Simplified neural network for generalized least absolute deviation

This paper proposes a simplified neural network for generalized least absolute deviation by transforming its optimization conditions into a system of double projection equations. The proposed network is proved to be stable in the sense of Lyapunov and converges to an exact optimization solution of the original problem for any starting point. Compared with the existing neural networks for generalized least absolute deviation, the new model has the least neurons and low complexity and is suitable to parallel implementation. The validity and transient behavior of the proposed neural network are demonstrated by numerical examples.

     

The prediction of SO2 removal using statistical methods and artificial neural network

Artificial neural network and a statistical model have been applied in a laboratory scale trickle bed reactor (TBR) to investigate the SO₂ removal efficiency of activated carbon. The performance of artificial neural network (ANN) model has been compared with the statistical model based on central composite experimental design. Two independent variables, which affect the amount of SO₂ removal by the liquid phase in the TBR, were selected; namely liquid flow rate and gas flow rate. Amount of SO₂ removal was chosen as the dependent variable (target data). A second order statistical model has been considered to show the dependence of the amount of SO₂ removal on the operating parameters. A back-propagation ANN has been used to develop a model relating to the amount of SO₂ removal. A series of experiments have been conducted on the basis of the statistics-based design of experimental method. It is observed that a neural network architecture having one input layer with two neurons, one hidden layer with three neurons, one output layer with one neuron and an epoch size of 20 gives better prediction. The predictions are more accurate than those obtained from regression models.     

An artificial neural network for prediction of gas holdup in bubble columns with oily solutions

Gas holdup in a bubble column reactor filled with oil-based liquids was estimated by an artificial neural network (ANN). The ANN was trained using experimental data from the literature with various sparger pore diameters and a bubbly flow regime. The trained ANN was able to predict that the gas holdup of data did not seen during the training period over the studied range of physical properties, operating conditions, and sparger pore diameter with average normalized square error <0.05. Comparisons of the neural network predictions to correlations obtained from experimental data show that the neural network was properly designed and could powerfully estimate gas holdup in bubble column with oily solutions.     

Approximating support vector machine with artificial neural network for fast prediction

Support vector machine (SVM) is a powerful algorithm for classification and regression problems and is widely applied to real-world applications. However, its high computational load in the test phase makes it difficult to use in practice. In this paper, we propose hybrid neural network (HNN), a method to accelerate an SVM in the test phase by approximating the SVM. The proposed method approximates the SVM using an artificial neural network (ANN). The resulting regression function of the ANN replaces the decision function or the regression function of the SVM. Since the prediction of the ANN requires significantly less computation than that of the SVM, the proposed method yields faster test speed. The proposed method is evaluated by experiments on real-world benchmark datasets. Experimental results show that the proposed method successfully accelerates SVM in the test phase with little or no prediction loss.     

用于电磁兼容预测的自适应泛化回归神经网络

为了更好地对电磁兼容进行预测,提出一种自适应泛化回归神经网络（AGRNN）,与传统泛化回归神经网络（GRNN）区别在于：将光滑因子设为最小数据距离的1/2,将偏置设为光滑因子的倒数。对简单一维数据的测试表明,无论数据如何分布,AGRNN的拟合曲线均较GRNN更加接近样本点、且更平滑。以平行线间电磁耦合干扰为具体算例,证明AGRNN对训练数据与测试数据的预测优于改进BP算法,且网络不需要训练。     

人工神经网络在成矿预测中的应用

成矿预测正从定性描述性预测向定量成矿预测转变,数理统计方法和技术逐渐引入地学研究。传统统计方法多假想包含地学现象的空间为均质,假定在一个尺度上的地学关系在另一个尺度上也是相同的,而在实际应用中这样的地质条件是不可能存在的。而非线性科学正具有不满足线性叠加原理的性质,因此将非线性科学如人工神经网络与成矿预测相结合是未来矿产资源预测的发展方向。采用Kohonen聚类模型和BP预测模型相结合的方法,对包古图金矿区1 444个矿点的地球化学数据进行聚类分析并建立成矿预测模型,预测正确率为85.2%。该方法性能良好,具有一定的实际意义,为解决成矿预测提供了一种新的手段。     

BP神经网络用于预测多参数关联变压器油的性能

基于变压器油性能参数之间的关联性,采用BP神经网络方法,在Matlab平台下研究预测多参数关联变压器油的性能,利用变压器油日常的监测数据,建立击穿电压与4个影响因素的关联模型.论文分别就常规BP算法和变学习速率、变动量因子的改进BP算法进行了比较研究,结果表明,改进BP算法模型的预测结果精度较高,预测值与实际值的相对误差在5%左右.本方法可以为变压器故障的早期诊断、预测防范和及时处理提供科学依据,具有重要的实际应用价值.     

Comparison of artificial neural network and regression models for estimating software development effort

Estimating the amount of effort required for developing an information system is an important project management concern. In recent years, a number of studies have used neural networks in various stages of software development. This study compares the prediction performance of multilayer perceptron and radial basis function neural networks to that of regression analysis. The results of the study indicate that when a combined third generation and fourth generation languages data set were used, the neural network produced improved performance over conventional regression analysis in terms of mean absolute percentage error.     

Performance comparison of artificial neural network models for daily rainfall prediction

With an aim to predict rainfall one-day in advance, this paper adopted different neural network models such as feed forward back propagation neural network (BPN), cascade-forward back propagation neural network (CBPN), distributed time delay neural network (DTDNN) and nonlinear autoregressive exogenous network (NARX), and compared their forecasting capabilities. The study deals with two data sets, one containing daily rainfall, temperature and humidity data of Nilgiris and the other containing only daily rainfall data from 14 rain gauge stations located in and around Coonoor (a taluk of Nilgiris). Based on the performance analysis, NARX network outperformed all the other networks. Though there is no major difference in the performances of BPN, CBPN and DTDNN, yet BPN performed considerably well confirming its prediction capabilities. Levenberg Marquardt proved to be the most effective weight updating technique when compared to different gradient descent approaches. Sensitivity analysis was instrumental in identifying the key predictors.     

The prediction of meteorological variables using artificial neural network

Artificial neural network model had been implemented in different areas such as industrial processes, sciences, and business. In these days, climatic changes have occurred. In this study, meteorological variables are predicted using ANN model. The experimental values are obtained from the Turkish Meteorological Center for different measurement stations. The prediction of the meteorological values are realized, when the neural network model have been trained and tested. Obtained results show that the difference between estimated and measured values is very low. The neural network models for prediction are successfully applied to the meteorological variables.     

Emergence of adaptive behaviors for artificial creature using a combined artificial neural network

This study proposes a method to acquire adaptive behavior for artificial creature which has a lot of joints using a combined Artificial Neural Network (ANN). Experiment in this study focuses on artificial fish model, which has a lot of joints, tracking towards a target in the virtual water environment. In order to control motions of joints, a combined ANN is implemented with the model. At first, one ANN is prepared to control specific joints so as to swim basically in response to minimal input information using evolutionary computation in preliminary experiments. And an new network is constructed by combining its network and the other network. In order to acquire complicate behavior for artificial creature, weights of combined ANN are optimized. Experiment result shows the model which has many joints acquire adaptive swimming behavior towards a target by optimizing combined network.     

互感器故障诊断人工神经网络法

基于神经网络的基本结构和算法，该文建立了一个用于高压电磁式互感器故障诊断的人工神经网络。其中采用了有效的网络学习算法，旨在全面、快速和准确地实现互感器故障诊断，以提高互感器及电力系统运行的可靠性。根据互感器的故障特征，该文建立一个3层前向神经网络，采用误差逆传播学习算法进行了讨论，并由仿真计算结果加以论证。     

Comparison of regression and artificial neural network model for the prediction of springback during air bending process of interstitial free steel sheet

This paper compares the regression and neural network modeling for predicting springback of interstial free steel sheet during air bending process. In this investigation, punch travel, strain hardening exponent, punch radius, punch velocity and width of the sheet were considered as input variables and springback as response variable. It has been observed that the ANN modeling process has been able to predict the springback with higher accuracy when compared with regression model.     

An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring

Accurate equipment remaining useful life prediction is critical to effective condition based maintenance for improving reliability and reducing overall maintenance cost. In this paper, an artificial neural network (ANN) based method is developed for achieving more accurate remaining useful life prediction of equipment subject to condition monitoring. The ANN model takes the age and multiple condition monitoring measurement values at the present and previous inspection points as the inputs, and the life percentage as the output. A function generalized from the Weibull failure rate function is used to fit each condition monitoring measurement series for a failure history, and the fitted measurement values are used to form the ANN training set so as to reduce the effects of the noise factors that are irrelevant to the equipment degradation. A validation mechanism is introduced in the ANN training process to improve the prediction performance of the ANN model. The proposed ANN method is validated using real-world vibration monitoring data collected from pump bearings in the field. A comparative study is performed between the proposed ANN method and an adapted version of a reported method, and the results demonstrate the advantage of the proposed method in achieving more accurate remaining useful life prediction.     

Efficient prediction of exchange rates with low complexity artificial neural network models

In recent years forecasting of financial data such as interest rate, exchange rate, stock market and bankruptcy has been observed to be a potential field of research due to its importance in financial and managerial decision making. Survey of existing literature reveals that there is a need to develop efficient forecasting models involving less computational load and fast forecasting capability. The present paper aims to fulfill this objective by developing two novel ANN models involving nonlinear inputs and simple ANN structure with one or two neurons. These are: functional link artificial neural network (FLANN) and cascaded functional link artificial neural network (CFLANN). These have been employed to predict currency exchange rate between US$ to British Pound, Indian Rupees and Japanese Yen. The performance of the proposed models have been evaluated through simulation and have been compared with those obtained from standard LMS based forecasting model. It is observed that the CFLANN model performs the best followed by the FLANN and the LMS models.     

Stability evaluation of dump slope using artificial neural network and multiple regression

The present study mainly investigates the effect of the residual surface stress and the applied electric voltage on the nonlinear dynamic instability of the viscoelastic piezoelectric nanoresonators under parametric excitation. In fact, great attention is given to the influence of the residual surface stress on the nonlinear instability of the system. Numerical examples are treated which show various bifurcations. By means of a bifurcation analysis, it is shown that the instability of the system can be significantly affected by considering the residual surface effect. The results also show that a discontinuous bifurcation is always accompanied by a jump. Finally, stable and unstable regions in dynamic instability of viscoelastic piezoelectric nanoplates are addressed.

     

基于决策树算法确定一个最小神经网络

神经网络隐层神经元的个数对于网络的性能有着重要的影响,通常情况下,对于一个特定问题来说,没有一个确定的方法来决定隐含层到底应该有多少个神经元,一般采用试探的方法通过多次实验来达到理想效果.在分类问题中,决策树和神经网络的结构有着一定的关联性,通过把决策树映射到神经网络结构中来确定隐层神经元的个数的方法能够有效地设计神经网络的结构,从而提高训练的效率并达到良好的分类效果.实验结果表明,该方法能够得到一个有着良好识别率的最小神经网络.方法简单有效,直观且易于操作.     

Backbreak prediction in the Chadormalu iron mine using artificial neural network

Backbreak is one of the unfavorable blasting results, which can be defined as the unwanted rock breakage behind the last row of blast holes. Blast pattern parameters, like stemming, burden, delay timing, stiffness ratio (bench height/burden) and rock mass conditions (e.g., geo-mechanical properties and joints), are effective in backbreak intensity. Till date, with the exception of some qualitative guidelines, no specific method has been developed for predicting the phenomenon. In this paper, an effort has been made to apply artificial neural networks (ANNs) for predicting backbreak in the blasting operation of the Chadormalu iron mine (Iran). Number of ANN models with different hidden layers and neurons were tried, and it was found that a network with architecture 10-7-7-1 is the optimum model. A comparative study also approved the superiority of the ANN modeling over the conventional regression analysis. Mean square error (MSE), variance account for (VAF) and coefficient of determination (R ²) between measured and predicted backbreak for the ANN model were calculated and found 89.46 %, 0.714 and 90.02 %, respectively. Also, for the regression model, MSE, VAF and R ² were computed and found 66.93 %, 1.46 and 68.10 %, respectively. Sensitivity analysis was also carried out to find out the influence of each input parameter on backbreak results, and it was revealed that burden is the most influencing parameter on the backbreak, whereas water content is the least effective parameter in this regard.     

An innovative neural network approach for stock market prediction

The Journal of Supercomputing - This paper aims to develop an innovative neural network approach to achieve better stock market predictions. Data were obtained from the live stock market for...