Neural networks of data inhibiting long memory pattern

We experiment with three neural network models for forecasting to better understand the performance of neural networks for the case when the data exhibits a long memory pattern. To obtain the optimum networks, the effect of network characteristics such as the training parameters, the number of hidden layers, and the testing and training percentages are simulated. The third model, which consists of a combination of individual time series forecasts, provides superior results.     

An investigation of neural networks for linear time-series forecasting

This study examines the capability of neural networks for linear time-series forecasting. Using both simulated and real data, the effects of neural network factors such as the number of input nodes and the number of hidden nodes as well as the training sample size are investigated. Results show that neural networks are quite competent in modeling and forecasting linear time series in a variety of situations and simple neural network structures are often effective in modeling and forecasting linear time series.Scope and purposeNeural network capability for nonlinear modeling and forecasting has been established in the literature both theoretically and empirically. The purpose of this paper is to investigate the effectiveness of neural networks for linear time-series analysis and forecasting. Several research studies on neural network capability for linear problems in regression and classification have yielded mixed findings. This study aims to provide further evidence on the effectiveness of neural network with regard to linear time-series forecasting. The significance of the study is that it is often difficult in reality to determine whether the underlying data generating process is linear or nonlinear. If neural networks can compete with traditional forecasting models for linear data with noise, they can be used in even broader situations for forecasting researchers and practitioners.     

A regime-switching recurrent neural network model applied to wind time series

This paper proposes a regime-switching recurrent network model (RS-RNN) for non-stationary time series. The RS-RNN model emits a mixture density with dynamic nonlinear regimes that fit flexibly data distributions with non-Gaussian shapes. The key novelties are: development of an original representation of the means of the component distributions by dynamic nonlinear recurrent networks, and derivation of a corresponding expectation maximization (EM) training algorithm for finding the model parameters. The results show that the RS-RNN applied to a real-world wind speed time series achieves standardized residuals similar to popular previous models, but it is more accurate distribution forecasting than other linear switching (MS-AR) and nonlinear neural network (MLP and RNN) models.     

基于递归神经网络的风暴潮增水预测

风暴潮增水的准确预测能极大地减少人员伤害和经济损失,具有重要的实用价值。传统的风暴潮预报方法主要包括经验和数值预报,很难建立起相对准确的模型。现有的基于机器学习风暴潮预报方法大都只提取出静态数据间的关系,并没有充分挖掘出风暴潮数据背后的时序关联特性。文中提出了一种基于递归神经网络的风暴潮增水预测方法。本文对风暴潮时序数据进行特定的处理,并设计合适结构的递归神经网络,从而完成时序数据的预测。相较于传统的BP神经网络,递归神经网络能更好地应对时序数据的预测问题。将该方法用于潍坊水站的增水预测中,结果表明,相对于BP神经网络,递归神经网络能得到更好的预测结果,误差更小。     

Short‐term electric power load forecasting based on cosine radial basis function neural networks: An experimental evaluation

This article presents the results of a study aimed at the development of a system for short‐term electric power load forecasting. This was attempted by training feedforward neural networks (FFNNs) and cosine radial basis function (RBF) neural networks to predict future power demand based on past power load data and weather conditions. This study indicates that both neural network models exhibit comparable performance when tested on the training data but cosine RBF neural networks generalize better since they outperform considerably FFNNs when tested on the testing data. © 2005 Wiley Periodicals, Inc. Int J Int Syst 20: 591–605, 2005.     

Hybridization of the probabilistic neural networks with feed-forward neural networks for forecasting

Feed-forward neural networks (FFNNs) are among the most important neural networks that can be applied to a wide range of forecasting problems with a high degree of accuracy. Several large-scale forecasting competitions with a large number of commonly used time series forecasting models conclude that combining forecasts from more than one model often leads to improved performance, especially when the models in the ensemble are quite different. In the literature, several hybrid models have been proposed by combining different time series models together. In this paper, in contrast of the traditional hybrid models, a novel hybridization of the feed-forward neural networks (FFNNs) is proposed using the probabilistic neural networks (PNNs) in order to yield more accurate results than traditional feed-forward neural networks. In the proposed model, the estimated values of the FFNN models are modified based on the distinguished trend of their residuals and optimum step length, which are respectively yield from a probabilistic neural network and a mathematical programming model. Empirical results with three well-known real data sets indicate that the proposed model can be an effective way in order to construct a more accurate hybrid model than FFNN models. Therefore, it can be applied as an appropriate alternative model for forecasting tasks, especially when higher forecasting accuracy is needed.     

Evolving Recurrent Neural Network using Cartesian Genetic Programming to Predict The Trend in Foreign Currency Exchange Rates

Forecasting the foreign exchange rate is an uphill task. Numerous methods have been used over the years to develop an efficient and reliable network for forecasting the foreign exchange rate. This study utilizes recurrent neural networks (RNNs) for forecasting the foreign currency exchange rates. Cartesian genetic programming (CGP) is used for evolving the artificial neural network (ANN) to produce the prediction model. RNNs that are evolved through CGP have shown great promise in time series forecasting. The proposed approach utilizes the trends present in the historical data for its training purpose. Thirteen different currencies along with the trade-weighted index (TWI) and special drawing rights (SDR) is used for the performance analysis of recurrent Cartesian genetic programming-based artificial neural networks (RCGPANN) in comparison with various other prediction models proposed to date. The experimental results show that RCGPANN is not only capable of obtaining an accurate but also a computationally efficient prediction model for the foreign currency exchange rates. The results demonstrated a prediction accuracy of 98.872 percent (using 6 neurons only) for a single-day prediction in advance and, on average, 92% for predicting a 1000 days’ exchange rate in advance based on ten days of data history. The results prove RCGPANN to be the ultimate choice for any time series data prediction, and its capabilities can be explored in a range of other fields.     

Forecasting warranty performance in the presence of the ‘maturing data’ phenomenon

Forecasting of warranty performance helps car engineers to fine-tune their strategies for warranty cost reduction. The forecasting process involves prediction of not only the specific months-in-service (MIS) warranty performance at a certain future time, but also future MIS values. However, the ‘maturing data’ phenomenon that causes a warranty performance measure at specific MIS values to change with time make such forecasting challenging. Although dynamic linear models have been used for forecasting warranty performance, the focus mainly has been to utilize previous-model-year vehicle data for the analysis. In this paper, we apply a neural network model to forecast year-end warranty performance in the presence of the ‘maturing data’ phenomenon. We use a special type of neural network, viz. radial basis function (RBF), and optimize its parameters by minimizing training and testing errors through planned experimentation. This application shows the effectiveness of RBF neural networks to forecast warranty performance in the presence of the ‘maturing data’ phenomenon.     

基于改进eRCNN的局部路网交通流预测

针对误差反馈循环卷积神经网络在运用到短时交通流预测时存在仅仅能接收时序误差序列,忽略交通流误差数据中隐含的空间拓扑特征,且在模型初始化时其采用的通用卷积神经网络初始化方法降低了模型训练效率的问题,本文提出一种优化的误差反馈循环卷积神经网络模型,在误差反馈循环卷积神经网络模型基础上根据预测误差数据的时空特性对误差反馈层进行结构强化,能够处理包含简单空间关系的误差序列。同时通过在模型训练的过程中分离模型产生的历史预测误差和训练误差,使得模型构建过程更加高效,加速了模型收敛速度。通过北京市四环道路交通数据的实验表明,优化的误差反馈循环卷积神经网络预测模型在预测精度、构建效率及鲁棒性上均得到有效提高。     

A model updating strategy for predicting time series with seasonal patterns

Traditional methodologies for time series prediction take the series to be predicted and split it into training, validation, and test sets. The first one serves to construct forecasting models, the second set for model selection, and the third one is used to evaluate the final model. Different time series approaches such as ARIMA and exponential smoothing, as well as regression techniques such as neural networks and support vector regression, have been successfully used to develop forecasting models. A problem that has not yet received proper attention, however, is how to update such forecasting models when new data arrives, i.e. when a new event of the considered time series occurs.This paper presents a strategy to update support vector regression based forecasting models for time series with seasonal patterns. The basic idea of this updating strategy is to add the most recent data to the training set every time a predefined number of observations takes place. This way, information in new data is taken into account in model construction. The proposed strategy outperforms the respective static version in almost all time series studied in this work, considering three different error measures.     

Short-term electric power load forecasting using feedforward neural networks

Abstract: This paper presents the results of a study on short‐term electric power load forecasting based on feedforward neural networks. The study investigates the design components that are critical in power load forecasting, which include the selection of the inputs and outputs from the data, the formation of the training and the testing sets, and the performance of the neural network models trained to forecast power load for the next hour and the next day. The experiments are used to identify the combination of the most significant parameters that can be used to form the inputs of the neural networks in order to reduce the prediction error. The prediction error is also reduced by predicting the difference between the power load of the next hour (day) and that of the present hour (day). This is a promising alternative to the commonly used approach of predicting the actual power load. The potential of the proposed method is revealed by its comparison with two existing approaches that utilize neural networks for electric power load forecasting.     

Adaptative time constants improve the prediction capability of recurrent neural networks

Classical statistical techniques for prediction reach their limitations in applications with nonlinearities in the data set; nevertheless, neural models can counteract these limitations. In this paper, we present a recurrent neural model where we associate an adaptative time constant to each neuron-like unit and a learning algorithm to train these dynamic recurrent networks. We test the network by training it to predict the Mackey-Glass chaotic signal. To evaluate the quality of the prediction, we computed the power spectra of the two signals and computed the associated fractional error. Results show that the introduction of adaptative time constants associated to each neuron of a recurrent network improves the quality of the prediction and the dynamical features of a neural model. The performance of such dynamic recurrent neural networks outperform time-delay neural networks.     

An ensemble of neural networks for weather forecasting

This study presents the applicability of an ensemble of artificial neural networks (ANNs) and learning paradigms for weather forecasting in southern Saskatchewan, Canada. The proposed ensemble method for weather forecasting has advantages over other techniques like linear combination. Generally, the output of an ensemble is a weighted sum, which are weight-fixed, with the weights being determined from the training or validation data. In the proposed approach, weights are determined dynamically from the respective certainties of the network outputs. The more certain a network seems to be of its decision, the higher the weight. The proposed ensemble model performance is contrasted with multi-layered perceptron network (MLPN), Elman recurrent neural network (ERNN), radial basis function network (RBFN), Hopfield model (HFM) predictive models and regression techniques. The data of temperature, wind speed and relative humidity are used to train and test the different models. With each model, 24-h-ahead forecasts are made for the winter, spring, summer and fall seasons. Moreover, the performance and reliability of the seven models are then evaluated by a number of statistical measures. Among the direct approaches employed, empirical results indicate that HFM is relatively less accurate and RBFN is relatively more reliable for the weather forecasting problem. In comparison, the ensemble of neural networks produced the most accurate forecasts.     

Application of neural networks in forecasting engine systems reliability

This paper presents a comparative study of the predictive performances of neural network time series models for forecasting failures and reliability in engine systems. Traditionally, failure data analysis requires specifications of parametric failure distributions and justifications of certain assumptions, which are at times difficult to validate. On the other hand, the time series modeling technique using neural networks provides a promising alternative. Neural network modeling via feed-forward multilayer perceptron (MLP) suffers from local minima problems and long computation time. The radial basis function (RBF) neural network architecture is found to be a viable alternative due to its shorter training time. Illustrative examples using reliability testing and field data showed that the proposed model results in comparable or better predictive performance than traditional MLP model and the linear benchmark based on Box–Jenkins autoregressive-integrated-moving average (ARIMA) models. The effects of input window size and hidden layer nodes are further investigated. Appropriate design topologies can be determined via sensitivity analysis.     

Recurrent neural networks and robust time series prediction

We propose a robust learning algorithm and apply it to recurrent neural networks. This algorithm is based on filtering outliers from the data and then estimating parameters from the filtered data. The filtering removes outliers from both the target function and the inputs of the neural network. The filtering is soft in that some outliers are neither completely rejected nor accepted. To show the need for robust recurrent networks, we compare the predictive ability of least squares estimated recurrent networks on synthetic data and on the Puget Power Electric Demand time series. These investigations result in a class of recurrent neural networks, NARMA(p,q), which show advantages over feedforward neural networks for time series with a moving average component. Conventional least squares methods of fitting NARMA(p,q) neural network models are shown to suffer a lack of robustness towards outliers. This sensitivity to outliers is demonstrated on both the synthetic and real data sets. Filtering the Puget Power Electric Demand time series is shown to automatically remove the outliers due to holidays. Neural networks trained on filtered data are then shown to give better predictions than neural networks trained on unfiltered time series.     

Time series forecasting based on wavelet decomposition and feature extraction

Time series forecasting is one of the most important issues in numerous applications in real life. The objective of this study was to propose a hybrid neural network model based on wavelet transform (WT) and feature extraction for time series forecasting. The motivation of the proposed model, which is called PCA-WCCNN, is to establish a single simplified model with shorter training time and satisfactory forecasting performance. This model combines the principal component analysis (PCA) and WT with artificial neural networks (ANNs). Given a forecasting sequence, order of the original forecasting model is determined firstly. Secondly, the original time series is decomposed into approximation and detail components by employing WT technique. Then, instead of using all the components as inputs, feature inputs are extracted from all the sub-series obtained from the above step. Finally, based on the extracted features and all the sub-series, a famous neural network construction method called cascade-correlation algorithm is applied to train neural network model to learn the dynamics. As an illustration, the proposed model is compared with two classical models and two hybrid models, respectively. They are the traditional cascade-correlation neural network, back-propagation neural network, wavelet-based cascade-correlation network using all the wavelet components as inputs to establish one model (WCCNN) and wavelet-based cascade-correlation network with combination of each sub-series model (WCCNN multi-models). Results obtained from this study indicate that the proposed method improves the accuracy of ANN and can yield better efficiency than other four neural network models.

     

Training algorithm for radial basis function neural network based on quantum-behaved particle swarm optimization

Radial basis function (RBF) networks are widely applied in function approximation, system identification, chaotic time series forecasting, etc. To use a RBF network, a training algorithm is absolutely necessary for determining the network parameters. The existing training algorithms, such as orthogonal least squares (OLS) algorithm, clustering and gradient descent algorithm, have their own shortcomings respectively. In this paper, we propose a training algorithm based on a novel population-based evolutionary technique, quantum-behaved particle swarm optimization (QPSO), to train RBF neural network. The proposed QPSO-trained RBF network was tested on non-linear system identification problem and chaotic time series forecasting problem, and the results show that it can identify the system and forecast the chaotic time series more quickly and precisely than that trained by the particle swarm algorithm.     

An artificial neural network (p, d, q) model for timeseries forecasting

Artificial neural networks (ANNs) are flexible computing frameworks and universal approximators that can be applied to a wide range of time series forecasting problems with a high degree of accuracy. However, despite all advantages cited for artificial neural networks, their performance for some real time series is not satisfactory. Improving forecasting especially time series forecasting accuracy is an important yet often difficult task facing forecasters. Both theoretical and empirical findings have indicated that integration of different models can be an effective way of improving upon their predictive performance, especially when the models in the ensemble are quite different. In this paper, a novel hybrid model of artificial neural networks is proposed using auto-regressive integrated moving average (ARIMA) models in order to yield a more accurate forecasting model than artificial neural networks. The empirical results with three well-known real data sets indicate that the proposed model can be an effective way to improve forecasting accuracy achieved by artificial neural networks. Therefore, it can be used as an appropriate alternative model for forecasting task, especially when higher forecasting accuracy is needed.     

A Monte Carlo EM approach for partially observable diffusion processes: theory and applications to neural networks

We present a Monte Carlo approach for training partially observable diffusion processes. We apply the approach to diffusion networks, a stochastic version of continuous recurrent neural networks. The approach is aimed at learning probability distributions of continuous paths, not just expected values. Interestingly, the relevant activation statistics used by the learning rule presented here are inner products in the Hilbert space of square integrable functions. These inner products can be computed using Hebbian operations and do not require backpropagation of error signals. Moreover, standard kernel methods could potentially be applied to compute such inner products. We propose that the main reason that recurrent neural networks have not worked well in engineering applications (e.g., speech recognition) is that they implicitly rely on a very simplistic likelihood model. The diffusion network approach proposed here is much richer and may open new avenues for applications of recurrent neural networks. We present some analysis and simulations to support this view. Very encouraging results were obtained on a visual speech recognition task in which neural networks outperformed hidden Markov models.     

An Adaptive Approach to Market Development Forecasting

In the field of time series models for forecasting, the commonly accepted fact is that no one model could be shown to be superior to all others. An effective time series model for forecasting must incorporate the specific characteristics of the targeted problem domain. This paper proposes a neura network model for market development forecasting In this model, monotonicity and knowledge of seasonal period are incorporated into neural network training. The model is superior to the traditional curve fitting methods, in that it is adaptive in modelling trend and season factors for the time series in cases where the growth curve functions and seasonal functions are a priori unknown. The model is superior to unconstrained neural networks for time series modelling in that random fluctuations can be avoided. An example of forecasting daily sales using the neural network model is demonstrated.