This paper describes a simple method of generating concentration gradients with linear and parabolic profiles by using a Christmas tree-shaped microfluidic network.The microfluidic gradient generator consists of two p...This paper describes a simple method of generating concentration gradients with linear and parabolic profiles by using a Christmas tree-shaped microfluidic network.The microfluidic gradient generator consists of two parts：a Christmas tree-shaped network for gradient generation and a broad microchannel for detection.A two-dimensional model was built to analyze the flow field and the mass transfer in the microfluidic network.The simulating results show that a series of linear and parabolic gradient profiles were generated via adjusting relative flow rate ratios of the two source solutions（R_L^2≥0.995 and _PR^2≥0.999）,which could match well with the experimental results（R_L^2≥0.987 and _PR^2≥0.996）.The proposed method is promising for the generation of linear and parabolic concentration gradient profiles,with the potential in chemical and biological applications such as combinatorial chemistry synthesis,stem cell differentiation or cytotoxicity assays.展开更多
Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, a...Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, assuming that the training examples are input in a stochastic way. The monotonicity of the error function in the iteration and the boundedness of the weight are both guaranteed. We also present a numerical experiment to support our results.展开更多
Online gradient methods are widely used for training the weight of neural networks and for other engineering computations. In certain cases, the resulting weight may become very large, causing difficulties in the impl...Online gradient methods are widely used for training the weight of neural networks and for other engineering computations. In certain cases, the resulting weight may become very large, causing difficulties in the implementation of the network by electronic circuits. In this paper we introduce a punishing term into the error function of the training procedure to prevent this situation. The corresponding convergence of the iterative training procedure and the boundedness of the weight sequence are proved. A supporting numerical example is also provided.展开更多
The gradient method for training Elman networks with a finite training sample set is considered. Monotonicity of the error function in the iteration is shown. Weak and strong convergence results are proved, indicating...The gradient method for training Elman networks with a finite training sample set is considered. Monotonicity of the error function in the iteration is shown. Weak and strong convergence results are proved, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively. A numerical example is given to support the theoretical findings.展开更多
In this paper, a gradient method with momentum for sigma-pi-sigma neural networks (SPSNN) is considered in order to accelerate the convergence of the learning procedure for the network weights. The momentum coefficien...In this paper, a gradient method with momentum for sigma-pi-sigma neural networks (SPSNN) is considered in order to accelerate the convergence of the learning procedure for the network weights. The momentum coefficient is chosen in an adaptive manner, and the corresponding weak convergence and strong convergence results are proved.展开更多
A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF ...A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.展开更多
As weapon system effectiveness is affected by many factors,its evaluation is essentially a multi-criterion decision making problem for its complexity.The evaluation model of the effectiveness is established on the bas...As weapon system effectiveness is affected by many factors,its evaluation is essentially a multi-criterion decision making problem for its complexity.The evaluation model of the effectiveness is established on the basis of metrics architecture of the effectiveness.The Bayesian network,which is used to evaluate the effectiveness,is established based on the metrics architecture and the evaluation models.For getting the weights of the metrics by Bayesian network,subjective initial values of the weights are given,gradient ascent algorithm is adopted,and the reasonable values of the weights are achieved.And then the effectiveness of every weapon system project is gained.The weapon system,whose effectiveness is relative maximum,is the optimization system.The research result shows that this method can solve the problem of AHP method which evaluation results are not compatible to the practice results and overcome the shortcoming of neural network in multilayer and multi-criterion decision.The method offers a new approach for evaluating the effectiveness.展开更多
＂ A method is proposed to estimate the longitudinal road gradient with a concept ＂general gradient force （GGF）＂, in which uncertain factors such as additional vertical load, road surface change, and strong wind a...＂ A method is proposed to estimate the longitudinal road gradient with a concept ＂general gradient force （GGF）＂, in which uncertain factors such as additional vertical load, road surface change, and strong wind are also taken into account. An adaptive downhill shift control system is then developed to help driver to use the engine brake with lower gears while downhill driving. In the adaptive system, a three-layer neural network is built to evaluate the necessity to make use of engine brake capability in current downhill situation, and the neural network is trained with samples from experienced drivers. Field test results of the adaptive system are introduced to verify the effectiveness of the approach mentioned above.展开更多
Interpenetrating polymer network (IPN), gradient IPN and BaTiO3 filled IPN, composed of poly(ethylene glycol urethane) (PEGPU) and unsaturated polyester resin (UP) curing at room temperatures were prepared. Then the e...Interpenetrating polymer network (IPN), gradient IPN and BaTiO3 filled IPN, composed of poly(ethylene glycol urethane) (PEGPU) and unsaturated polyester resin (UP) curing at room temperatures were prepared. Then the effect of soft/hard segment ratio in polyurethane (PU), component ratio of PU to UP in IPN, adding amount of BaTiO3 in filled IPN, the component sequences and interval times between each IPN for gradient IPN, on morphology and mechanical behavior of IPN and BaTiO3/IPN nanocomposites with different molecular weight of PU were studied systematically. Moreover, the investigation on the relationship between the morphologies and the mechanical properties indicated that the IPN with finer morphology exhibited an excellent consistency of the higher strengths and elongations.展开更多
Enumerating the relative proportions of soil losses due to rill erosion processes during monsoon and post-monsoon season is a significant factor in predicting total soil losses and sediment transport and deposition. P...Enumerating the relative proportions of soil losses due to rill erosion processes during monsoon and post-monsoon season is a significant factor in predicting total soil losses and sediment transport and deposition. Present study evaluated the rill network with simulated experiment of treatments on varying slope and rainfall intensity to find out the rill erosion processes and sediment discharge in relation to slope and rainfall intensity. Results showed a significant relationship between the rainfall intensity and sediment yield (r = 0.75). Our results illustrated that due to increase in rainfall intensity represent the development of efficient rill network while, no rill was found with a slope of 20° and a rainfall intensity of 60 mm·h-1. The highest rill length was observed in plot E with 20° slope and 120 mm·h-1 rainfall intensity at 360 minutes. Positive and strong correlation (R2 = 0.734, P 0.001) was observed between the cumulative rainfall intensity and sediment discharge. A longitudinal profile was delineated and showed that the depth and numbers of depressions amplified with time and were more prominent for escalating rainfall intensity for its steeper slopes. Information derived from the study could be applied to estimate longer-term erosion stirring over larger areas possessing parallel landforms.展开更多
Documenting the recovery of hydrologic functions following perturbations of a landscape/watershed is important to address issues associated with land use change and ecosystem restoration. High resolution LiDAR data fo...Documenting the recovery of hydrologic functions following perturbations of a landscape/watershed is important to address issues associated with land use change and ecosystem restoration. High resolution LiDAR data for the USDAForestServiceSanteeExperimentalForestin coastalSouth Carolina,USAwas used to delineate the remnant historical water management structures within the watersheds supporting bottomland hardwood forests that are typical of the re- gion. Hydrologic functions were altered during the early1700’s agricultural use period for rice cultivation, with changes to detention storage, impoundments, and runoff routing. Since late1800’s, the land was left to revert to forests, without direct intervention. The resultant bottomlands, while typical in terms of vegetative structure and composition, still have altered hydrologic pathways and functions due to the historical land use. Furthermore, an accurate estimate of the watershed drainage area (DA) contributing to stream flow is critical for reliable estimates of peak flow rate, runoff depth and coefficient, as well as water and chemical balance. Peak flow rate, a parameter widely used in design of channels and cross drainage structures, is calculated as a function of the DA and other parameters. However, in contrast with the upland watersheds, currently available topographic maps and digital elevation models (DEMs) used to estimate the DA are not adequate for flat, low-gradient Coastal Plain (LCP) landscape. In this paper we explore a case study of a 3rd order watershed (equivalent to 14-digit hydrologic unit code (HUC)) at headwaters of east branch of Cooper River draining to Charleston Harbor, SC to assess the drainage area and corresponding mean annual runoff coefficient based on various DEMs including LiDAR data. These analyses demonstrate a need for application of LiDAR-based DEMs together with field verification to improve the basis for assessments of hydrology, watershed drainage characteristics, and modeling in the LCP.展开更多
基金Supported by the National Natural Science Foundation of China(81372358,81527801,51303140,and 81602489)the Natural Science Foundation of Hubei Province(2014CFA029)+1 种基金the Colleges of Hubei Province Outstanding Youth Science and Technology Innovation Team(T201305)the Applied Foundational Research Program of Wuhan Municipal Science and Technology Bureau(2015060101010056)
文摘This paper describes a simple method of generating concentration gradients with linear and parabolic profiles by using a Christmas tree-shaped microfluidic network.The microfluidic gradient generator consists of two parts：a Christmas tree-shaped network for gradient generation and a broad microchannel for detection.A two-dimensional model was built to analyze the flow field and the mass transfer in the microfluidic network.The simulating results show that a series of linear and parabolic gradient profiles were generated via adjusting relative flow rate ratios of the two source solutions（R_L^2≥0.995 and _PR^2≥0.999）,which could match well with the experimental results（R_L^2≥0.987 and _PR^2≥0.996）.The proposed method is promising for the generation of linear and parabolic concentration gradient profiles,with the potential in chemical and biological applications such as combinatorial chemistry synthesis,stem cell differentiation or cytotoxicity assays.
基金Partly supported by the National Natural Science Foundation of China,and the Basic Research Program of the Committee of ScienceTechnology and Industry of National Defense of China.
文摘Online gradient algorithm has been widely used as a learning algorithm for feedforward neural network training. In this paper, we prove a weak convergence theorem of an online gradient algorithm with a penalty term, assuming that the training examples are input in a stochastic way. The monotonicity of the error function in the iteration and the boundedness of the weight are both guaranteed. We also present a numerical experiment to support our results.
文摘Online gradient methods are widely used for training the weight of neural networks and for other engineering computations. In certain cases, the resulting weight may become very large, causing difficulties in the implementation of the network by electronic circuits. In this paper we introduce a punishing term into the error function of the training procedure to prevent this situation. The corresponding convergence of the iterative training procedure and the boundedness of the weight sequence are proved. A supporting numerical example is also provided.
基金the National Natural Science Foundation of China (No.10471017)
文摘The gradient method for training Elman networks with a finite training sample set is considered. Monotonicity of the error function in the iteration is shown. Weak and strong convergence results are proved, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively. A numerical example is given to support the theoretical findings.
文摘In this paper, a gradient method with momentum for sigma-pi-sigma neural networks (SPSNN) is considered in order to accelerate the convergence of the learning procedure for the network weights. The momentum coefficient is chosen in an adaptive manner, and the corresponding weak convergence and strong convergence results are proved.
基金Projects(60974031,60704011,61174128)supported by the National Natural Science Foundation of China
文摘A self-organizing radial basis function(RBF) neural network(SODM-RBFNN) was presented for predicting the production yields and operating optimization. Gradient descent algorithm was used to optimize the widths of RBF neural network with the initial parameters obtained by k-means learning method. During the iteration procedure of the algorithm, the centers of the neural network were optimized by using the gradient method with these optimized width values. The computational efficiency was maintained by using the multi-threading technique. SODM-RBFNN consists of two RBF neural network models: one is a running model used to predict the product yields of fluid catalytic cracking unit(FCCU) and optimize its operating parameters; the other is a learning model applied to construct or correct a RBF neural network. The running model can be updated by the learning model according to an accuracy criterion. The simulation results of a five-lump kinetic model exhibit its accuracy and generalization capabilities, and practical application in FCCU illustrates its effectiveness.
文摘As weapon system effectiveness is affected by many factors,its evaluation is essentially a multi-criterion decision making problem for its complexity.The evaluation model of the effectiveness is established on the basis of metrics architecture of the effectiveness.The Bayesian network,which is used to evaluate the effectiveness,is established based on the metrics architecture and the evaluation models.For getting the weights of the metrics by Bayesian network,subjective initial values of the weights are given,gradient ascent algorithm is adopted,and the reasonable values of the weights are achieved.And then the effectiveness of every weapon system project is gained.The weapon system,whose effectiveness is relative maximum,is the optimization system.The research result shows that this method can solve the problem of AHP method which evaluation results are not compatible to the practice results and overcome the shortcoming of neural network in multilayer and multi-criterion decision.The method offers a new approach for evaluating the effectiveness.
文摘＂ A method is proposed to estimate the longitudinal road gradient with a concept ＂general gradient force （GGF）＂, in which uncertain factors such as additional vertical load, road surface change, and strong wind are also taken into account. An adaptive downhill shift control system is then developed to help driver to use the engine brake with lower gears while downhill driving. In the adaptive system, a three-layer neural network is built to evaluate the necessity to make use of engine brake capability in current downhill situation, and the neural network is trained with samples from experienced drivers. Field test results of the adaptive system are introduced to verify the effectiveness of the approach mentioned above.
文摘Interpenetrating polymer network (IPN), gradient IPN and BaTiO3 filled IPN, composed of poly(ethylene glycol urethane) (PEGPU) and unsaturated polyester resin (UP) curing at room temperatures were prepared. Then the effect of soft/hard segment ratio in polyurethane (PU), component ratio of PU to UP in IPN, adding amount of BaTiO3 in filled IPN, the component sequences and interval times between each IPN for gradient IPN, on morphology and mechanical behavior of IPN and BaTiO3/IPN nanocomposites with different molecular weight of PU were studied systematically. Moreover, the investigation on the relationship between the morphologies and the mechanical properties indicated that the IPN with finer morphology exhibited an excellent consistency of the higher strengths and elongations.
文摘Enumerating the relative proportions of soil losses due to rill erosion processes during monsoon and post-monsoon season is a significant factor in predicting total soil losses and sediment transport and deposition. Present study evaluated the rill network with simulated experiment of treatments on varying slope and rainfall intensity to find out the rill erosion processes and sediment discharge in relation to slope and rainfall intensity. Results showed a significant relationship between the rainfall intensity and sediment yield (r = 0.75). Our results illustrated that due to increase in rainfall intensity represent the development of efficient rill network while, no rill was found with a slope of 20° and a rainfall intensity of 60 mm·h-1. The highest rill length was observed in plot E with 20° slope and 120 mm·h-1 rainfall intensity at 360 minutes. Positive and strong correlation (R2 = 0.734, P 0.001) was observed between the cumulative rainfall intensity and sediment discharge. A longitudinal profile was delineated and showed that the depth and numbers of depressions amplified with time and were more prominent for escalating rainfall intensity for its steeper slopes. Information derived from the study could be applied to estimate longer-term erosion stirring over larger areas possessing parallel landforms.
文摘Documenting the recovery of hydrologic functions following perturbations of a landscape/watershed is important to address issues associated with land use change and ecosystem restoration. High resolution LiDAR data for the USDAForestServiceSanteeExperimentalForestin coastalSouth Carolina,USAwas used to delineate the remnant historical water management structures within the watersheds supporting bottomland hardwood forests that are typical of the re- gion. Hydrologic functions were altered during the early1700’s agricultural use period for rice cultivation, with changes to detention storage, impoundments, and runoff routing. Since late1800’s, the land was left to revert to forests, without direct intervention. The resultant bottomlands, while typical in terms of vegetative structure and composition, still have altered hydrologic pathways and functions due to the historical land use. Furthermore, an accurate estimate of the watershed drainage area (DA) contributing to stream flow is critical for reliable estimates of peak flow rate, runoff depth and coefficient, as well as water and chemical balance. Peak flow rate, a parameter widely used in design of channels and cross drainage structures, is calculated as a function of the DA and other parameters. However, in contrast with the upland watersheds, currently available topographic maps and digital elevation models (DEMs) used to estimate the DA are not adequate for flat, low-gradient Coastal Plain (LCP) landscape. In this paper we explore a case study of a 3rd order watershed (equivalent to 14-digit hydrologic unit code (HUC)) at headwaters of east branch of Cooper River draining to Charleston Harbor, SC to assess the drainage area and corresponding mean annual runoff coefficient based on various DEMs including LiDAR data. These analyses demonstrate a need for application of LiDAR-based DEMs together with field verification to improve the basis for assessments of hydrology, watershed drainage characteristics, and modeling in the LCP.
