Fully parallel ANN-based arrhythmia classifier on a single-chip FPGA: FPAAC

被引:14
作者
Ozdemir, Ahmet Turan [1 ]
Danisman, Kenan [1 ]
机构
[1] Erciyes Univ, Fac Engn, Dept Elect & Elect Engn, Kayseri, Turkey
关键词
Artificial neural networks; electrocardiogram; principal component analysis; arrhythmia; field programmable gate arrays; NEURAL-NETWORK; BEAT DETECTION; ECG SIGNALS; TRANSFORMS;
D O I
10.3906/elk-1006-488
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recognition of cardiac arrhythmias by electrocardiogram (ECG) is an important issue for diagnosis of cardiac abnormalities. Many studies on recognition of cardiac arrhythmias by ECG, using various techniques, have been performed in the past 20 years. Artificial neural networks (ANNs) are the most widely used tool in medical diagnosis systems (MDS) because of their powerful prediction characteristics. An ANN model is inspired by real biological neural networks, with a parallel structure that is potentially fast for computation. However, the suggested ANN architectures in the literature can only be run sequentially, on powerful processors, due to their complexity. Our approach enables the implementation of a simple ANN architecture with lower requirements for hardware resources. The features of the ECG signal are reduced dramatically using principle component analysis (PCA) while keeping the error rate of the ANN at an acceptable level, near 5%. To enable the implementation of real ANN models on parallel devices, the features of the ECG signal that are applied to the ANN inputs must be reduced. In this study, field programmable gate arrays (FPGA) implementation of a fully parallel, fault-tolerant ANN for ECG arrhythmia classification (FPAAC) is realized. An ANN model, which consists of 8 inputs, a hidden layer with 2 neurons, and I output neuron, is implemented on an FPGA using IEEE-754 32-bit floating-point numerical representation. FPAAC classifies 3 classes of arrhythmia, premature ventricular contraction (PVC), fusion (F), and normal (N) beats, and its accuracy is 97.66%. The ECG records used in this work were taken from the MIT-BIH arrhythmia database.
引用
收藏
页码:667 / 687
页数:21
相关论文
共 36 条
[1]   Evaluating arrhythmias in ECG signals using wavelet transforms [J].
Addison, PS ;
Watson, JN ;
Clegg, GR ;
Holzer, M ;
Sterz, F ;
Robertson, CE .
IEEE ENGINEERING IN MEDICINE AND BIOLOGY MAGAZINE, 2000, 19 (05) :104-109
[2]  
ALKAZZAZ SA, 2008, 3 INT C INF COMM TEC, P1
[3]  
[Anonymous], 2019, NEURAL NETWORK DESIG
[4]  
[Anonymous], 1994, Neural networks: a comprehensive foundation
[5]  
ASYALI MH, 2008, 13 NAT BIOM ENG M BI, P1
[6]  
ATOUI H, 2010, INFORM TECHNOLOGY BI, V99, P1
[7]   Principal component analysis in ECG signal processing [J].
Castells, Francisco ;
Laguna, Pablo ;
Soernmo, Leif ;
Bollmann, Andreas ;
Roig, José Millet .
EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING, 2007, 2007 (1)
[8]  
Cvikl M, 2007, IFMBE PROC, V16, P66
[9]   FPGA-oriented HW/SW implementation of ECG beat detection and classification algorithm [J].
Cvikl, Matej ;
Zemva, Andrej .
DIGITAL SIGNAL PROCESSING, 2010, 20 (01) :238-248
[10]   Modelling of the hysteresis effect of target voltage in reactive magnetron sputtering process by using neural networks [J].
Danisman, Kenan ;
Danisman, Senguel ;
Savas, Soner ;
Dalkiran, Ilker .
SURFACE & COATINGS TECHNOLOGY, 2009, 204 (05) :610-614