13
  • Accepted : 2012.11.19
  • Published : 2013.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Electrocardiograms (ECGs) are widely used by clinicians to identify the functional status of the heart. Thus, there is considerable interest in automated systems for real-time monitoring of arrhythmia. However, intra- and inter-patient variability as well as the computational limits of real-time monitoring poses significant challenges for practical implementations. The former requires that the classification model be adjusted continuously, and the latter requires a reduction in the number and types of ECG features, and thus, the computational burden, necessary to classify different arrhythmias. We propose the use of adaptive learning to automatically train the classifier on up-to-date ECG data, and employ adaptive feature selection to define unique feature subsets pertinent to different types of arrhythmia. Experimental results show that this hybrid technique outperforms conventional approaches and is therefore a promising new intelligent diagnostic tool.

Keywords

References

  1. M. D. Dale Dubin, rapid interpretation of EKG's, 6th Edition, Cover Inc, USA, 2000.
  2. M. E. A. Bashir, M. Akasha, D. G. Lee, Min Yi, K. H. Ryu, E. J. Bae, M. Cho, and C. Yoo, " Highlighting the Current Issues with Pride Suggestions for Improving the Performance of Real Time Cardiac Health Monitoring," in Proc. of 1st int. conf. on Inf. Technology. In Bio and Medical Informatics, pp. 226-233, 30 August - 3 September, 2010.
  3. M. E. A. Bashir, K. S. Ryu, S. H. Park, D. G. Lee, J-W. Bae, H. S. Shon, and K. Ho Ryu, "Superiority Real-Time Cardiac Arrhythmias Detection using Trigger Learning Method," in Proc. of 2nd Int. conf. on Inf. Technology. In Bio and Medical Informatics, pp. 53-65, August 29 - September 2, 2011.
  4. M. E. A. Bashir, G. Min Yi, P. Minghao, H. S. Shon, and K. Ho Ryu, "Fine-tuning ECG Parameters Technique for Precise A bnormalities Detection," in Proc. of Int. Conf. on Bioscience, Biochemistry and Bioinformatics, pp.305-309, February 26-28, 2011.
  5. M. E. A. Bashir, K. S. Ryu, S. H. Park, D. G. Lee, J-W. Bae, H. Sun Shon, and K. Ho Ryu, "Pro-Detection of Atrial Fibrillation with ECG Parameters Mining Technique," in Proc. of Int. Conf. on Electrical and Electronics Eng., December 22-23, 2011.
  6. G. Bortolan, I. Jekova and I. Christov, " Comparison of four methods for premature ventricular contractions and normal beats clustering," IEEE Comp. in Card., vol. 32, , pp.921-924, 2005.
  7. U. Rajendra, P. Subbann, S. Iyengar, A. Raod, and S. Dua, "Classification of heart rate data using artificial neural network and fuzzy equivalence relation," Patt. Recog., vol. 61 pp.61-68, 2003.
  8. M. E. A. Bashir, M. Akasha, D. G. Lee, Min Yi, K. H. Ryu, E. J. Bae, M. Cho, and C. Yoo, "Nested Ensemble Technique for Excellence Real Time Cardiac Health Monitoring," in Proc. of 1. World Cong. in Comp. Sci. Comp. Eng. and Appl. Comput., pp.519-5225, July 12-15, 2010.
  9. G. Clifford, F. Azuaje, P. McSharrg, advanced methods and tools for ECG data analysis, Artech house, 2006.
  10. Y. H. Hu, S. Palreddy, and W. J. Tompkins, Eds., "Patient adaptable ECG beat classification using mixture of experts," in Neural Network for Signal Processing V. Piscataway, NJ: IEEE Press, vol. 44, no. 9, pp.495-463, 1995.
  11. O. Pichler, A. Teuner and B.J. Hosticka, "A comparison of texture feature extraction using adaptive Gabor filtering, pyramidal and tree structured wavelet transforms," Pattern Recognition, vol. 29, no. 5, pp.733-742,1996. https://doi.org/10.1016/0031-3203(95)00127-1
  12. K. Minami, H. Nakajima, and T. Toyoshima, "Real-time discrimination of ventricular tachyarrhythmia with Fourier-transform neural network," IEEE Transactions on Biomedical Engineering, vol. 46, no. 2, pp. 179-185, 1999. https://doi.org/10.1109/10.740880
  13. Z. Dokur, T. Ölmez and E. Yazgan, "Comparison of discrete wavelet and Fourier transforms for ECG beat classification," Elect. Lett., vol. 35, no. 18, pp.1502-1504, 1999. https://doi.org/10.1049/el:19991095
  14. G. K.Prasad, and J. S Sahambi, "Classification of ECG arrhythmias using multi-resolution analysis and neural networks," in Proc. of IEEE Conference on Convergent Technologies, pp.227-231, October 15-17, 2003.
  15. K. Sternickel, "Automatic pattern recognition in ECG timeseries," Comput. Meth. and Prog. in Biomed., vol. 68, pp.109-115, 2002. https://doi.org/10.1016/S0169-2607(01)00168-7
  16. Z. Dokur and T. Olmez, "ECG beat classification by a novel hybrid neural network," Comput. Meth. And Prog. In Biomed., vol. 66, , pp. 167-181, 2002.
  17. X. Wang and K. Paliwal, "Feature extraction and dimensionality reduction algorithms and their applications in vowel recognition," Pattern Recognition, vol. 36, pp.2429-2439, 2003. https://doi.org/10.1016/S0031-3203(03)00044-X
  18. Y. Ozbay, R. Ceylan and B. Karlik, "A fuzzy clustering neural network architecture for classification of ECG arrhythmias," Comp. in Biology and Medicine, vol. 36, pp. 376-388, 2006. https://doi.org/10.1016/j.compbiomed.2005.01.006
  19. A. Hyvarinen, "Fast and robust fixed-point algorithms for independent component analysis," IEEE Tran. on Neural Networks, vol. 10, no. 3, pp. 626-634, 1999. https://doi.org/10.1109/72.761722
  20. Z. Wang, Z. He and J. Z. Chen, "Blind EGG separation using ICA neural networks," in Proc. of 19th int. conf. of the IEEE-EMBS, pp.1351-1354, October 30 - November 2, 1997.
  21. C. Thomas, R. Harshman, and R. Menon, "Noise reduction in BOLDbased fMRI using component analysis," Neuroimage, vol. 17, pp.1521-1537, 2002. https://doi.org/10.1006/nimg.2002.1200
  22. M. I. Owis, AB. Youssef, and Y M. Kadah, "Characterization of ECG signals based on blind source separation," Medical and Biological Eng. and Computing, vol. 40, pp.557-564, 2002. https://doi.org/10.1007/BF02345455
  23. Y. Sung-Nien, C. Kuan-To, "Integration of independent component analysis and neural networks for ECG beat classification," Expert Systems with Applications, vol. 34, pp.2841-2846, 2008. https://doi.org/10.1016/j.eswa.2007.05.006
  24. L. Sornmo and P. Laguna, "Bioelectrical Signal Processing in Cardiac and Neurological Applications", Inc. Hoboken, New Jersey, 2005.
  25. J. de Bie, "P-wave trending: A valuable tool for documenting supraventricular arrhythmias and AV conduction disturbances," in Proc. of IEEE Conf. on Comp. in Card., pp.511-514, September 23-26, 1990.
  26. J. Millet, M. Pkrez, G. Joseph, A. Mocholi, and J. Chorro, "Previous identification of QRS Onset and Offset is not essential for classifying QRS complex in a single lead," Com. In card., vol. 24, , pp.299-302, 1997.
  27. G. Moody and R. Mark, "QRS Morphology Representation and Noise Estimation using the Karhunen-Loève Transform," in Proc. of IEEE Conf. on Comp. in Card., pp.269-272, September 19-22, 1989,
  28. M. Lagerholm, C. Peterson, G. Braccini, L. Edenbrandt, and L. Sörnmo, "Clustering ECG complex using Hermite Functions and selforganizing maps," T. On B. med. Eng, vol. 47, pp.838-848, 2000. https://doi.org/10.1109/10.846677
  29. L. Senhadii, G. Carrault, J. Bellanger, and G. Passariello, "Comparing wavelet transforms for recognizing cardiac patterns," IEEE Eng. in Med. and Bio. Mag., vol. 14, no. 2, pp.167-173, 1995. https://doi.org/10.1109/51.376755
  30. G. Herrero, A. Gotchev, I. Christov, K. Egiazarian, "Heartbeat classification using independent component analysis and matching Pursuits," in Proc. of int. Conf. on Acoustics, Speech, and Signal processing, pp.725-728, March 18-23, 2005.
  31. I. Christov and G. Bortolan, "Ranking of pattern recognition parameters for premature ventricular contractions classification by neural networks," Physiological Measurement, vol. 25, no. 5, pp.1281-1290, 2004. https://doi.org/10.1088/0967-3334/25/5/017
  32. I. M. Ishag, A. F. A. Dafa-Alla, G. Min Yi, D. G. Lee, J-W. Bae, K. Ho Ryu, "Agglomeration, Cluster accuracy, Hierarchical clustering. On-body sensor," Advances in Experimental Medicine and Biology, vol. 680, no. 1, pp. 83-88, 2010. https://doi.org/10.1007/978-1-4419-5913-3_10
  33. S. Osowski and T. Linh, "ECG beat recognition using fuzzy hybrid neural network," IEEE Trans. Biomed. Eng., vol. 48, no. 11, pp.1265-1271, 2001. https://doi.org/10.1109/10.959322
  34. J. P. Abenstein, "Algorithms for real time ambulatory ECG monitoring," Biomed. Sci. Instrum, vol. 14, pp.73-79, 1978.
  35. H. G. Lee, K. Noh, B. J. Lee, H. S. Shon, K. Ho Ryu, "Cardiovascular Disease Diagnosis Method by Emerging Patterns," Advanced Data Mining and Applications ,vol. 4093, pp.819-826, 2006. https://doi.org/10.1007/11811305_89
  36. M. Chen, S. Gonzalez, A. Vasilakos, H. Cao and V. C. M. Leung, "Body Area Networks: A Survey", ACM/Springer Mobile Networks and Applications (MONET), Vol. 16, No. 2, pp. 171-193, April 2011. https://doi.org/10.1007/s11036-010-0260-8
  37. S. Gonzalez, M. Chen, V. Leung, "Mobility Support for Health Monitoring at Home Using Wearable Sensors", IEEE Transactions on Information Technology in Biomedicine, vol.15, no.4, pp.539-549, July 2011. https://doi.org/10.1109/TITB.2010.2104326
  38. G. Bortolan, R. Degani, and J. L. Willems, "ECG classification with neural networks and cluster analysis," in Proc. of IEEE Conf. on Com. In Card., pp.177-180, September 23-26, 1991.
  39. M. E. A. Bashir, D. G. Lee, M. Li, J. W. Bae, H. S. Shon, M. C. Cho, and K. H. Ryu, "Trigger Learning and ECG Parameter Tuning for Real-Time Cardiac Clinical Information System, IEEE Trans. In Bio Med., Vol. 16, No. 4, pp.561-571, July 2012
  40. S. Osowski, and T. H. Linh, "ECG beat recognition using fuzzy hybrid neural network," IEEE Trans. on Bio. Engineering, vol. 48, no. 11, pp.1265-1271, 2001. https://doi.org/10.1109/10.959322
  41. T. Yang, B. Devine, and P. Macfarlane, "Artificial neural networks for the diagnosis of atrial fibrillation," Med. and Bio. Engineering and computing, vol. 32, no. 6, pp.615-619, 1994. https://doi.org/10.1007/BF02524235
  42. A. Kampouraki, G. Manis, and C. Nikou, "heartbeat time series classification with support vector machines," IEEE Inf. Tech. in Biomedicine, vol. 13, no, 4, pp.512-518, 2009. https://doi.org/10.1109/TITB.2008.2003323
  43. F. Sheng-wei, "Diagnostic study on arrhythmia cordis based on particle swarm optimization-based support vector machine," Expert Systems with Applications, vol. 37, no. 10, 2010, pp.6748-6752. https://doi.org/10.1016/j.eswa.2010.02.126
  44. P. Chazal, M. Dwyer, and R. Reilly, "Automatic classification of heartbeats using ECG morphology and heartbeat interval features," IEEE Trans. Biomed. Eng., vol. 51, no. 7, pp.1196-1206, 2004. https://doi.org/10.1109/TBME.2004.827359
  45. A. Kampouraki, G. Manis, and C. Nikou, "heartbeat time series classification with support vector machines," Eng. In Med. And Bio. Sc., 2009, pp. 512 - 518
  46. K. Birman, "Rule-Based Learning for More Accurate ECG Analysis," Tran. On Puttern analysis and Mach. Intelligence., vol. 4, no. 4, pp.369-380, 1982.
  47. U. Rajendra, P. Subbann, S.Iyengar, A. Raod, and S. Dua, "Classification of heart rate data using artificial neural network and fuzzy equivalence relation," Pattern Recog., vol. 36, pp. 61-68, 2003. https://doi.org/10.1016/S0031-3203(02)00063-8
  48. O. Castillo, P. Melin, E. Ramirez, and J. Soria, "Hybrid intelligent system for cardiac arrhythmia classification with Fuzzy K-Nearest Neighbors and neural networks combined with a fuzzy system," Expert Systems with Applications, vol. 39, 2012, pp. 2947-2955. https://doi.org/10.1016/j.eswa.2011.08.156
  49. S. Mitra, M. Mitra, B.B. Chaudhuri, A rough set-based inference engine for ECG classification, IEEE Trans. Instrum. Meas., vol.55 (December), 2006, pp. 2198-2206. https://doi.org/10.1109/TIM.2006.884279
  50. I. M. Ishag, A. F. A. Dafa-Alla, G. Min Yi, D. G. Lee, J-W. Bae, K. Ho Ryu, "Agglomeration, Cluster accuracy, Hierarchical clustering. On-body sensor," Advances in Experimental Medicine and Biology, vol. 680, no. 1, 2010, pp. 83-88. https://doi.org/10.1007/978-1-4419-5913-3_10
  51. H. G. Lee, K. Noh, B. J. Lee, H. S. Shon, K. Ho Ryu, "Cardiovascular Disease Diagnosis Method by Emerging Patterns," Advanced Data Mining and Applications ,vol. 4093, 2006, pp.819-826. https://doi.org/10.1007/11811305_89
  52. M. E. A. Basheer, K. S. Ryu, U. Yun, and K. H. Ryu, "Pro-Detection of Atrial Fibrillation Using Mixture of Experts," will be published to IEICE Transaction, 2012.
  53. UCI Machine Learning Repository, "http://www.ics.uci.edu/-mlearn/MLRepository.html".
  54. WEKA web site, "http://www.cs.waikato.ac.nz/-ml/weka/index.html".
  55. M. Engin, "ECG beat classification using neuro-fuzzy network," Pattern Recognition Letters, vol. 25, pp.1715-1722, 2004. https://doi.org/10.1016/j.patrec.2004.06.014

Cited by

  1. The Experimental Study on Concrete Permeability of Wireless Communication Module Embedded in Reinforced Concrete Structures vol.9, pp.6, 2013, https://doi.org/10.1155/2013/520507
  2. Combining Support Vector Machine Recursive Feature Elimination and Intensity-dependent Normalization for Gene Selection in RNAseq vol.18, pp.5, 2013, https://doi.org/10.7472/jksii.2017.18.5.47
  3. Medical Data Feature Learning Based on Probability and Depth Learning Mining: Model Development and Validation vol.9, pp.4, 2013, https://doi.org/10.2196/19055