Neural network-based EKG pattern recognition

被引：64

作者：

Foo, SY ^{[1
]}

Stuart, G

Harvey, B

Meyer-Baese, A

机构：

[1] FSU Coll Engn, FAMU, Dept Elect Engn & Comp Engn, Tallahassee, FL 32310 USA

[2] Sonalyst Inc, Panama City, FL 32407 USA

来源：

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE | 2002年 / 15卷 / 3-4期

关键词：

neural networks; electrocardiogram; pattern recognition;

D O I：

10.1016/S0952-1976(02)00041-6

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The highly nonlinear chaotic nature of electrocardiogram (EKG) data represents a well-suited application of artificial neural networks (ANNs) for the detection of normal and abnormal heartbeats. Digitized EKG data were applied to a two-layer feed-forward neural network trained to distinguish between different types of heartbeat patterns. The Levenberg-Marquardt training algorithm was found to provide the best training results. In our study, the trained ANN correctly distinguished between normal heartbeats and premature ventricular contractions in 92% of the cases presented. (C) 2001 Elsevier Science Ltd. All rights reserved.

引用

页码：253 / 260

页数：8

共 9 条

[1]

[Anonymous], 1990, Proceedings Computers in Cardiology

[2]

CONDE T, 1994, P IEEE ICNN ORL FL J, P3552

[3] TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM [J].

HAGAN, MT ;

MENHAJ, MB .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (06) :989-993

[4]

MARK RG, 1982, P 4 ANN C IEEE EMBS, P205

[5]

Nguyen D., 1990, INT JOINT C NEURAL N, V3, P21, DOI DOI 10.1109/IJCNN.1990.137819

[6]

PRESS WH, 1992, NUMERICAL RECIPES C, P97

[7]

RUMELHART DE, 1994, IEEE T NEURAL NETWOR, V5, P989

[8]

VANBEMMEL JH, 1982, HDB STATISTICS, V2, P501

[9]

WEINBERG GM, 1995, DESIGN CARDIAC PACEM, P34

← 1 →