Based on the advantages and disadvantages of genetic algorithm (GA) and artificial neural network (ANN), an optimization model with the adaptive genetic algorithm and the traditional BP neural network is presented for...
详细信息
ISBN:
(纸本)9780769547923
Based on the advantages and disadvantages of genetic algorithm (GA) and artificial neural network (ANN), an optimization model with the adaptive genetic algorithm and the traditional BP neural network is presented for the quantitative detection of gas mixtures. To overcome the disadvantages of ANN with inherent slowly searching rate and partially leading to minimum, the adaptive genetic algorithm is used to get better initial weights and thresholds of the BP network in the early stage, which combines the advantages of genetic algorithm with parallel-computing and strong whole searching capacity. In the later, the network is trained by the errorbackpropagation method A three-layer 7x18x3 BP network is designed for a group of gas mixtures with five samples. The results show that the convergence speed and the learn precision of adaptive genetic algorithm optimizing neural network are better than that of the traditional BP algorithm, which can make shorter the calculation time three times at the begin of the same weights and thresholds and at the end of global error with the magnitude of 1x10(-4). The application of GA optimizing BP network to the recognition of gas mixtures is reliable and the method can improve the detection efficiency of gas mixtures, which can give some references for developing intelligent detection apparatus.
In this study, a neural network (NN) modeling approach has been used to predict the mechanical and geometrical behaviors of mouse embryo cells. Two NN models have been implemented. In the first NN model dimple depth (...
详细信息
In this study, a neural network (NN) modeling approach has been used to predict the mechanical and geometrical behaviors of mouse embryo cells. Two NN models have been implemented. In the first NN model dimple depth (w), dimple radius (a) and radius of the semi-circular curved surface of the cell (R) were used as inputs of the model while indentation force (f) was considered as output. In the second NN model, indentation force (f), dimple radius (a) and radius of the semi-circular curved surface of the cell (R) were considered as inputs of the model and dimple depth was predicted as the output of the model. In addition, sensitivity analysis has been carried out to investigate the influence of the significance of input parameters on the mechanical behavior of mouse embryos. Experimental data deduced by Fluckiger (2004) were collected to obtain training and test data for the NN. The results of these investigations show that the correlation values of the test and training data sets are between 0.9988 and 1.0000, and are in good agreement with the experimental observations.
Wheat sharp eyespot is an important plant disease of wheat roots. To improve the accuracy of prediction of this disease and to control the disease effectively, This paper presents a new prediction model by principal c...
详细信息
ISBN:
(纸本)9783037850817
Wheat sharp eyespot is an important plant disease of wheat roots. To improve the accuracy of prediction of this disease and to control the disease effectively, This paper presents a new prediction model by principal components analysis (PCA) and backpropagation artificial neural network (BP-ANN) methods. The application of BP and PCA in forecasting plant diseases was also summarized. Application of BP Neural Network and PCA in Prediction for wheat Diseases. To build diagnosing wheat diseases based on BP neural network, and PCA was discussed. The precision of the simulation is the high, fault tolerant capacity is better, reliability, and robustness are better. The result of the forecast model is satisfied. So the model of predicting wheat disease based on adaptive neural networks has the important reference value. The test results showed to build the early warning model is effective and likely which, will provide a model to set up the effective early warning platform. Results showed that BP neural network and PCA had a strong application value in the diagnosis of plant diseases.
In this paper we use a neural network approach for defects identification in textile. The images analyzed came from an artificial vision system that we used to acquire and memorize them in bitmap file format. The visi...
详细信息
ISBN:
(纸本)9783540859833
In this paper we use a neural network approach for defects identification in textile. The images analyzed came from an artificial vision system that we used to acquire and memorize them in bitmap file format. The vision system is made of two grey scale line scan camera arrays and each array is composed of four CCD cameras with a sensor of 2048 pixels. Every single camera has a field of view of 600mm. The big amount of pixels to be studied to determine whether the texture is defective or not, requires the implementation of some encoding technique to reduce the number of the significant elements. The artificial neural networks (ANN) are manipulated to compress a bitmap that may contain several defects in order to represent it with a number of coefficients that is smaller than the total number of pixel but still enough to identify all kinds of defects classified. An error back propagation algorithm is also used to train the neural network. The proposed technique includes, also, steps to break down large images into smaller windows or array and eliminate redundant information.
In optimal dispatching decision system of hydropower station, discharge of reservoir is forecast usually. However the discharge has complicated nonlinear relations with downriver level and backwater flux when backwate...
详细信息
ISBN:
(纸本)0780379896
In optimal dispatching decision system of hydropower station, discharge of reservoir is forecast usually. However the discharge has complicated nonlinear relations with downriver level and backwater flux when backwater effect exists. It is difficult to get satisfactory forecasting results with traditional linear interpolation method. This paper proposes a nonlinear decision-making method. based on errorbackpropagation (EBP) Artificial Neural Network (ANN) to establish forecasting discharge model of reservoir. Improved EBP algorithm is presented to process ANN model training. Simulation results show that the proposed method forecasts discharge with the backwater effect better than traditional linear interpolation method. The ANN model and improved EBP algorithm proposed are also applicable to other similar systems.
In this paper, we propose a new method for direct identifying the stator flux linkage and electromagnetic torque of induction motors, which uses artificial neural networks. Because the multilayer feedforward network h...
详细信息
ISBN:
(纸本)7506251159
In this paper, we propose a new method for direct identifying the stator flux linkage and electromagnetic torque of induction motors, which uses artificial neural networks. Because the multilayer feedforward network has the good capability of approximating any linear or nonlinear function, which is trained using the backpropagation (BP) algorithm, it can observe the stator flux linkage and electro-magnetic torque of induction motors accurately. Based on this principle, we built a new direct torque control (DTC) system. With simulation experiment, the results show that this method can observe accurately the stator flux linkage and electro-magnetic torque of induction motors, and the system has good dynamic and static performance.
A new method for high-fidelity holographic storage is suggested. A two-dimensional optimized phase mask is adopted during hologram recording. The EBP terrorbackpropagation) method and phase retrieval algorithm are u...
详细信息
A new method for high-fidelity holographic storage is suggested. A two-dimensional optimized phase mask is adopted during hologram recording. The EBP terrorbackpropagation) method and phase retrieval algorithm are used for the phase mask design. Simulation results show that reconstruction error is significantly reduced compared with that of random phase mask and no phase mask, while the spectral uniformity is also improved. (C) 1999 Elsevier Science B.V. All rights reserved.
The purpose of this study was to examine the usefulness of BP neural networks for source localization of MEG. Since the performance of this method does not depend on the complexity of brain parameters and source model...
详细信息
The purpose of this study was to examine the usefulness of BP neural networks for source localization of MEG. Since the performance of this method does not depend on the complexity of brain parameters and source models, a homogeneous brain model and a single current dipole source are assumed for convenience. Localization accuracy was examined in relation to the configuration and scale of the network. As a result, average error for position and moment estimations was within 2%, while the maximum error was about 5%. It was therefore concluded that the neural network method was useful for MEG source localization, though some improvements are still necessary.
暂无评论