A Probabilistic Process Neural Network and Its Application in ECG Classification

Abstract

A novel probabilistic process neural network (PPNN) model is proposed for the multi-channel time-varying signal classification problems with ambiguity and randomness distribution characteristics. This model was constructed from an input time-varying signal layer, a probabilistic process neuron (PPN) hidden layer, a pattern layer, and a Softmax classifier. The number of nodes in the input layer is the same as the number of time-varying signal input channels, which can realize the overall input of the time-varying signal. The PPN hidden layer performs the spatio-temporal aggregation operations for time-varying input signals and probabilistic outputs. The connection weight functions from the input layer to the hidden layer are represented by the typical samples or cluster center functions in different pattern subsets of the sample set, which the prior knowledge of signal categories is implicitly expressed by the morphological distribution features and combinational relations. A pattern layer selectively summed to the output of the PPN hidden layer using the categorical attributes of the connection weight function vector. And the Softmax classifier implements the probabilistic classification of time-varying signals. PPNN has the advantages of fewer model parameters, suitable for modeling small samples and integrating prior knowledge of signal categories. This paper develops the specific learning algorithms which synthesize dynamic time warping, C-means clustering, and BP algorithm. The 12-lead electrocardiogram (ECG) signals for heart disease diagnosis were used for classification testing. The experimental results from 12-lead ECG signal across ten types of disease classification verify the effectiveness of the model and the proposed algorithm. INDEX TERMS Dynamic signal classification, Bayesian decision rules, probabilistic process neural network, training algorithm, ECG signal classification.

Cervical Histopathology Image Classification Using Multilayer Hidden Conditional Random Fields and Weakly Supervised Learning

“…Components of an ANN include neurons, connections, weights, biases, propagation functions and learning rules. Recently, a novel probabilistic process neural network (PPNN) was purposed to classify electrocardiogram signals [28]. In addition, a new content-based medical image retrieval (CBMIR) framework using convolutional neural network (CNN) and hash coding is proposed [29].…”

A Flexible and Stretchable 12‐Lead Electrocardiogram System with Individually Deformable Interconnects

“…Similarly, the T wave at lead aVL is biphasic with a lower amplitude for women. [60] Currently, some artificial intelligence algorithms for ECG signal processing mainly include convolutional neural networks (CNN), [61,62] probabilistic neural networks, [63,64] support vector machines (SVMs), [65,66] artificial neural networks (ANN), [67] fuzzy systems, [68] neurofuzzy systems, [69,70] genetic-fuzzy systems, [71] and linear discriminants (LDs). [72,73] Since this flexible system is only applied to a limited number of healthy individuals, a CNN model provided in the literature [62] that has been trained for 12-lead ECG signals was directly adopted to further verify that the ECG signals recorded with the flexible system have similar characters with the ECG recorded with the clinical 12-lead systems.…”

Early Strokes Detection of Patient and Health Monitoring System Based On Data Analytics Using K-Means Algorithm

“…It limits the experimental results to accept the noiseless signals and reject the noisy signals under unsupervised health monitoring. [11]It develops the precise learning algorithms that synthesize dynamic time deformation, C-means clump, and BP algorithmic program.…”