This paper proposes a Fuzzy Neural Network (FNN) model, which uses a propagation algorithm. A logical operation is defined by a set of weights which are independent of inputs. The realization of the basic And,Or and N...This paper proposes a Fuzzy Neural Network (FNN) model, which uses a propagation algorithm. A logical operation is defined by a set of weights which are independent of inputs. The realization of the basic And,Or and Negation fuzzy logical operations is shown by the fuzzy neuron. A example in fault diagnosis is put forward and the result witnesses some effectiveness of the new FNN model.展开更多
This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that th...This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.展开更多
In order to predict and improve the performance of natural gas/diesel dual fuel engine (DFE), a combustion rate model based on forward neural network was built to study the combustion process of the DFE. The effect ...In order to predict and improve the performance of natural gas/diesel dual fuel engine (DFE), a combustion rate model based on forward neural network was built to study the combustion process of the DFE. The effect of the operatin g parameters on combustion rate was also studied by means of this model. The stu dy showed that the predicted results were good agreement with the experimental d a ta. It was proved that the developed combustion rate model could be used to succ essfully predict and optimize the combustion process of dual fuel engine.展开更多
Accurate blood pressure （BP） measurement is essential in epidemiological studies, screening programmes, and research studies as well as in clinical practice for the early detection and prevention of high BP-related ...Accurate blood pressure （BP） measurement is essential in epidemiological studies, screening programmes, and research studies as well as in clinical practice for the early detection and prevention of high BP-related risks such as coronary heart disease, stroke, and kidney failure. Posture of the participant plays a vital role in accurate measurement of BP. Guidelines on measurement of BP contain recommendations on the position of the back of the participants by advising that they should sit with supported back to avoid spuriously high readings. In this work, principal component analysis （PCA） is fused with forward stepwise regression （SWR）, artificial neural network （ANN）, adaptive neuro-fuzzy inference system （ANFIS）, and the least squares support vector machine （LS-SVM） model for the prediction of BP reactivity to an unsupported back in norrnotensive and hypertensive participants. PCA is used to remove multi-collinearity among anthropometric predictor variables and to select a subset of components, termed ＇principal components＇ （PCs）, from the original dataset. The selected PCs are fed into the proposed models for modeling and testing. The evaluation of the performance of the constructed models, using appropriate statistical indices, shows clearly that a PCA-based LS-SVM （PCA-LS-SVM） model is a promising approach for the prediction of BP reactivity in comparison to others. This assessment demonstrates the importance and advantages posed by hybrid models for the prediction of variables in biomedical research studies.展开更多
基金The National Natural Science Foundation of China(No.61565004)the Natural Science Foundation of Guangxi(Nos.2015GXNSFBA139252+7 种基金2014GXNSFGA1180032013GXNSFDA019002)Guangxi Education Scientific Research Program(Nos.ZD2014057KY2015B103)Guilin Scientific Research and Technology Development Program(Nos.20140127-120150133-3)Guangxi Scientific Research and Technology Development Program(No.1598017-1)Guangxi Key Laboratory of Automatic Detecting Technology and Instruments(No.YQ15104)
文摘This paper proposes a Fuzzy Neural Network (FNN) model, which uses a propagation algorithm. A logical operation is defined by a set of weights which are independent of inputs. The realization of the basic And,Or and Negation fuzzy logical operations is shown by the fuzzy neuron. A example in fault diagnosis is put forward and the result witnesses some effectiveness of the new FNN model.
文摘This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.
文摘In order to predict and improve the performance of natural gas/diesel dual fuel engine (DFE), a combustion rate model based on forward neural network was built to study the combustion process of the DFE. The effect of the operatin g parameters on combustion rate was also studied by means of this model. The stu dy showed that the predicted results were good agreement with the experimental d a ta. It was proved that the developed combustion rate model could be used to succ essfully predict and optimize the combustion process of dual fuel engine.
文摘Accurate blood pressure （BP） measurement is essential in epidemiological studies, screening programmes, and research studies as well as in clinical practice for the early detection and prevention of high BP-related risks such as coronary heart disease, stroke, and kidney failure. Posture of the participant plays a vital role in accurate measurement of BP. Guidelines on measurement of BP contain recommendations on the position of the back of the participants by advising that they should sit with supported back to avoid spuriously high readings. In this work, principal component analysis （PCA） is fused with forward stepwise regression （SWR）, artificial neural network （ANN）, adaptive neuro-fuzzy inference system （ANFIS）, and the least squares support vector machine （LS-SVM） model for the prediction of BP reactivity to an unsupported back in norrnotensive and hypertensive participants. PCA is used to remove multi-collinearity among anthropometric predictor variables and to select a subset of components, termed ＇principal components＇ （PCs）, from the original dataset. The selected PCs are fed into the proposed models for modeling and testing. The evaluation of the performance of the constructed models, using appropriate statistical indices, shows clearly that a PCA-based LS-SVM （PCA-LS-SVM） model is a promising approach for the prediction of BP reactivity in comparison to others. This assessment demonstrates the importance and advantages posed by hybrid models for the prediction of variables in biomedical research studies.
