A radial basis probabilistic process neural network model and corresponding classification algorithm

Liu, Kun; Xu, Shengli; Feng, Naidan

doi:10.1007/s10489-018-1369-x

Cited by 12 publications

(12 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RBPNN is a classification model based on Bayes decision theory, which offers high learning efficiency and dis-tinguishing signals features ability [29], [30]. This RBPNN is composed of an input layer, a kernel transformation layer based on radial basis probability neurons, a pattern layer, and a Softmax classifier.…”

Section: B a Radial Basis Probabilistic Neural Networkmentioning

confidence: 99%

A CNN-RBPNN Model With Feature Knowledge Embedding and its Application to Time-Varying Signal Classification

Lü¹,

Wang²,

Xu³

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

A novel technique, combining the feature extraction mechanisms of a convolutional neural network (CNN) with the classification method of a radial basis probability neural network (RBPNN), is proposed for small sample set modeling and feature knowledge embedding in multi-channel time-varying signal classification. This CNN-RBPNN consists of a signal input layer, signal feature parallel extraction and integration units, and an RBPNN classifier. Each channel signal in a feature extraction unit corresponds to a 1D CNN. The extracted features are represented as feature vectors, and these vectors constitute a comprehensive feature matrix. The RBPNN classifier was designed using signal feature embedding mechanism based on radial basis kernels and the property of combining pattern subclasses into pattern classes to form complex class boundaries. A dynamic clustering algorithm was used to divide each pattern class sample into several subclasses. Typical signal samples in each pattern subclass were designated as kernel centers, in order to achieve signal categories features embedding. This process was also used to determine the number of nodes in the RBPN layer. The RBPN layer outputs were selectively summed in the pattern layer according to kernel center category, which can generate irregular class boundaries, reducing the overlap among different pattern class boundary. The proposed CNN-RBPNN replaces the fullconnection layer and classifier unit of conventional CNN with RBPNN, which can extract and represent signals distribution features and structural properties, implement structural and data constraints. This can reduce the structural risks of small sample set modeling. In this study, the properties of CNN-RBPNN are analyzed and an integrated learning algorithm is proposed. An experiment was conducted using 12-lead ECG signals in a seven-classification in the case of small sample set. Results demonstrated that, the correct recognition rate is 5.7% higher than other methods in the experiment, the performance evaluation index also showed significant improvement. INDEX TERMS Time-varying signal classification, CNN feature extraction, radial basis probability network, prior feature knowledge embedding, small sample set modeling

show abstract

Section: B a Radial Basis Probabilistic Neural Networkmentioning

confidence: 99%

A CNN-RBPNN Model With Feature Knowledge Embedding and its Application to Time-Varying Signal Classification

Lü¹,

Wang²,

Xu³

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…The output of the pattern layer is a selective sum for PNN hidden layer outputs according to the categorical attributes of the connection weight function vector. As a result, it enlarges the difference in the attribution probability of different types of signal samples, that can improve the separability of patterns [5].…”

Section: B Probabilistic Process Neural Network Modelmentioning

confidence: 99%

“…k is the serial number set of the PPN hidden layer node corresponding to the k th pattern class. The probability of Softmax classifier assigning a training signal sample X i (t) to the category k [5], [25] is: p(y = k|q (i) ; θ ) =…”

Section: Volume 7 2019mentioning

confidence: 99%

“…The input and output of some systems are functions which vary in time [1]- [4]. Signal analysis and evaluation results often have a certain degree of uncertainty, due to the influence of systematic error and noise [5]. Instead, answers are often converted to a degree of certainty, a value between 0 and 1, representing a certain probability or ambiguity [6], [7].…”

Section: Introductionmentioning

confidence: 99%

“…On the basis of the previous study on probability and fuzziness in the classification of t-v signals [5], [17], this paper proposes a novel probabilistic process neuron (PPN) and a probabilistic process neural network (PPNN) model, which extends the conventional PNN model in the time domain. The inputs of PPN are multi-channel t-v signals.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Probabilistic Process Neural Network and Its Application in ECG Classification

Feng

Liang

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

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.

show abstract

A novel hybrid deep learning method with cuckoo search algorithm for classification of arrhythmia disease using ECG signals

Sharma

Dinkar

Gupta

2021

Neural Comput & Applic

View full text Add to dashboard Cite

A radial basis probabilistic process neural network model and corresponding classification algorithm

Cited by 12 publications

References 28 publications

A CNN-RBPNN Model With Feature Knowledge Embedding and its Application to Time-Varying Signal Classification

A CNN-RBPNN Model With Feature Knowledge Embedding and its Application to Time-Varying Signal Classification

A Probabilistic Process Neural Network and Its Application in ECG Classification

A novel hybrid deep learning method with cuckoo search algorithm for classification of arrhythmia disease using ECG signals

Contact Info

Product

Resources

About