Parameters Optimization Using Genetic Algorithms in Support Vector Regression for Sales Volume Forecasting

Budgeting planning plays an important role in coordinating activities in organizations. An accurate sales volume forecasting is the key to the entire budgeting process. All of the other parts of the master budget are dependent on the sales volume forecasting in some way. If the sales volume forecasting is sloppily done, then the rest of the budgeting process is largely a waste of time. Therefore, the sales volume forecasting process is a critical one for most businesses, and also a difficult area of management. Most of researches and companies use the statistical methods, regression analysis, or sophisticated computer simulations to analyze the sales volume forecasting. Recently, various prediction Artificial Intelligent (AI) techniques have been proposed in forecasting. Support Vector Regression (SVR) has been applied successfully to solve problems in numerous fields and proved to be a better prediction model. However, the select of appropriate SVR parameters is difficult. Therefore, to improve the accuracy of SVR, a hybrid intelligent support system based on evolutionary computation to solve the difficulties involved with the parameters selection is presented in this research. Genetic Algorithms (GAs) are used to optimize free parameters of SVR. The experimental results indicate that GA-SVR can achieve better forecasting accuracy and performance than traditional SVR and artificial neural network (ANN) prediction models in sales volume forecasting.

Heating load interval forecasting approach based on support vector regression and error estimation

As the existing heating load forecasting methods are almostly point forecasting,an interval forecasting approach based on Support Vector Regression (SVR) and interval estimation of relative error is proposed in this paper.The forecasting output can be defined as energy saving control setting value of heating supply substation;meanwhile,it can also provide a practical basis for heating dispatching and peak load regulating operation.By means of the proposed approach,SVR model is used to point forecasting and the error interval can be gained by using nonparametric kernel estimation to the forecast error,which avoid the distributional assumptions.Combining the point forecasting results and error interval,the forecast confidence interval is obtained.Finally,the proposed model is performed through simulations by applying it to the data from a heating supply network in Harbin,and the results show that the method can meet the demands of energy saving control and heating dispatching.

Long Term Load Forecasting and Recommendations for China Based on Support Vector Regression

Long-term load forecasting (LTLF) is a challenging task because of the complex relationships between load and factors affecting load. However, it is crucial for the economic growth of fast developing countries like China as the growth rate of gross domestic product (GDP) is expected to be 7.5%, according to China’s 11th Five-Year Plan (2006-2010). In this paper, LTLF with an economic factor, GDP, is implemented. A support vector regression (SVR) is applied as the training algorithm to obtain the nonlinear relationship between load and the economic factor GDP to improve the accuracy of forecasting.

On-line forecasting model for zinc output based on self-tuning support vector regression and its application

An on-line forecasting model based on self-tuning support vectors regression for zinc output was put forward to maximize zinc output by adjusting operational parameters in the process of imperial smelting furnace. In this model, the mathematical model of support vector regression was converted into the same format as support vector machine for classification. Then a simplified sequential minimal optimization for classification was applied to train the regression coefficient vector α- α* and threshold b. Sequentially penalty parameter C was tuned dynamically through forecasting result during the training process. Finally, an on-line forecasting algorithm for zinc output was proposed. The simulation result shows that in spite of a relatively small industrial data set, the effective error is less than 10% with a remarkable performance of real time. The model was applied to the optimization operation and fault diagnosis system for imperial smelting furnace.

Short-Term Financial Time Series Forecasting Integrating Principal Component Analysis and Independent Component Analysis with Support Vector Regression

Financial time series forecasting could be beneficial for individual as well as institutional investors. But, the high noise and complexity residing in the financial data make this job extremely challenging. Over the years, many researchers have used support vector regression (SVR) quite successfully to conquer this challenge. In this paper, an SVR based forecasting model is proposed which first uses the principal component analysis (PCA) to extract the low-dimensional and efficient feature information, and then uses the independent component analysis (ICA) to preprocess the extracted features to nullify the influence of noise in the features. Experiments were carried out based on 16 years’ historical data of three prominent stocks from three different sectors listed in Dhaka Stock Exchange (DSE), Bangladesh. The predictions were made for 1 to 4 days in advance targeting the short term prediction. For comparison, the integration of PCA with SVR (PCA-SVR), ICA with SVR (ICA-SVR) and single SVR approaches were applied to evaluate the prediction accuracy of the proposed approach. Experimental results show that the proposed model (PCA-ICA-SVR) outperforms the PCA-SVR, ICA-SVR and single SVR methods.

Improved IMM algorithm based on support vector regression for UAV tracking

With the development of technology, the relevant performance of unmanned aerial vehicles(UAVs) has been greatly improved, and various highly maneuverable UAVs have been developed, which puts forward higher requirements on target tracking technology. Strong maneuvering refers to relatively instantaneous and dramatic changes in target acceleration or movement patterns, as well as continuous changes in speed,angle, and acceleration. However, the traditional UAV tracking algorithm model has poor adaptability and large amount of calculation. This paper applies support vector regression(SVR)to the interacting multiple model(IMM) algorithm. The simulation results show that the improved algorithm has higher tracking accuracy for highly maneuverable targets than the original algorithm, and can adjust parameters adaptively, making it more adaptable.

Profit Guided or Statistical Error Guided? A Study of Stock Index Forecasting Using Support Vector Regression

Stock index forecasting has been one of the most widely investigated topics in the field of financial forecasting. Related studies typically advocate for tuning the parameters of forecasting models by minimizing learning errors measured using statistical metrics such as the mean squared error or mean absolute percentage error. The authors argue that statistical metrics used to guide parameter tuning of forecasting models may not be meaningful, given the fact that the ultimate goal of forecasting is to facilitate investment decisions with expected profits in the future. The authors therefore introduce the Sharpe ratio into the process of model building and take it as the profit metric to guide parameter tuning rather than using the commonly adopted statistical metrics. The authors consider three widely used trading strategies, which include a na¨?ve strategy, a filter strategy and a dual moving average strategy, as investment scenarios. To verify the effectiveness of the proposed profit guided approach, the authors carry out simulation experiments using three global mainstream stock market indices. The results show that profit guided forecasting models are competitive, and in many cases produce significantly better performances than statistical error guided models. This implies thatprofit guided stock index forecasting is a worthwhile alternative over traditional stock index forecasting practices.

Early Warning Model of Diamondback Moth Based on ε-Support Vector Regression

The model for predicting vegetable pest diamondback moth was established based on E-Support Vector Regression algorithms in the multiply occurrence season of diamondback moth. The experimental data of diamondback moth in Guangdong vegetable were analyzed, and the result showed that when penalty factor c was 43, kernel function parameter k was O. 2, the better prediction result could be obtained by the early warning model of E-Support Vector Regression algorithms.

A Multiple Model Approach to Modeling Based on Fuzzy Support Vector Machines

A new multiple models(MM) approach was proposed to model complex industrial process by using Fuzzy Support Vector Machines(F -SVMs). By applying the proposed approach to a pH neutralization titration experiment, F -SVMs MM not only provides satisfactory approximation and generalization property, but also achieves superior performance to USOCPN multiple modeling method and single modeling method based on standard SVMs.

Endpoint Prediction of EAF Based on Multiple Support Vector Machines

The endpoint parameters are very important to the process of EAF steel-making, but their on-line measurement is difficult. The soft sensor technology is widely used for the prediction of endpoint parameters. Based on the analysis of the smelting process of EAF and the advantages of support vector machines, a soft sensor model for predicting the endpoint parameters was built using multiple support vector machines （MSVM）. In this model, the input space was divided by subtractive clustering and a sub-model based on LS-SVM was built in each sub-space. To decrease the correlation among the sub-models and to improve the accuracy and robustness of the model, the sub- models were combined by Principal Components Regression. The accuracy of the soft sensor model is perfectly improved. The simulation result demonstrates the practicability and efficiency of the MSVM model for the endpoint prediction of EAF.

Predicting the Acute Toxicity of Aromatic Amines by Linear and Nonlinear Regression Methods

In current paper, a quantitative structure-activity relationship （QSAR） study was performed for the prediction of acute toxicity of aromatic amines. A set of 56 compounds was randomly divided into a training set of 46 compounds and a test set of 10 compounds. The electronic and topological descriptors computed by the Scigress package and Dragon software were used as predictor variables. Multiple linear regression （MLR） and support vector machine （SVM） were utilized to build the linear and nonlinear QSAR models, respectively. The obtained models with five descriptors show strong predictive ability. The linear model fits the training set with R2 = 0.71, with higher SVM values of R2 = 0.77. The validation results obtained from the test set indicate that the SVM model is comparable or superior to that obtained by MLR, both in terms of prediction ability and robustness.

A Novel Hybrid FA-Based LSSVR Learning Paradigm for Hydropower Consumption Forecasting

Due to the nonlinearity and nonstationary of hydropower market data, a novel hybrid learning paradigm is proposed to predict hydropower consumption, by incorporating firefly algorithm （FA） into least square support vector regression （LSSVR）, i.e., FA-based LSSVR model. In the novel model, the powerful and effective artificial intelligence （AI） technique, i.e., LSSVR, is employed to forecast hydropower consumption. Furthermore, a promising AI optimization tool, i.e., FA, is espe- cially introduced to address the crucial but difficult task of parameters determination in LSSVR （e.g., hyper and kernel function parameters）. With the Chinese hydropower consumption as sample data, the empirical study has statistically confirmed the superiority of the novel FA-based LSSVR model to other benchmark models （including existing popular traditional econometric models, AI models and similar hybrid LSSVRs with other popular parameter searching tools）~ in terms of level and direc- tional accuracy. The empirical results also imply that the hybrid FA-based LSSVR learning paradigm with powerful forecasting tool and parameters optimization method can be employed as an effective forecasting tool for not only hydropower consumption but also other complex data.

Knowledge mining collaborative DESVM correction method in short-term load forecasting

Short-term forecasting is a difficult problem because of the influence of non-linear factors and irregular events.A novel short-term forecasting method named TIK was proposed,in which ARMA forecasting model was used to consider the load time series trend forecasting,intelligence forecasting DESVR model was applied to estimate the non-linear influence,and knowledge mining methods were applied to correct the errors caused by irregular events.In order to prove the effectiveness of the proposed model,an application of the daily maximum load forecasting was evaluated.The experimental results show that the DESVR model improves the mean absolute percentage error(MAPE) from 2.82% to 2.55%,and the knowledge rules can improve the MAPE from 2.55% to 2.30%.Compared with the single ARMA forecasting method and ARMA combined SVR forecasting method,it can be proved that TIK method gains the best performance in short-term load forecasting.

SVR-Boosting ensemble model for electricity price forecasting in electric power market

A revised support vector regression (SVR) ensemble model based on boosting algorithm (SVR-Boosting) is presented in this paper for electricity price forecasting in electric power market. In the light of characteristics of electricity price sequence, a new triangular-shaped 为oss function is constructed in the training of the forecasting model to inhibit the learning from abnormal data in electricity price sequence. The results from actual data indicate that, compared with the single support vector regression model, the proposed SVR-Boosting ensemble model is able to enhance the stability of the model output remarkably, acquire higher predicting accuracy, and possess comparatively satisfactory generalization capability.

A New Multi-Method Combination Forecasting Model for ESDD Predicting

Equal Salt Deposit Density (ESDD) is a main factor to classify contamination severity and draw pollution distribution map. The precise ESDD forecasting plays an important role in the safety, economy and reliability of power system. To cope with the problems existing in the ESDD predicting by multivariate linear regression (MLR), back propagation (BP) neural network and least squares support vector machines (LSSVM), a nonlinear combination forecasting model based on wavelet neural network (WNN) for ESDD is proposed. The model is a WNN with three layers, whose input layer has three neurons and output layer has one neuron, namely, regarding the ESDD forecasting results of MLR, BP and LSSVM as the inputs of the model and the observed value as the output. In the interest of better reflection of the influence of each single forecasting model on ESDD and increase of the accuracy of ESDD prediction, Morlet wavelet is used to con-struct WNN, error backpropagation algorithm is adopted to train the network and genetic algorithm is used to determine the initials of the parameters. Simulation results show that the accuracy of the proposed combina-tion ESDD forecasting model is higher than that of any single model and that of traditional linear combina-tion forecasting (LCF) model. The model provides a new feasible way to increase the accuracy of pollution distribution map of power network.

Intelligent Forecasting of Sintered Ore’s Chemical Components Based on SVM

Using object mathematical model of traditional control theory can not solve the forecasting problem of the chemical components of sintered ore.In order to control complicated chemical components in the manufacturing process of sintered ore,some key techniques for intelligent forecasting of the chemical components of sintered ore are studied in this paper.A new intelligent forecasting system based on SVM is proposed and realized.The results show that the accuracy of predictive value of every component is more than 90%.The application of our system in related companies is for more than one year and has shown satisfactory results.

Forecasting stock closing prices with an application to airline company data

Forecasting stock market movements is a challenging task from the practitioners’point of view.We explore how model selection via the least absolute shrinkage and selection operator(LASSO)approach can be better used to forecast stock closing prices using real-world datasets of daily stock closing prices of three major international airlines.Combining the LASSO method with multiple external data sources in our model leads to a robust and efficient method to predict stock behavior.We also compare our approach with ridge,tree,and support vector machine regressions,as well as neural network approaches to model the data.We include lags of each external variable and response variable in the model,resulting in a total of 870 predictor variables.The empirical results indicate that the LASSO-fitted model is the most effective when compared to other approaches we consider.The results show that the closing price of an airline stock is affected by its closing price for the previous days and those of other types of airlines and is significantly correlated with the Shanghai Composite Index for the previous day and 3 days prior.Other influencing factors include the positive impact of the Shanghai Composite Index daily share volume,the negative impact of loan interest rates,the amount of highway passenger and railway freight turnover,etc.

基于新闻情感分析和区间分解的汇率预测研究

汇率序列具有非线性和连续变化等特点,其细节波动是一系列事件和新闻综合影响的结果.然而,现有区间预测模型难以量化重大事件和公众情绪的影响,导致其缺乏广泛的适用性,且传统区间分解方法存在上下界混叠的缺陷.因此,论文从新冠疫情冲击出发,提出一种基于新闻情感分析和区间分解的汇率波动实时预测模型.首先,基于Snownlp情感词典对外汇新闻文本进行情感分析,获得相应的情感分数.另外,构建全球恐惧指数(the global fear index,简称GFI)以量化新冠疫情的影响,并将其与芝加哥期权交易所波动率(the Chicago board options exchange volatility index,简称VIX指数)相结合作为汇率的影响因素.然后,提出一种新的区间经验模态分解(interval empirical mode decomposition,简称IEMD)方法对区间汇率序列进行多尺度分解,并根据样本熵重构得到高、中、低频区间序列和残差项.其次,利用极限学习机(extreme learning machine,简称ELM)、多层感知机(multi-layer perceptron,简称MLP)、随机森林(random forest,简称RF)和二次曲面支持向量回归(quadric surface support vector regression,简称QSSVR)分别对不同特征的子序列进行组合预测,以提高预测结果的准确性和稳定性.最后,利用论文方法对美元兑人民币、澳元兑人民币和瑞士法郎兑人民币3种汇率进行实证预测分析,结果表明,论文模型适用于重大事件影响下的汇率区间波动预测,与现有方法相比具有较高的预测精度.

基于图像处理的水培生菜冠层图像叶面积估测研究

为实现精准、高效、无损地获取植物工厂环境下水培生菜相关长势参数叶面积(Leaf area,LA),基于数字图像处理和机器学习回归方法建立单株水培生菜冠层图像LA估测模型。首先,通过智能手机获取2个生菜品种不同生长期的冠层可见光图像,利用Photoshop图像处理软件将原始图像统一剪裁为900像素×900像素大小,采用中值滤波(MedianBlur)法对剪裁后的图像进行去噪运算,将RGB图像转化为HSV颜色空间,再采用mask掩膜法分割彩色图像;然后,利用图像法获取单株生菜LA实测值,构建以LA实测值为因变量,以生菜冠层投影面积(Projected leaf area,PLA)为自变量的线性回归(Linear regression,LR)模型和以全局图像特征(颜色、形状、纹理等)为自变量的支持向量回归(Support vector regression,SVR)、多元线性回归(Multiple linear regression,MLR)和随机森林(Random forest,RF)等LA估测模型进行对比分析;最后,采用决定系数(Coefficient of determination,R^(2))和均方根误差(Root mean square error,RMSE)评估模型的准确性。结果表明:RF模型估测效果最好,对于生菜品种‘绿萝’单株LA估测结果的R^(2)为0.9714、RMSE为8.89 cm2,对于品种‘碧霄’估测结果的R^(2)为0.9201、RMSE为23.34 cm2。本研究验证了RF回归模型能够较准确地估测生菜单株叶面积,可为植物工厂水培生菜LA无损估测提供新的解决方案和研究基础。

微胶囊相变材料改良粉砂土的导热系数及预测模型

【目的】针对季节冻土地区渠道冻融破坏,分析微胶囊相变材料(microencapsulated phase change materials,mPCM)改良粉砂土层渠基的温度场,对改良粉砂土的导热系数进行研究。【方法】以mPCM为改良剂,掺入渠基粉砂土形成mPCM改良粉砂土;对mPCM改良粉砂土进行导热系数实验和内部结构表征;采用多元线性回归和支持向量机(support vector machine,SVM)方法分别建立mPCM改良粉砂土的导热系数预测模型。【结果】mPCM改良粉砂土导热系数与含水率、干密度、mPCM掺量有关,且受冰水相对含量、冰水相变潜热、mPCM相变潜热和mPCM填充密实作用的影响,具有明显的温度效应;mPCM改良粉砂土导热系数的变化与实验温度和mPCM相变温度有关,可分为快速降低、缓慢降低和逐步上升3个阶段;多元线性回归和SVM模型均能较好地拟合预测mPCM改良粉砂土的导热系数,但SVM模型更适用于表征mPCM改良粉砂土导热系数各影响因素间的非线性关系。【结论】mPCM改良粉砂土的导热系数提高能够有效调控渠基土温度场,减轻渠道冻害,且SVM模型能更加准确地进行导热系数预测。