A hybrid artificial intelligence model for river flow forecasting

A hybrid hydrologic estimation model is presented with the aim of performing accurate river flow forecasts without the need of using prior knowledge from the experts in the field. The problem of predicting stream flows is a non-trivial task because the various physical mechanisms governing the river flow dynamics act on a wide range of temporal and spatial scales and almost all the mechanisms involved in the river flow process present some degree of nonlinearity. The proposed system incorporates both statistical and artificial intelligence techniques used at different stages of the reasoning cycle in order to calculate the mean daily water volume forecast of the Salvajina reservoir inflow located at the Department of Cauca, Colombia. The accuracy of the proposed model is compared against other well-known artificial intelligence techniques and several statistical tools previously applied in time series forecasting. The results obtained from the experiments carried out using real data from years 1950 to 2006 demonstrate the superiority of the hybrid system.     

RBFNN versus FFNN for daily river flow forecasting at Johor River,Malaysia

Streamflow forecasting can have a significant economic impact, as this can help in water resources management and in providing protection from water scarcities and possible flood damage. Artificial neural network (ANN) had been successfully used as a tool to model various nonlinear relations, and the method is appropriate for modeling the complex nature of hydrological systems. They are relatively fast and flexible and are able to extract the relation between the inputs and outputs of a process without knowledge of the underlying physics. In this study, two types of ANN, namely feed-forward back-propagation neural network (FFNN) and radial basis function neural network (RBFNN), have been examined. Those models were developed for daily streamflow forecasting at Johor River, Malaysia, for the period (1999–2008). Comprehensive comparison analyses were carried out to evaluate the performance of the proposed static neural networks. The results demonstrate that RBFNN model is superior to the FFNN forecasting model, and RBFNN can be successfully applied and provides high accuracy and reliability for daily streamflow forecasting.     

A self-organizing HCMAC neural-network classifier

This paper presents a self-organizing hierarchical cerebellar model arithmetic computer (HCMAC) neural-network classifier, which contains a self-organizing input space module and an HCMAC neural network. The conventional CMAC can be viewed as a basis function network (BFN) with supervised learning, and performs well in terms of its fast learning speed and local generalization capability for approximating nonlinear functions. However, the conventional CMAC has an enormous memory requirement for resolving high-dimensional classification problems, and its performance heavily depends on the approach of input space quantization. To solve these problems, this paper presents a novel supervised HCMAC neural network capable of resolving high-dimensional classification problems well. Also, in order to reduce what is often trial-and-error parameter searching for constructing memory allocation automatically, proposed herein is a self-organizing input space module that uses Shannon's entropy measure and the golden-section search method to appropriately determine the input space quantization according to the various distributions of training data sets. Experimental results indicate that the self-organizing HCMAC indeed has a fast learning ability and low memory requirement. It is a better performing network than the conventional CMAC for resolving high-dimensional classification problems. Furthermore, the self-organizing HCMAC classifier has a better classification ability than other compared classifiers.     

A comparison study between fuzzy time series model and ARIMA model for forecasting Taiwan export

This study compares the application of two forecasting methods on the amount of Taiwan export, the ARIMA time series method and the fuzzy time series method. Models discussed for the fuzzy time series method include the Factor models, the Heuristic models, and the Markov model. When the sample period is prolong in our models, the ARIMA model shows smaller than predicted error and closer predicted trajectory to the realistic trend than those of the fuzzy model, resulted in more accurate forecasts of the export amount in the ARIMA model. Especially, the coefficient of the error term for the previous period has increased to 79%, implying the influential effect of external factors. These external factors attribute to the export amount of Taiwan according to the economic viewpoints. However, this impact reduces as time progressing and the export amount of the lag period of 12 or 13 do not affect current export amount anymore. In conclusion, when the sample period is shorter with only a small set of data available, the fuzzy time series models can be utilized to predict export values accurately, outperforming the ARIMA model.     

A neural-network architecture for syntax analysis

Artificial neural networks (ANNs), due to their inherent parallelism, offer an attractive paradigm for implementation of symbol processing systems for applications in computer science and artificial intelligence. The paper explores systematic synthesis of modular neural-network architectures for syntax analysis using a prespecified grammar-a prototypical symbol processing task which finds applications in programming language interpretation, syntax analysis of symbolic expressions, and high-performance compilers. The proposed architecture is assembled from ANN components for lexical analysis, stack, parsing and parse tree construction. Each of these modules takes advantage of parallel content-based pattern matching using a neural associative memory. The proposed neural-network architecture for syntax analysis provides a relatively efficient and high performance alternative to current computer systems for applications that involve parsing of LR grammars which constitute a widely used subset of deterministic context-free grammars. Comparison of quantitatively estimated performance of such a system (implemented using current CMOS VLSI technology) with that of conventional computers demonstrates the benefits of massively parallel neural-network architectures for symbol processing applications.     

两种时间序列模型在客流量预测上的比较

模糊时间序列模型和季节模型都是基于时间序列的模型,为了探讨在时间序列表现出一定的周期性时,哪种模型的预测效果会更好,分别利用模糊时间序列模型和季节模型对南京某商场的客流量进行预测,计算并比较两种方法下的相对误差值和RMSE（Root Mean Square Error）值,发现季节模型的相对误差值图形的平滑度要优于模糊时间序列模型,季节模型的RMSE值小于模糊时间序列模型,这表明考虑到数据特征的模型有更好的预测结果。     

The Delft-FEWS flow forecasting system

Since its introduction in 2002/2003, the current generation of the Delft-FEWS operational forecasting platform has found application in over forty operational centres. In these it is used to link data and models in real time, producing forecasts on a daily basis. In some cases it forms a building block of a country-wide national forecasting system using distributed client-server technology. In other cases it is applied at a much smaller scale on a simple desktop workstation, providing forecasts for a single basin. The flexibility of the software in open integration of models and data has additionally appealed to the research community.This paper discusses the principles on which the Delft-FEWS system has been developed, as well as a brief background of the architecture of the system and concepts used for storing and handling data. One of the key features of the system is its flexibility in integrating (third-party) models and data, and the available approaches to linking models and accessing data are highlighted. A brief overview of different applications of the system is given to illustrate how the software is used to support differing objectives in the domain of real time environmental modelling.     

A neural-network contention controller for packet switchingnetworks

A novel approach to solving the output contention in packet switching networks with synchronous switching mode is presented. A contention controller has been designed based on the K-winner-take-all neural-network technique with a speedup factor to achieve a real-time computation of a nonblocking switching high-speed high-capacity packet switch without packet loss. Simulation results for evaluation of the performance of the K-winner network controller with 10 neurons are presented to study the constraints of the "frozen state" as well as those of same initial state. An optoelectronic contention controller constructed from a K-winner neural network is proposed.     

A neural-network method for the nonlinear servomechanism problem

The solution of the nonlinear servomechanism problem relies on the solvability of a set of mixed nonlinear partial differential and algebraic equations known as the regulator equations. Due to the nonlinear nature, it is difficult to obtain the exact solution of the regulator equations. This paper proposes to solve the regulator equations based on a class of recurrent neural network, which has the features of a cellular neural network. This research not only represents a novel application of the neural networks to numerical mathematics, but also leads to an effective approach to approximately solving the nonlinear servomechanism problem. The resulting design method is illustrated by application to the well-known ball and beam system.     

A neural-network algorithm for a graph layout problem

We present a neural-network algorithm for minimizing edge crossings in drawings of nonplanar graphs. This is an important subproblem encountered in graph layout. The algorithm finds either the minimum number of crossings or an approximation thereof and also provides a linear embedding realizing the number of crossings found. The parallel time complexity of the algorithm is O(1) for a neural network with n(2) processing elements, where n is the number of vertices of the graph. We present results from testing a sequential simulator of the algorithm on a set of nonplanar graphs and compare its performance with the heuristic of Nicholson.     

Face recognition: a convolutional neural-network approach

We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image sampling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image samples into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image sample, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 individuals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.     

A multi-pattern deep fusion model for short-term bus passenger flow forecasting

Short-term passenger flow forecasting is one of the crucial components in transportation systems with data support for transportation planning and management. For forecasting bus passenger flow, this paper proposes a multi-pattern deep fusion (MPDF) approach that is constructed by fusing deep belief networks (DBNs) corresponding to multiple patterns. The dataset of the short-term bus passenger flow is first segmented into different clusters by an affinity propagation algorithm. The passenger flow distribution of these clusters is subsequently analyzed for identifying different patterns. In each pattern, a DBN is developed as a deep representation for the passenger flow. The outputs of the DBNs are finally fused by chronological order rearrangement. Taking a bus line in Guangzhou city of China as an example, the present MPDF approach is modeled. Five approaches, non-parametric and parametric models, are applied to the same case for comparison. The results show that, the proposed model overwhelms all the peer methods in terms of mean absolute percentage error, root-mean-square error, and determination coefficient criteria. In addition, there exists significant difference between the addressed model and the comparison models. It is recommended from the present study that the deep learning technique incorporating the pattern analysis is promising in forecasting the short-term passenger flow.     

A new recurrent neural-network architecture for visual patternrecognition

We propose a new type of recurrent neural-network architecture, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units. The proposed recurrent neural network differs from Jordan's and Elman's recurrent neural networks with respect to function and architecture, because it has been originally extended from being a mere multilayer feedforward neural network, to improve discrimination and generalization powers. We also prove the convergence properties of the learning algorithm in the proposed recurrent neural network, and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeric database of Concordia University, Montreal, Canada. Experimental results have confirmed that the proposed recurrent neural network improves discrimination and generalization powers in the recognition of visual patterns     

A neural-network approach to nonparametric and robustclassification procedures

In this paper algorithms of neural-network type are introduced for solving estimation and classification problems when assumptions about independence, Gaussianity, and stationarity of the observation samples are no longer valid. Specifically, the asymptotic normality of several nonparametric classification tests is demonstrated and their implementation using a neural-network approach is presented. Initially, the neural nets train themselves via learning samples for nominal noise and alternative hypotheses distributions resulting in near optimum performance in a particular stochastic environment. In other than the nominal environments, however, high efficiency is maintained by adapting the optimum nonlinearities to changing conditions during operation via parallel networks, without disturbing the classification process. Furthermore, the superiority in performance of the proposed networks over more traditional neural nets is demonstrated in an application involving pattern recognition.     

基于CNN-XGBoost的短时交通流预测

为准确预测短时交通流,缓解交通拥堵提高交通运行效率,提出一种基于CNN-XGBoost的短时交通流预测方法。结合短时交通流数据的时间相关性和空间相关性,将本路段和邻近路段的历史数据一同作为输入进行预测。利用卷积神经网络(convolutional neural networks,CNN)实现特征提取以减少数据冗余性,提出一种参数经果蝇算法优化的XGBoost模型用于交通流量预测。实例验证结果表明,CNN可对时间和空间结合下的交通流数据进行有效特征提取;相比SVR、LSTM等模型,改进的XGBoost模型下的交通流量预测误差明显减小。     

Exchange rate forecasting: comparison of various architectures of neural networks

This paper evaluates the predictive accuracy of neural networks in forecasting exchange rate. The multi-layer perceptron (MLP) and radial basis function (RBF) networks with different architectures are used to forecast five exchange rate time series. The results of each prediction are evaluated and compared according to the networks and architectures used. It is found that neural networks can be effectively used in forecasting exchange rate and hence in designing trading strategies. RBF networks performed better than MLP networks in our simulation experiment. This experiment suggests that it is possible to extract information hidden in the exchange rate and predict it into future.     

Multi-city traffic flow forecasting via multi-task learning

Applied Intelligence - Traffic flow forecasting or prediction plays an important role in the traffic control and management of a city. Existing works mostly train a model using the traffic flow...     

RQEA-SVR在交通流预测中的应用

建立在统计学习理论和结构风险最小化准则基础上的支持向量回归（SVR）是处理小样本数据回归问题的有利工具,SVR的参数选取直接影响其学习性能和泛化能力。文中将SVR参数选取看作是参数的组合优化问题,确定组合优化问题的目标函数,采用实数量子进化算法（RQEA）求解组合优化问题进而优选SVR参数,形成RQEA-SVR,并应用RQEA-SVR求解交通流预测问题。仿真试验表明RQEA是优选SVR参数的有效方法,解决交通流预测问题具有优良的性能。     

A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition

Multi-step ahead forecasting is still an open challenge in time series forecasting. Several approaches that deal with this complex problem have been proposed in the literature but an extensive comparison on a large number of tasks is still missing. This paper aims to fill this gap by reviewing existing strategies for multi-step ahead forecasting and comparing them in theoretical and practical terms. To attain such an objective, we performed a large scale comparison of these different strategies using a large experimental benchmark (namely the 111 series from the NN5 forecasting competition). In addition, we considered the effects of deseasonalization, input variable selection, and forecast combination on these strategies and on multi-step ahead forecasting at large. The following three findings appear to be consistently supported by the experimental results: Multiple-Output strategies are the best performing approaches, deseasonalization leads to uniformly improved forecast accuracy, and input selection is more effective when performed in conjunction with deseasonalization.     

A lotus 1-2-3 based cash flow forecasting system

The role of Industrial Engineers within financial institutions has expanded significantly through the current emphasis on cash management related services. This paper discusses an automated cash flow forecasting system developed in conjunction with Citibank Panama's Cash Management Group. Features of Lotus 1-2-3 software are combined with a regression based multiplicative approach to yield an effective forecasting tool for financial treasury personnel. Development of the system is illustrated through a case study.