A hybrid neural network cybernetic system for quantifying cross-market dynamics and business forecasting

The internal structure of a complex system can manifest itself with correlations among its components. In global business, the interactions between different markets cause collective lead–lag behavior having special statistical properties which reflect the underlying dynamics. In this work, a cybernetic system of combining the vector autoregression (VAR) and genetic algorithm (GA) with neural network (NN) is proposed to take advantage of the lead–lag dynamics, to make the NN forecasting process more transparent and to improve the NN’s prediction capability. Two business case studies are carried out to demonstrate the advantages of our proposed system. The first one is the tourism demand forecasting for the Hong Kong market. Another business case study is the modeling and forecasting of Asian Pacific stock markets. The multivariable time series data is investigated with the VAR analysis, and then the NN is fed with the relevant variables determined by the VAR analysis for forecasting. Lastly, GA is used to cope with the time-dependent nature of the co-relationships among the variables. Experimental results show that our system is more robust and makes more accurate prediction than the benchmark NN. The contribution of this paper lies in the novel application of the forecasting modules and the high degree of transparency of the forecasting process.     

Optimizing mathematical parameters of Grey system theory: an empirical forecasting case of Vietnamese tourism

Accurately forecasting the demand for international and domestic tourism is a key goal for tourism industry leaders. The purpose of this study is to present more appropriate models for forecasting the demand for tourism in Vietnam. The authors apply GM(1,1), Verhulst, DGM(1,1) and DGM(2,1) to test which concise prediction models can improve the ability to predict the number of tourists visiting this country. In order to guarantee the accuracy of forecasting process, data cover in the period from 2005 through 2013 and are obtained from the official website of VNATR “Vietnam National Administration of Tourism” report. The MAPE, MSE, RMSE and MAD are four important criteria which are used to compare the various forecasting models results. Key findings indicate that the optimal value of GM(1,1), Verhulst, DGM(1,1) can enhance the forecasting results perfectly with minimum predicted errors. In the case of the tourism revenue, using the Verhulst model is evidently better than the others. For the number of international and domestic tourist prediction, the application of Verhulst and DGM(1,1) models is well done. For visitors coming from specific countries (i.e., China, Korea, Taiwan, Japan and America), DGM(2,1) is very poor for predicting in this situation, whereas remaining three models GM(1,1), Verhulst, DGM(1,1) and DGM(2,1) perform excellently. The results also pointed out that the tourism demands in Vietnam are growing rapidly; thus, the governments must be well prepared for tourism industry and enhance relative fundamental construction for tourism markets.

     

基于改进的灰色模型的旅游需求预测研究

针对海南省旅游需求预测问题,对传统的灰马尔科夫模型进行改进,提出了一种动态优化子集模糊灰马尔科夫预测模型。该模型首先根据GM(1,1)模型预测结果的平均绝对误差百分比,通过输入子集法来确定最优输入子集个数;然后利用模糊集理论,将计算出的隶属度向量作为马尔科夫转移矩阵向量的权重,以修正预测值。为了能够根据时间推移进行预测,建立了等维递补的动态预测模型。实验以海南省各市县旅游饭店接待情况为例,验证了该模型可以有效地提高预测数据的准确性。     

旅游高峰期交通流量的多时间尺度预测方法及应用

对旅游交通需求进行准确的短时预测难度很大,其时空分布规律更加难以估计。为了解决该问题,提高预测精度,首先分析了旅游交通流的多时间尺度可预测性,进而运用多时间尺度预测方法对旅游交通流量进行了预测。结果表明,模型预测性能良好、精度较高,从分类和分层的角度构建旅游交通多时间尺度预测模型、分析旅游交通流量分布和旅游交通流量动态分配,能够为旅游高峰期的道路交通运行态势快速评估和制定应急交通组织管理方案提供精确参考。     

A novel dynamic progress forecasting approach for construction projects

In this paper, we propose a novel construction project progress forecasting approach which combines the grey dynamic prediction model and the residual modified model to forecast the current progress during the construction phase. Firstly, four typical S-curves simplified from various sigmoid curves are proposed and fitted to the grey dynamic prediction model. For higher prediction accuracy, three different residual modified models are taken to amend the initial prediction value which was derived from the above step. The mean absolute percentage error (MAPE) and standard deviation of the estimate of Y (SDY) are used to assess the accuracy of the composite results. The better residual modified prediction model is adopted to combine the grey dynamic prediction model to form the novel progress forecasting approach. Then, practical completed construction cases are provided for testing the prediction ability of the proposed progress forecasting approach. Results show that the forecasting approach proposed to forecast construction progress during construction phase is able to get better prediction accuracy almost within 10% whether typical S-curves or practical cases. The new approach relatively provides an accurate, simple and stable method for predicting construction progress in comparison with the previous traditional forecasting methods.     

Chaotic time series method combined with particle swarm optimization and trend adjustment for electricity demand forecasting

Electricity demand forecasting plays an important role in electric power systems planning. In this paper, nonlinear time series modeling technique is applied to analyze electricity demand. Firstly, the phase space, which describes the evolution of the behavior of a nonlinear system, is reconstructed using the delay embedding theorem. Secondly, the largest Lyapunov exponent forecasting method (LLEF) is employed to make a prediction of the chaotic time series. In order to overcome the limitation of LLEF, a weighted largest Lyapunov exponent forecasting method (WLLEF) is proposed to improve the prediction accuracy. The particle swarm optimization algorithm (PSO) is used to determine the optimal weight parameters of WLLEF. The trend adjustment technique is used to take into account the seasonal effects in the data set for improving the forecasting precision of WLLEF. A simulation is performed using a data set that was collected from the grid of New South Wales, Australia during May 14–18, 2007. The results show that chaotic characteristics obviously exist in electricity demand series and the proposed prediction model can effectively predict the electricity demand. The mean absolute relative error of the new prediction model is 2.48%, which is lower than the forecasting errors of existing methods.     

An improved sales forecasting approach by the integration of genetic fuzzy systems and data clustering: Case study of printed circuit board

Success in forecasting and analyzing sales for given goods or services can mean the difference between profit and loss for an accounting period and, ultimately, the success or failure of the business itself. Therefore, reliable prediction of sales becomes a very important task. This article presents a novel sales forecasting approach by the integration of genetic fuzzy systems (GFS) and data clustering to construct a sales forecasting expert system. At first, all records of data are categorized into k clusters by using the K-means model. Then, all clusters will be fed into independent GFS models with the ability of rule base extraction and data base tuning. In order to evaluate our K-means genetic fuzzy system (KGFS) we apply it on a printed circuit board (PCB) sales forecasting problem which has been used as the case in different studies. We compare the performance of an extracted expert system with previous sales forecasting methods using mean absolute percentage error (MAPE) and root mean square error (RMSE). Experimental results show that the proposed approach outperforms the other previous approaches.     

The adaptive fuzzy time series model with an application to Taiwan’s tourism demand

In this study, an adaptive fuzzy time series model for forecasting Taiwan’s tourism demand is proposed to further enhance the predicted accuracy. We first transfer fuzzy time series data to the fuzzy logic group, assign weights to each period, and then use the proposed adaptive fuzzy time series model for forecasting in which an enrollment forecasting values is applied to obtain the smallest forecasting error. Finally, an illustrated example for forecasting Taiwan’s tourism demand is used to verify the effectiveness of proposed model and confirmed the potential benefits of the proposed approach with a very small forecasting error MAPE and RMSE.     

基于Hadoop和并行BP网络的打车需求量预测系统研究

一个良好的打车需求量预测系统可以帮助完善城市的交通系统,帮助城市更高效地进行出租车的调度。基于Hadoop设计并搭建了一个打车需求量预测系统。除此之外,针对传统BP神经网络收敛速度慢的缺点,提出了一种基于MapReduce的并行BP神经网络,并将其用作系统的预测模型对打车需求量进行预测。根据实验结果,提出的系统能良好地对城市内某一区域一天内的打车需求量进行预测。     

Application of hybrid computational intelligence models in short-term bus load forecasting

Artificial neural networks (ANNs) are a favorable scheme in load forecasting applications mainly due to their endogenous capacity of robust modeling of data sets with highly non-linear relationship between inputs and outputs. Usually, the inputs correspond to historical load values, exogenous variables like temperature, day type identification codes and others. The outputs refer to the load values under examination. The majority of the load forecasting related literature focuses in aggregated load system level. While contemporary research efforts focus in smart grid technologies, there is need to study the characteristics of small scaled loads. Bus load forecasting refers to prediction of the demand patterns in buses of the transmission and distribution systems. Bus load exhibits low correlation with the aggregated system load, since it is characterized by a high level of stochasticity. Hence, a proper selection and formulation of the forecasting model is essential in order to keep the prediction accuracy within acceptable ranges. The treatment of bus load characteristics is held with computational intelligence techniques such as clustering and ANN. Neural network based systems are a favorable scheme in recent years in price and load predictions over traditional time series models. ANN can fully adapt expert knowledge and modify their parameters accordingly to simulate the problem`s attributions through training paradigms. Thus, ANN based systems are an essential choice, justified by the paper`s findings, for highly volatile time series. This work focuses on the short-term load forecasting (STLF) of a number of buses within the Greek interconnected system. Firstly, a modified version of the ANN already proposed for the aggregated load of the interconnected system is employed. To enhance the forecasting accuracy of the ANN, the load profiling methodology is used resulting to the formulation of two novel hybrid forecasting models. These models refer to the combination of the ANN with a clustering algorithm, resulting to superior performance. Simulation results indicate that the combination captures and successfully treats the special characteristics of the bus load patterns. The scope of the present paper is to develop efficient forecasting systems for short-term bus load predictions. This is a current research challenge due to the high interest for smart grids and demand side management applications by utilities, regulators, retailer and energy service companies. Bus load forecasting appears to be a more difficult engineering problem compared to forecasting of the total load of a country. No hybrid models for bus load predictions have been presented so far in the literature. Two novel clustering based tools are developed and successfully tested in a number of loads covering different types of electricity consumers and demand levels.     

基于需求预测的PaaS平台资源分配方法

针对缺乏PaaS平台下资源需求的有效预测与优化分配的问题，提出一种资源需求预测模型和分配方法。首先，根据PaaS平台中应用对资源需求的周期性来对资源序列进行切分，并在短期预测的基础上结合应用的多周期性特征，利用多元回归算法建立综合的预测模型。然后，基于MapReduce架构设计实现了一个Master-Slave模式的PaaS平台资源分配系统。最后，结合当前任务请求和资源需求预测结果进行资源分配。实验结果表明，采用该资源需求预测模型和分配方法后，相比于自回归模型和指数平滑算法，平均绝对百分比误差分别下降8.71个百分点和2.07个百分点，均方根误差分别下降2.01个百分点和0.46个百分点。所提预测模型的预测结果不仅误差小，与真实值的拟合程度也较高，而且利用较小的时间开销就可以获得较高的准确度。此外，使用该预测模型的PaaS平台的资源请求的平均等待时间有了明显的下降。     

Recursive Bayesian echo state network with an adaptive inflation factor for temperature prediction

Temperature prediction is a challenging problem and a concern in energy, environment, industry and agriculture etc. Climate models and statistical time-series forecasting methods are the ineffective forecasting tools of the long-range temperature prediction. A recurrent neural network (RNN) can model complex system with high accuracy. As a type of RNN design approach, echo state network (ESN) is used for temperature forecasting in this study. Based on analysis of monthly maximum, mean and minimum temperatures data sets, a novel recursive Bayesian linear regression (RBLR) algorithm based on ESN is presented in this study. The algorithm consists of two main components: an ESN and a RBLR algorithm with an adaptive inflation factor that changes the confidence level of the prior data. Our proposed method improves the prediction accuracy of the long-range temperature forecasting. Experimental investigations using Central England temperature time series show that the proposed method can forecast monthly maximum, mean and minimum temperatures for the next 12 months and produce good prediction.

     

ANN-based residential water end-use demand forecasting model

Bottom-up urban water demand forecasting based on empirical data for individual water end uses or micro-components (e.g., toilet, shower, etc.) for different households of varying characteristics is undoubtedly superior to top-down estimates originating from bulk water metres that are currently performed. Residential water end-use studies partially enabled by modern smart metering technologies such as those used in the South East Queensland Residential End Use Study (SEQREUS) provide the opportunity to align disaggregated water end-use demand for households with an extensive database covering household demographic, socio-economic and water appliance stock efficiency information. Artificial neural networks (ANNs) provide the ideal technique for aligning these databases to extract the key determinants for each water end-use category, with the view to building a residential water end-use demand forecasting model. Three conventional ANNs were used: two feed-forward back propagation networks and one radial basis function network. A sigmoid activation hidden layer and linear activation output layer produced the most accurate forecasting models. The end-use forecasting models had R² values of 0.33, 0.37, 0.60, 0.57, 0.57, 0.21 and 0.41 for toilet, tap, shower, clothes washer, dishwasher, bath and total internal demand, respectively. All of the forecasting models except the bath demand were able to reproduce the means and medians of the frequency distributions of the training and validation sets. This study concludes with an application of the developed forecasting model for predicting the water savings derived from a citywide implementation of a residential water appliance retrofit program (i.e., retrofitting with efficient toilets, clothes washers and shower heads).     

Business failure prediction using hybrid2 case-based reasoning (H2CBR)

We have investigated business failure prediction (BFP) by a combination of decision-aid, statistical, and artificial intelligence techniques. The goal is to construct a hybrid forecasting method for BFP by combining various outranking preference functions with case-based reasoning (CBR), whose heart is the k-nearest neighbor (k-NN) algorithm, and to empirically test the predictive performance of its modules. The hybrid² CBR (H²CBR) forecasting method was constructed by integrating six hybrid CBR modules. These hybrid CBR modules were built up by combining and modifying six outranking preference functions with the algorithm of k-NN inside CBR. A trial-and-error iterative process was employed to identify the optimal hybrid CBR module of the H²CBR forecasting system. The prediction of the optimal module is the final output of the H²CBR forecasting method. We have compared the predictive performance of the six hybrid CBR modules in BFP of Chinese listed companies. In this empirical study, the classical CBR algorithm based on the Euclidean metric, and the two classical statistical methods of logistic regression (Logit) and multivariate discriminant analysis (MDA) were used as baseline models for comparison. Feature subsets were selected with the stepwise method of MDA. The predictive performance of the H²CBR system is promising; the most preferred hybrid CBR for short-term BFP of Chinese listed companies is based on the ranking-order preference function.     

Improving project-profit prediction using a two-stage forecasting system

Accurate project-profit prediction is a crucial issue because it can provide an early feasibility estimate for the project. In order to achieve accurate project-profit prediction, this study developed a novel two-stage forecasting system. In stage one, the proposed forecasting system adopts fuzzy clustering technology, fuzzy c-means (FCM) and kernel fuzzy c-means (KFCM), for the correct grouping of different projects. In stage two, least-squares support vector regression (LSSVR) technology is employed for forecasting the project-profit in different project groups, respectively. Moreover, genetic algorithms (GA) were simultaneously used to select the parameters of the LSSVR. The project data come from a real enterprise in Taiwan. In this study, some forecasting methodologies are also compared, for instance Generalized Regression Neural Network (GRNN), Radial Basis Function Neural Networks (RBFNN), and Back Propagation Neural Network (BPNN), to predict project-profit in this real case. Empirical results indicate that the two-stage forecasting system (FCM+LSSVR and KFCM+LSSVR) has superior performance in terms of forecasting accuracy, compared to other methods. Furthermore, in observing the results of the two-stage forecasting system, it can be seen that FCM+LSSVR can achieve superior performance, and KFCM+LSSVR can achieve consistently good performance. Therefore, based on the empirical results, the two-stage forecasting system was verified to efficiently provide credible predictions for project-profit forecasting.     

A sparse Gaussian process regression model for tourism demand forecasting in Hong Kong

In recent years, Gaussian process (GP) models have been popularly studied to solve hard machine learning problems. The models are important due to their flexible non-parametric modeling abilities using Mercer kernels and the Bayesian framework for probabilistic inference. In this paper, we propose a sparse GP regression (GPR) model for tourism demand forecasting in Hong Kong. The sparsification procedure of the GPR model not only decreases the computational complexity but also improves the generalization ability. We experiment the proposed model with monthly demand data that are relevant to Hong Kong’s tourism industry, and compare the performance of the sparse GPR model with those of various kernel-based models to show its effectiveness. The proposed sparse GPR model shows that its forecasting capability outperforms those of the ARMA model and the two state-of-the-art SVM models.     

灰色GM(1,1,t α)模型与自忆性原理的耦合及应用

针对实际工程应用中传统GM(1,1)模型预测的局限性,以含时间幂次项的灰色GM(1,1,tα)模型为基础,构建了灰色GM(1,1,tα)与自忆性原理的耦合预测模型;用动力系统自忆性原理来克服传统灰色模型对初值比较敏感的弱点;将灰色GM(1,1,t2)自忆性模型应用于某沿海高速软土地基沉降的模拟和预测,获得了满意的模拟和预测精度.实验算例表明,所提出的新模型显著地改善了传统灰色预测模型的模拟预测精度.     

Empirical Mode Decomposition based ensemble deep learning for load demand time series forecasting

Load demand forecasting is a critical process in the planning of electric utilities. An ensemble method composed of Empirical Mode Decomposition (EMD) algorithm and deep learning approach is presented in this work. For this purpose, the load demand series were first decomposed into several intrinsic mode functions (IMFs). Then a Deep Belief Network (DBN) including two restricted Boltzmann machines (RBMs) was used to model each of the extracted IMFs, so that the tendencies of these IMFs can be accurately predicted. Finally, the prediction results of all IMFs can be combined by either unbiased or weighted summation to obtain an aggregated output for load demand. The electricity load demand data sets from Australian Energy Market Operator (AEMO) are used to test the effectiveness of the proposed EMD-based DBN approach. Simulation results demonstrated attractiveness of the proposed method compared with nine forecasting methods.     

A novel nonlinear ensemble forecasting model incorporating GLAR and ANN for foreign exchange rates

In this study, we propose a novel nonlinear ensemble forecasting model integrating generalized linear auto-regression (GLAR) with artificial neural networks (ANN) in order to obtain accurate prediction results and ameliorate forecasting performances. We compare the new model's performance with the two individual forecasting models—GLAR and ANN—as well as with the hybrid model and the linear combination models. Empirical results obtained reveal that the prediction using the nonlinear ensemble model is generally better than those obtained using the other models presented in this study in terms of the same evaluation measurements. Our findings reveal that the nonlinear ensemble model proposed here can be used as an alternative forecasting tool for exchange rates to achieve greater forecasting accuracy and improve prediction quality further.     

基于粗糙集和CBR的救灾口粮需求预测

救灾口粮预测所采用的方法多以专家经验判断为主,具有较大的随机性。为此,从灾害案例的特点出发,针对案例推理时存在效率低下和权重确定差异性较大的问题,结合粗糙集处理不确定知识的优点和案例推理的特点,提出一种方法,实现灾害应急救灾口粮需求预测,并通过洪涝灾害实例进行分析。结果表明该方法有利于减少主观影响,提高需求预测的准确率和效率。