Evolutionary model selection in a wavelet-based support vector machine for automated seizure detection

被引:55
作者
Zavar, M. [1 ]
Rahati, S. [2 ]
Akbarzadeh-T, M. -R. [3 ]
Ghasemifard, H. [4 ]
机构
[1] Islamic Azad Univ, Sama Tech & Vocat Training Sch, Quchan Branch, Quchan, Iran
[2] Islamic Azad Univ, Mashhad Branch, Mashhad, Iran
[3] Ferdowsi Univ Mashhad, Ctr Appl Res Soft Comp & Intelligent Syst, Mashhad, Iran
[4] Mashhad Univ Med Sci, Dr Shiekh Pediat Hosp, Mashhad, Iran
关键词
Support vector machines; Genetic algorithm; Model selection; Wavelet kernel function; Partial seizure; ECG; ELECTROCARDIOGRAPHIC CHANGES; EPILEPSY; SYSTEM; DEATH;
D O I
10.1016/j.eswa.2011.01.087
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Support vector machines (SVM) have in recent years been gainfully used in various pattern recognition applications. Based on statistical learning theory, this paradigm promises strong robustness to noise and generalization to unseen data. As in any classification technique, appropriate choice of the kernels and input features play an important role in SVM performance. In this study, an evolutionary scheme searches for optimal kernel types and parameters for automated seizure detection. We consider the Lyapunov exponent, fractal dimension and wavelet entropy for possible feature extraction. The classification accuracy of this approach is examined by applying the MIT (Massachusetts Institute of Technology) dataset and comparing results with the SVM. The MIT-BIH dataset has the electrocardiographic (ECG) changes in patients with partial epilepsy which two types ECG beats (partial epilepsy and normal). A comparison of results shows that performance of the evolutionary scheme outweighs that of support vector machine. In the best condition, the accuracy rate of the proposed approaches reaches 100% for specificity and 96.29% for sensitivity. (C) 2011 Elsevier Ltd. All rights reserved.
引用
收藏
页码:10751 / 10758
页数:8
相关论文
共 24 条
[1]   Postictal heart rate oscillations in partial epilepsy [J].
Al-Aweel, IC ;
Krisknamurthy, KB ;
Hausdorff, JM ;
Mietus, JE ;
Ives, JR ;
Blum, AS ;
Schomer, DL ;
Goldberger, AL .
NEUROLOGY, 1999, 53 (07) :1590-1592
[2]  
AVCI E, 2008, EXPERT SYSTEMS APPL, P1
[3]   A tutorial on Support Vector Machines for pattern recognition [J].
Burges, CJC .
DATA MINING AND KNOWLEDGE DISCOVERY, 1998, 2 (02) :121-167
[4]   SUPPORT-VECTOR NETWORKS [J].
CORTES, C ;
VAPNIK, V .
MACHINE LEARNING, 1995, 20 (03) :273-297
[5]  
cui w.z., 2006, IEEE INF THEOR WORKS, P340
[6]   Neural network-based EKG pattern recognition [J].
Foo, SY ;
Stuart, G ;
Harvey, B ;
Meyer-Baese, A .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2002, 15 (3-4) :253-260
[7]   An expert system for detection of electrocardiographic changes in patients with partial epilepsy using wavelet-based neural networks [J].
Güler, I ;
Übeyli, ED .
EXPERT SYSTEMS, 2005, 22 (02) :62-71
[8]   Application of adaptive neuro-fuzzy inference system for detection of electrocardiographic changes in patients with partial epilepsy using feature extraction [J].
Güler, I ;
Übeyli, ED .
EXPERT SYSTEMS WITH APPLICATIONS, 2004, 27 (03) :323-330
[9]   Sudden unexpected death in epilepsy: A search for risk factors [J].
Hitiris, Nikolas ;
Suratman, Suraya ;
Kelly, Kevin ;
Stephen, Linda J. ;
Sills, Graerne J. ;
Brodie, Martin J. .
EPILEPSY & BEHAVIOR, 2007, 10 (01) :138-141
[10]   Finding the missing link between ictal bradyarrhythmia, ictal asystole, and sudden unexpected death in epilepsy [J].
Leung, H. ;
Kwan, P. ;
Elger, C. E. .
EPILEPSY & BEHAVIOR, 2006, 9 (01) :19-30