ECG Based Myocardial Infarction Detection Using Different Classification Techniques

ECG signal classification is essential for the production of high grade classification results to support diagnostic decisions and develop treatments. Recent methods of feature extraction—for example, autoregressive (AR) modeling; magnitude squared coherence (MSC); wavelet coherence (WTC) using the PhysioNet database—have yielded an extensive set of features. A large number of these features may be inconsequential, as they contain superfluous components that put an excessive burden on computation leading to a loss of performance. For this reason, the hybrid firefly and particle swarm optimization (FFPSO) method is used to optimize the raw ECG signal instead of extracting features using AR, MSC and WTC. This chapter proposes a design for an efficient system for the classification of mocardial infarction (MI) using an artificial neural network (ANN) (Levenberg-Marquardt Neural Network) and two different classifiers. Our experimental results show that an FFPSO algorithm with an ANN give a 99.3% rate of accuracy when combining the MIT-BIH and the NSR databases.

[1]  Amrit Pal Singh,et al.  Comparative Study of Firefly Algorithm and Particle Swarm Optimization for Noisy Non- Linear Optimization Problems , 2012 .

[2]  Surekha Borra,et al.  Attendance management system using hybrid face recognition techniques , 2016, 2016 Conference on Advances in Signal Processing (CASP).

[3]  V. Rao Vemuri,et al.  Use of K-Nearest Neighbor classifier for intrusion detection , 2002, Comput. Secur..

[4]  Martin T. Hagan,et al.  Neural network design , 1995 .

[5]  J Spilka,et al.  Detection of inferior myocardial infarction: A comparison of various decision systems and learning algorithms , 2010, 2010 Computing in Cardiology.

[6]  Mohammad Saleh Nambakhsh,et al.  Morphological Heart Arrhythmia Detection Using Hermitian Basis Functions and kNN Classifier , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Xin-She Yang.  17. Firefly Algorithm , 2010 .

[8]  Xin-She Yang,et al.  Firefly Algorithm, Lévy Flights and Global Optimization , 2010, SGAI Conf..

[9]  Dana H. Brooks,et al.  Feature-based segmentation of ECG signals , 1996, Proceedings of Third International Symposium on Time-Frequency and Time-Scale Analysis (TFTS-96).

[10]  Rabindra Kumar Sahu,et al.  A hybrid firefly algorithm and pattern search technique for automatic generation control of multi area power systems , 2015 .

[11]  P. Balachennaiah,et al.  Optimizing real power loss and voltage stability limit of a large transmission network using firefly algorithm , 2016 .

[12]  Hao Zhang,et al.  Highly Accurate ECG Beat Classification Based on Continuous Wavelet Transformation and Multiple Support Vector Machine Classifiers , 2009, 2009 2nd International Conference on Biomedical Engineering and Informatics.

[13]  Leo Schamroth,et al.  An introduction to electrocardiography , 1976 .

[14]  Rajiv Ranjan,et al.  A Unified Approach of ECG Signal Analysis , 2012 .

[15]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[16]  Xin-She Yang,et al.  Firefly algorithm, stochastic test functions and design optimisation , 2010, Int. J. Bio Inspired Comput..

[17]  Songbo Tan,et al.  An effective refinement strategy for KNN text classifier , 2006, Expert Syst. Appl..

[18]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[19]  John G. Proakis,et al.  Digital Signal Processing: Principles, Algorithms, and Applications , 1992 .

[20]  Sri Rama Krishna Kalva,et al.  Detection of Bundle Branch Block using Adaptive Bacterial Foraging Optimization and Neural Network , 2017 .

[21]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[22]  Padmavathi Kora,et al.  Hybrid Bacterial Foraging and Particle Swarm Optimization for detecting Bundle Branch Block , 2015, SpringerPlus.

[23]  Si Wu,et al.  Improving support vector machine classifiers by modifying kernel functions , 1999, Neural Networks.

[24]  S. Hargittai.  Savitzky-Golay least-squares polynomial filters in ECG signal processing , 2005, Computers in Cardiology, 2005.

[25]  Padmavathi Kora,et al.  Improved Bat algorithm for the detection of myocardial infarction , 2015, SpringerPlus.

[26]  R. Gupta,et al.  A statistical approach for determination of time plane features from digitized ECG , 2011, Comput. Biol. Medicine.

[27]  Madhuchhanda Mitra,et al.  Application of Cross Wavelet Transform for ECG Pattern Analysis and Classification , 2014, IEEE Transactions on Instrumentation and Measurement.

[28]  Pan Wentao,et al.  Applying SVM for Foot Pressure Pattern Classification , 2014 .

[29]  Vivekananda Mukherjee,et al.  Firefly algorithm for congestion management in deregulated environment , 2016 .

[30]  Li Sun,et al.  ECG Analysis Using Multiple Instance Learning for Myocardial Infarction Detection , 2012, IEEE Transactions on Biomedical Engineering.

[31]  Nilanjan Dey,et al.  Attendance Recording System Using Partial Face Recognition Algorithm , 2017 .