Effectiveness of Different Artificial Neural Network Training Algorithms in Predicting Protozoa Risks in Surface Waters

A neural network approach was employed to relate risky Cryptosporidium and Giardia concentrations with other biological, chemical and physical parameters in surface water. A set of drinking water samples was classified as “risky” and “nonrisky” based on the concentrations of full and empty oocysts, and cycsts of Cryptosporidium and Giardia, respectively. Given the constraints associated with collecting large sets of microbial data, the study was aimed at identifying an effective training algorithm that would maximize the performance of a neural network model working with a relatively small dataset. A number of algorithms for training neural networks, including gradient search with first- and second-order partial derivatives, and genetic search were used and compared. Results showed that genetic algorithm based neural network training consistently provided better results compared to other training methods.     

Adverse effects of tribromoethanol as used in the production of transgenic mice

The authors developed and cross-validated prediction models for newly diagnosed cases of liver disorders by using logistic regression and neural networks. Computerized files of health care encounters from the Fallon Community Health Plan were used to identify 1,674 subjects who had had liver-related health services between July 1, 1992, and June 30, 1993. A total of 219 subjects were confirmed by review of medical records as incident cases. The 1,674 subjects were randomly and evenly divided into training and test sets. The training set was used to derive prediction algorithms based solely on the automated data; the test set was used for cross-validation. The area under the Receiver Operating Characteristic curve for a neural network model was significantly larger than that for logistic regression in the training set (p = 0.04). However, the performance was statistically equivalent in the test set (p = 0.45). Despite its superior performance in the training set, the generalizability of the neural network model is limited. Logistic regression may therefore be preferred over neural network on the basis of its established advantages. More generalizable modeling techniques for neural networks may be necessary before they are practical for medical research.     

基于模糊神经网络的地图匹配算法

提出了基于模糊神经网络的新的地图匹配算法.该算法综合了数字道路信息和GPS/DR定位信息,提取两个重要参数作为输入变量,即定位点到候选路段的投影距离及定位航向与候选路段方位角差.设计出了四层模糊神经网络及改进的收敛学习规则.实验结果表明所提出的算法能很好地匹配车辆行驶路段位置.      

Neural Network Embedded Monte Carlo Approach for Water Quality Modeling under Input Information Uncertainty

This paper proposes a neural network embedded Monte Carlo (NNMC) approach to account for uncertainty in water quality modeling. The framework of the proposed method has three major parts: a numerical water quality model, a neural network technique, and Monte Carlo simulation. The numerical model is used to generate desirable output for training and testing sets, and the neural network is used as a universal functional mapping tool to approximate the input-output response of the numerical model. The Monte Carlo simulation then uses the neural network to generate numerical realizations based on a probabilistic distribution of parameters, thus obtaining a probabilistic distribution of the simulated state variables. By embedding a neural network into the conventional Monte Carlo simulation, the proposed approach significantly improves upon the conventional method in computational efficiency. The proposed approach has been applied to uncertainty and risk analyses of a phosphorus model for Triadelphia Reservoir in Maryland. The results of this research show that the NNMC approach has potential for efficient uncertainty analysis of water quality modeling.     

基于ELM和MCSCKF的锂离子电池SOC估计

为了减少噪声对锂离子电池荷电状态估计的影响,本文提出一种新颖的基于极限学习机和最大相关熵平方根容积卡尔曼滤波的SOC估计方法。首先,利用泛化性好、运行速度快的极限学习机作为卡尔曼滤波的测量方程;其次,基于灰狼优化算法,极限学习机的超参数被优化以提高电池荷电状态的估计精度;最后,基于最大相关熵平方根容积卡尔曼滤波,极限学习机的测量噪声被进一步减弱。所提方法可以简化极限学习机繁琐的调参过程,且为闭环的SOC估计方法。所提方法在多工况和宽温度范围内被测试以验证其泛化性能。测试结果显示,所提方法明显地提高了锂离子电池的荷电状态估计精度。同时,对比其他算法,所提方法的平均运行时间仅仅为长短时序列和循环门控单元网络的三分之一。当行驶工况复杂、温度变化区间较大时,所提方法的均方根误差小于1%,最大误差小于3%。当存在初始误差与环境噪声时,所提方法显示出了优越的鲁棒性。      

Hidden neural networks

A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear performance gains compared to standard HMMs tested on the same task.     

Parameter Estimation in Groundwater Hydrology Using Artificial Neural Networks

The capability of artificial neural networks to act as universal function approximators has been traditionally used to model problems in which the relation between dependent and independent variables is poorly understood. In this paper, the capability of an artificial neural network to provide a data-driven approximation of the explicit relation between transmissivity and hydraulic head as described by the groundwater flow equation is demonstrated. Techniques are applied to determine the optimal number of nodes and training patterns needed for a neural network to approximate groundwater parameters for a simulated groundwater modeling case study. Furthermore, the paper explains how such an approximation can be used for the purpose of parameter estimation in groundwater hydrology.     

Extended Kalman Filter-Based Pruning Method for Recurrent Neural Networks

Pruning is one of the effective techniques for improving the generalization error of neural networks. Existing pruning techniques are derived mainly from the viewpoint of energy minimization, which is commonly used in gradient-based learning methods. In recurrent networks, extended Kalman filter (EKF)-based training has been shown to be superior to gradient-based learning methods in terms of speed. This article explains a pruning procedure for recurrent neural networks using EKF training. The sensitivity of a posterior probability is used as a measure of the importance of a weight instead of error sensitivity since posterior probability density is readily obtained from this training method. The pruning procedure is tested using three problems: (1) the prediction of a simple linear time series, (2) the identification of a nonlinear system, and (3) the prediction of an exchange-rate time series. Simulation results demonstrate that the proposed pruning method is able to reduce the number of parameters and improve the generalization ability of a recurrent network.     

General Approach for Training Back-Propagation Neural Networks in Vibration Control of Multidegree-of-Freedom Structures

A general approach is proposed for back-propagation training of multilayer feed-forward (MLFF) neural networks for active control of earthquake-induced vibrations in multidegree-of-freedom structures. The training functions for adjustment of connection weights of the neural network controller are formulated in the proposed approach by minimizing a general cost function using the steepest gradient descent scheme. The proposed method can be applied for training an MLFF neural network controller in vibration control of building structures both in the pattern (online) and batch (off-line) mode. The method can be implemented in structural control systems with more than one control action. Case studies are presented to demonstrate the feasibility of implementing the training approach for effective vibration control of structures subjected to earthquake ground motions.     

回声状态网络的研究进展

回声状态网络是近年来新兴的一种递归神经网络,独特而简单的训练方式以及高精度的训练结果已使其成为当前研究的热点之一.在该网络中,引入了储备池计算模式这一新的神经网络的建设方案,克服了之前网络模型基于梯度下降的学习算法所难以避免的收敛慢和容易陷入局部极小等问题.围绕这种新型网络结构,国内外许多学者开展了多样的研究.本文全面深入介绍了回声状态网络这一新兴技术,讨论了回声状态网络的优缺点,并综合近年的研究现状,总结了回声状态网络的主要研究工作进展和未来的研究方向.      

Prediction of Scour Downstream of Grade-Control Structures Using Neural Networks

A new approach for predicting local scour downstream of grade-control structures based on neural networks is presented. An explicit neural networks formulation (ENNF) is developed using a transfer function (sigmoid) and optimal weights obtained from a training process. A genetic algorithm was used to optimize the neural network architecture and the optimal weights for input and output parameters were obtained using the Levenberg–Marquardt back-propagation algorithm. Experimental data available in the literature, including large-scale results were used for training and validation of the proposed model. The predictive performance of the ENNF was found superior to other regression-based equations and the robustness of ENNF was evaluated using field data.     

基于进化策略调节参数的回归支持向量机及其在铁水脱硫中的应用

在回归支持向量机的建模中,参数调节问题一直是影响模型性能的重要因素之一。本文提出了一种基于进化策略的参数选择的新方法,并将它应用于铁水脱硫过程的建模上以预测铁水中的最终含硫量,其预测结果比神经网络的预测结果有一定改进。理论分析和应用结果表明,该方法是一种快速、简单、有效的调参方法。     

Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach

Flexible modelling in survival analysis can be useful both for exploratory and predictive purposes. Feed forward neural networks were recently considered for flexible non-linear modelling of censored survival data through the generalization of both discrete and continuous time models. We show that by treating the time interval as an input variable in a standard feed forward network with logistic activation and entropy error function, it is possible to estimate smoothed discrete hazards as conditional probabilities of failure. We considered an easily implementable approach with a fast selection criteria of the best configurations. Examples on data sets from two clinical trials are provided. The proposed artificial neural network (ANN) approach can be applied for the estimation of the functional relationships between covariates and time in survival data to improve model predictivity in the presence of complex prognostic relationships.     

Genetic Programming to Predict Bridge Pier Scour

Bridge-pier scour is a significant problem for the safety of bridges. Extensive laboratory and field studies have been conducted examining the effect of relevant variables. This note presents an alternative to the conventional regression-based equations (HEC-18 and regression equation developed by the writers), in the form of artificial neural networks (ANNs) and genetic programming (GP). There had been 398 data sets of field measurements that were collected from published literature and were used to train the network or evolve the program. The developed network and evolved programs were validated by using the observations that were not involved in the training. The performance of GP was found more effective when compared to regression equations and ANNs in predicting the scour depth at bridge piers.     

基于模糊聚类的BP神经网络模型预报中厚板轧制力

以实测数据为基础,在中厚板轧制设定中采用BP神经网络的方法取代传统的轧制力数学模型,并对神经网络输入项和训练样本进行分析,将传统轧制力模型的自学习过程引入神经元网络用于轧制力预报,改善预报精度.采用模糊聚类分析方法,科学选取学习样本,解决了由于样本多学习速度慢的问题.通过在线数据分析,可知这种方法对轧制力的预报精度有很大改善,而且神经元网络的结构也得到简化.此方法可以作为神经元网络应用的一个拓展.     

Intelligent Multivariable Modeling of Blast Furnace Molten Iron Quality Based on Dynamic AGA-ANN and PCA

Blast furnace(BF)ironmaking process has complex and nonlinear dynamic characteristics.The molten iron temperature(MIT)as well as Si,P and S contents of molten iron is difficult to be directly measured online,and large-time delay exists in offline analysis through laboratory sampling.A nonlinear multivariate intelligent modeling method was proposed for molten iron quality(MIQ)based on principal component analysis(PCA)and dynamic genetic neural network.The modeling method used the practical data processed by PCA dimension reduction as inputs of the dynamic artificial neural network(ANN).A dynamic feedback link was introduced to produce a dynamic neural network on the basis of traditional back propagation ANN.The proposed model improved the dynamic adaptability of networks and solved the strong fluctuation and resistance problem in a nonlinear dynamic system.Moreover,a new hybrid training method was presented where adaptive genetic algorithms(AGA)and ANN were integrated,which could improve network convergence speed and avoid network into local minima.The proposed method made it easier for operators to understand the inside status of blast furnace and offered real-time and reliable feedback information for realizing close-loop control for MIQ.Industrial experiments were made through the proposed model based on data collected from a practical steel company.The accuracy could meet the requirements of actual operation.     

Prediction of partition coefficient based on atom-type electrotopological state indices

The aim of this study was to determine the efficacy of atom-type electrotopological state indices for estimation of the octanol-water partition coefficient (log P) values in a set of 345 drug compounds or related complex chemical structures. Multilinear regression analysis and artificial neural networks were used to construct models based on molecular weights and atom-type electrotopological state indices. Both multilinear regression and artificial neural networks provide reliable log P estimations. For the same set of parameters, application of neural networks provided better prediction ability for training and test sets. The present study indicates that atom-type electrotopological state indices offer valuable parameters for fast evaluation of octanol-water partition coefficients that can be applied to screen large databases of chemical compounds, such as combinatorial libraries.     

A comparative study of artificial neural networks for the prediction of constitutive behaviour of HSLA and carbon steels

Backpropagation neural networks are utilized to store and predict the flow stresses of several steels. A convergence algorithm using a varying learning factor is developed which is shown to save one sixth of the learning time when compared with the algorithm in which a constant learning factor is utilized. A performance test shows that the well-trained neural network can interpolate flow stresses very well if the information for interpolation is sufficient in the training pairs. The capability of the network to extrapolate is found not to be impressive. The neural network can handle several groups of data during adaptive learning simultaneously without losing accuracy. The time needed for adaptive learning to reach a reasonable level of accuracy is short. Comparing the predicted results to other models, the output of neural network is shown to have the highest accuracy.