Heartbeat Classification Algorithm Based on One-Dimensional Convolution Neural Network

Abstract

The morbidity of cardiovascular disease increasingly rises, which makes great impact upon people’s health and life. Electrocardiogram (ECG) beat classification is of great significance to clinical diagnosis of cardiovascular diseases. Traditional ECG signal classification algorithm relies heavily on the accuracy of feature extraction or increases the complexity of the calculation process by means of the correlation characteristic coefficient transformation, which results in that the ECG beat classification effect is still not satisfactory. Aimed at this problem, a novel method based on convolution neural network (CNN) is presented in this paper. First, ECG signal is preprocessed to suppress the noise and to locate the R peaks, and five kinds of ECG beat waveform data are obtained. Then taking ECG beat sampling points as input, four layers of one-dimensional CNN are constructed for feature extraction and classification. Finally, experimental verification is carried out on the data from MIT-BIH database, and the accuracy of recognition and classification of the presented method reaches 99.10%. Comparison with the methods based on artificial features, this method shows better performance, which avoids serious dependence on the accuracy of feature extraction, skips the steps of feature extraction and selection, and reduces the complexity of computational process.

Hierarchical recursive signal modeling for multifrequency signals based on discrete measured data

“…The simulation results verify that the hierarchical estimation methods based on the separation have better performance than the modeling methods without separation. The proposed methods in this paper can combine other identification methods 61‐65 to investigate the parameter estimation problems of other linear and nonlinear models and control systems and can be applied to other fields 66‐73 such as signal processing, prediction and engineering application systems 74‐79 and so on.…”

Maximum likelihood extended gradient‐based estimation algorithms for the input nonlinear controlled autoregressive moving average system with variable‐gain nonlinearity

“…The proposed identification methods for the IN‐CARMA system with variable‐gain nonlinearity can joint some other identification ideas such as the particle filtering technique and the hierarchial principle or some other mathematical strategies to explore new identification methods and they can have potential advantages in identifying other linear and nonlinear systems. The proposed parameter estimation methods for the IN‐CARMA system with variable‐gain nonlinearity in this article can combine some mathematical tools and parameter estimation algorithms 72‐76 to study the parameter estimation problems of different systems with colored noises 77‐80 and can be applied to other literatures 81‐85 such as signal modeling and communication networked systems and engineering application systems and so on.…”

Maximum likelihood hierarchical least squares‐based iterative identification for dual‐rate stochastic systems

“…The simulation results show that the proposed algorithms can generate more accurate parameter estimates and have a faster convergence rate than the recursive least squares algorithm and the auxiliary model-based stochastic gradient algorithm. The proposed methods can be extended to study identification problems of other scalar or multivariable, linear, or nonlinear stochastic systems with colored noises [61][62][63][64][65][66] and can be applied to fields [67][68][69][70][71] such as engineering manufacturing systems.…”