Technology trends analysis and forecasting application based on decision tree and statistical feature analysis

Analyzing mass information and supporting foresight are very important task but they are extremely time-consuming work. In addition, information analysis and forecasting about the science and technology are also very critical tasks for researchers, government officers, businessman, etc. Some related studies recently have been executed and semi-automatic tools have been developed actively. Many researchers, annalists, and businessmen also generally use those tools for strategic decision making. However, existing projects and tools are based on subjective opinions from several experts and most of tools simply explain current situations, not forecasting near future trends. Therefore, in this paper, we propose a technology trends analysis and forecasting model based on quantitative analysis and several text mining technologies for effective, systematic, and objective information analysis and forecasting technology trends. Additionally, we execute a comparative evaluation between the suggested model and Gartner’s forecasting model for validating the suggested model because the Gartner’s model is widely and generally used for information analysis and forecasting.     

Chaotic multi-verse optimizer-based feature selection

Neural Computing and Applications - The multi-verse optimizer (MVO) is a new evolutionary algorithm inspired by the concepts of multi-verse theory namely, the white/black holes, which represents...     

改进EEMD-GRU混合模型在径流预报中的应用

为解决径流预测模型存在的预测精确度低、稳定性差、延时高等问题,结合门控制循环单元神经网络（gated recurrent unit, GRU）,集合经验模态分解（ensemble empirical mode decomposition, EEMD）的各自优点,提出一种基于改进EEMD方法的深度学习模型（EEMD-GRU）。该模型首先以智能算法对径流信号进行边界拓延,以解决EEMD边界效应。然后利用改进EEMD方法将径流信号分解为若干稳态分量,将各分量作为GRU模型的输入并对其进行预测。实验结果表明,与结合了经验模态分解的支持向量回归模型相比,并行EEMD-GRU径流预测模型的预测精准度、可信度和效率分别提高82.50%、144.67%和95.49%。基于EEMD-GRU的最优运算结果表明,该方法可进一步减少区域防洪的经济损失,提高灾害监管的工作效率。     

Assimilation of meteorological and remote sensing data for snowmelt runoff forecasting

A versatile data assimilation scheme for remote sensing snow cover products and meteorological data was developed, aimed at operational use for short-term runoff forecasting. Spatial and temporal homogenisation of the various input data sets is carried out, including meteorological point measurements from stations, numerical weather predictions, and snow maps from satellites. The meteorological data are downscaled to match the scale of the snow products, derived from optical satellite images of MODIS and from radar images of Envisat ASAR. Snow maps from SAR and optical imagery reveal systematic differences which need to be compensated for use in snowmelt models. We applied a semi-distributed model to demonstrate the use of satellite snow cover data for short-term runoff forecasting. During the snowmelt periods 2005 and 2006 daily runoff forecasts were made for the drainage basin Ötztal (Austrian Alps) for time lags up to 6 days. Because satellite images were obtained intermittently, prognostic equations were applied to predict the daily snow cover extent for model update. Runoff forecasting uncertainty is estimated by using not only deterministic meteorological predictions as input, but also 51 ensemble predictions of the EPS system of the European Centre for Medium Range Weather Forecast. This is particularly important for water management tasks, because meteorological forecasts are the main error source for runoff prediction, as confirmed by simulation studies with modified input data from the various sources. Evaluation of the runoff forecasts reveals good agreement with the measurements, confirming the usefulness of the selected data processing and assimilation scheme for operational use.     

基于二分搜索密度峰算法的RBFNN在月降水预报中的应用

针对径向基函数(RBF）网络结构和初始数据中心难以客观确定的不足,采用二分搜索密度峰值聚类算法（TSDPCA）找到数据中心值及数据簇类个数作为RBF神经网络的初始参数和隐藏层节点数,再利用梯度下降法优化RBFNN结构及各个参数建立预报模型,并应用于广西月降水预报中,以检验该模型的有效性。结果表明,与K-RBFNN和OLS-RBFNN的模型相比,TSDPCA-RBFNN预报平均相对误差值下降了10%~35%,具有更好的预报性能。     

实测海杂波光电图像混沌特性研究

基于随机信号模型的光电图像海杂波抑制是目前海杂波背景下目标检测常用方法,检测性能不甚稳定。在分析混沌动力系统相空间重构的基础上,通过提取实际海杂波光电图像序列的关联维数和最大Lyapunov指数,检验海杂波是否具有混沌性。实验结果表明:海杂波光电图像序列具有有限的关联维数和正的最大Lyapunov指数,验证了海杂波光电图像序列的混沌特性。海杂波具有的混沌特性使得可采用短时间预测法抑制海杂波,为海杂波光电弱目标检测提供新的解决思路。     

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.

     

基于最优特征组合改进极限梯度提升的负荷预测

为解决常规特征选择方法无法有效度量特征间的非线性相关的局限性,提出基于最优特征组合改进极限梯度提升(extreme gradient boosting,XGBoost)的负荷预测方法.该方法首先计算历史负荷与待预测负荷之间的互信息值(MI),取互信息最大的K个历史负荷特征形成MI滤集;进而从MI滤集取特征归因(SHAP)值最大的前L个特征形成SHAP滤集.通过粒子群优化寻找最优K、L值,建立基于最优特征组合改进极限梯度提升的预测模型(optimal feature combination improved XGBoost,OFCI-XGBoost).结果表明所提方法的预测误差为1.11％,低于相同策略改进的支持向量机、决策树、岭回归模型,验证了该预测模型的有效性.     

基于动态递归神经网络模型的混沌时间序列预测

提出了一种动态递归神经网络模型进行混沌时间序列预测,以最佳延迟时间为间隔的最小嵌入维数作为递归神经网络的输入维数,并按预测相点步进动态递归的生成训练数据,利用混沌特性处理样本及优化网络结构,用递归神经网络映射混沌相空间相点演化的非线性关系,提高了预测精度和稳定性。将该模型应用于Lorenz系统数据仿真以及沪市股票综合指数预测,其结果与已有网络模型预测的结果相比较,精度有很大提高。因此,证明了该预测模型在实际混沌时间序列预测领域的有效性和实用性。     

Identification of relationship between sunspots and natural runoff in the Yellow River based on discrete wavelet analysis

Annual natural runoff is an important index of a river, which may be affected by solar activities. In this study, 304 years of annual natural runoff at the Sanmenxia station located in the Yellow River and the sunspot relative number are decomposed with the application of a Complex Morlet. According to the results of real part, modulus and second power of modulus, the annual runoff series at the Sanmenxia station has an obvious periodic oscillation on 90–100, 50–80, 35–50, 15–35, about 10, and less than 10-year scales. Also, there are obvious periodic variability with 60–90 years, 30–50 years and about 10 years. There are two centers of energy: one is about 1840–1850 on 7–11-year scale and the other is about 1825–1925 on 60–70-year scale. From the wavelet variance, 3, 26, 46, 68 year periods are detected within a 100-year scale, and the 68-year period is the most significant. Similar analyses are conducted for the sunspot relative number within the same period 1700–2003. The sunspot series shows 11- and 60-year period variation, as well as eight energy centers. Then, the correlation analyses for 11- and 60-year serial scales are computed. From a long-term period (1700–2003) view, there is no notable correlation between the natural runoff and the sunspot relative number; however, it is evident that the correlations exist within a short-term period. The results also indicate that the relationships between solar activities and the natural runoff in the Yellow River are complicated.     

Probabilistic runoff volume forecasting in risk-based optimization for RTC of urban drainage systems

This article demonstrates the incorporation of stochastic grey-box models for urban runoff forecasting into a full-scale, system-wide control setup where setpoints are dynamically optimized considering forecast uncertainty and sensitivity of overflow locations in order to reduce combined sewer overflow risk. The stochastic control framework and the performance of the runoff forecasting models are tested in a case study in Copenhagen (76 km² with 6 sub-catchments and 7 control points) using 2-h radar rainfall forecasts and inlet flows to control points computed from a variety of noisy/oscillating in-sewer measurements. Radar rainfall forecasts as model inputs yield considerably lower runoff forecast skills than “perfect” gauge-based rainfall observations (ex-post hindcasting). Nevertheless, the stochastic grey-box models clearly outperform benchmark forecast models based on exponential smoothing. Simulations demonstrate notable improvements of the control efficiency when considering forecast information and additionally when considering forecast uncertainty, compared with optimization based on current basin fillings only.     

Neural-based electricity load forecasting using hybrid of GA and ACO for feature selection

Due to deregulation of electricity industry, accurate load forecasting and predicting the future electricity demand play an important role in the regional and national power system strategy management. Electricity load forecasting is a challenging task because electric load has complex and nonlinear relationships with several factors. In this paper, two hybrid models are developed for short-term load forecasting (STLF). These models use “ant colony optimization (ACO)” and “combination of genetic algorithm (GA) and ACO (GA-ACO)” for feature selection and multi-layer perceptron (MLP) for hourly load prediction. Weather and climatic conditions, month, season, day of the week, and time of the day are considered as load-influencing factors in this study. Using load time-series of a regional power system, the performance of ACO?+?MLP and GA-ACO?+?MLP hybrid models is compared with principal component analysis (PCA)?+?MLP hybrid model and also with the case of no-feature selection (NFS) when using MLP and radial basis function (RBF) neural models. Experimental results and the performance comparison with similar recent researches in this field show that the proposed GA-ACO?+?MLP hybrid model performs better in load prediction of 24-h ahead in terms of mean absolute percentage error (MAPE).     

Chaotic maps based on binary particle swarm optimization for feature selection

Feature selection is a useful pre-processing technique for solving classification problems. The challenge of solving the feature selection problem lies in applying evolutionary algorithms capable of handling the huge number of features typically involved. Generally, given classification data may contain useless, redundant or misleading features. To increase classification accuracy, the primary objective is to remove irrelevant features in the feature space and to correctly identify relevant features. Binary particle swarm optimization (BPSO) has been applied successfully to solving feature selection problems. In this paper, two kinds of chaotic maps—so-called logistic maps and tent maps—are embedded in BPSO. The purpose of chaotic maps is to determine the inertia weight of the BPSO. We propose chaotic binary particle swarm optimization (CBPSO) to implement the feature selection, in which the K-nearest neighbor (K-NN) method with leave-one-out cross-validation (LOOCV) serves as a classifier for evaluating classification accuracies. The proposed feature selection method shows promising results with respect to the number of feature subsets. The classification accuracy is superior to other methods from the literature.     

A rainfall analysis and forecasting tool

MENSEI-L is a stand-alone software tool for the automatic analysis of pluviometric networks, that also provides three-day rainfall forecasts based on weather types. The software tool, implemented in Python and R, is able to fill missing values in original daily data series and to generate synthetic pluviometers in ungauged locations, by means of kriging techniques. MENSEI-L also characterizes punctual and spatial, average and extreme distributions of precipitation for the complete pluviometric network. Tenerife (Canary Islands, Spain) is used as study site to evaluate the capabilities of MENSEI-L and the implicit rainfall analysis methodology that it implements. MENSEI-L proves to be a useful tool to extract information from dense observation networks where manual analysis is not practical.     

A new feature selection algorithm and composite neural network for electricity price forecasting

In a competitive electricity market, the forecasting of energy prices is an important activity for all the market participants either for developing bidding strategies or for making investment decisions. In this paper, a new forecast strategy is proposed for day ahead prediction of electricity price, which is a complex signal with nonlinear, volatile and time dependent behavior. Our forecast strategy includes a new two stage feature selection algorithm, a composite neural network (CNN) and a few auxiliary predictors. The feature selection algorithm has two filtering stages to remove irrelevant and redundant candidate inputs, respectively. This algorithm is based on mutual information (MI) criterion and selects the input variables of the CNN among a large set of candidate inputs. The CNN is composed of a few neural networks (NN) with a new data flow among its building blocks. The CNN is the forecast engine of the proposed strategy. A kind of cross-validation technique is also presented to fine-tune the adjustable parameters of the feature selection algorithm and CNN. Moreover, the proposed price forecast strategy is equipped with a few auxiliary predictors to enrich the candidate set of inputs of the forecast engine. The whole proposed strategy is examined on the PJM, Spanish and Californian electricity markets and compared with some of the most recent price forecast methods.     

面向数控加工工时估算的模型特征识别

利用数控加工结构件的特征具有层次分布式特点,提出了基于面邻接关系 的特征识别方法,将零件的面先分成基础面和约束面,再根据凹凸邻接关系组合为相应的层 集合,以层作为特征识别的基础,通过层的识别和组合获得数控加工结构件的特征,并提取 相关特征参数信息,结合机床的加工参数,对零件加工工时进行了估算,并进行了实例验证。     

Linearity versus non-linearity in forecasting Nile River flows

Egypt is almost totally dependent on the Nile River for satisfying about 95% of its water requirements. Aswan High Dam (AHD), located at the most upstream point of the river controls Egypt's share of water. Once a release decision is made, there is no chance of retrieving or recovering this released water. Therefore, long- and short-term forecasts of Nile flows at Aswan have been recognized to be of great importance to allow better management and operation of the reservoir.Several autoregressive (AR) models of uni- or multi-site flows upstream of Aswan had been developed to forecast monthly reservoir inflows for some lead-time. Most of these models failed to forecast, with satisfactory accuracy, the peak flows of July, August, and September due to high variability of flows during these months. Some hydrologists contributed this inaccuracy to the linearity assumption embedded in AR models.Artificial neural networks (ANNs) are being tested as a forecast tool to consider the non-linearity. Several neural networks using Neuralyst™ software have been investigated against updated AR models. The results indicated that the inclusion of non-linearity in the ANNs forecast might in some cases lead to improved forecast accuracy.     

Chaotic analysis of US money and velocity measures

This paper uses tools from dynamical systems theory to investigate the properties of US money and velocity series. Comparisons are made between simple-sum, Divisia and currency equivalent aggregates (of M1, M2, M3, and L), using the Anderson et al. monthly data (from January 1960 to June 1996).     

基于贪心核特征提取方法的中期峰值负荷预测

针对中期电力负荷预测, 提出基于贪心核主元回归(GKPCR)、贪心核岭回归(GKRR) 的特征提取建模方法. 通过对核矩阵的稀疏逼近, GKPCR和GKRR两种贪心核特征提取方法旨在寻找特征空间中数据的低维表示, 计算需求低, 适用于大数据集的在线学习. 将所提出的方法应用于不同地区的电力负荷中期峰值预测, 并与现有预测方法进行了比较. 实验结果表明, 在同等条件下, 所提出的方法能有效地改进预测精度, 而且性能更好, 显示了其有效性和应用潜力.

     

Incorporating feature selection method into support vector regression for stock index forecasting

Stock index forecasting is one of the most difficult tasks that financial organizations, firms and private investors have to face. Support vector regression (SVR) has become a popular alternative in stock index forecasting tasks due to its generalization capability in obtaining a unique solution. However, the major limitation of SVR is that it cannot capture the relative importance of independent variables to the dependent variable when many potential independent variables are considered. This study incorporates feature selection method and SVR for building stock index forecasting model. The proposed model uses multivariate adaptive regression splines (MARS), an effective nonlinear and nonparametric regression methodology, to identify important forecasting variables. The obtained significant predictor variables are then served as the inputs for the SVR model. Experimental results reveal that the obtained important variables from MARS can improve the forecasting performance of the SVR models. Moreover, the MARS results provide useful information about the relationship between the selected predictor variables and stock index through the obtained basis functions, important predictor variables and the MARS prediction function. Hence, the proposed stock index forecasting model can generate good forecasting performance and exhibits the capability of identifying significant predictor variables, which provide valuable information for further investment decisions/strategies.