The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this empirical study we develop forecasting models for electricity demand using publicly available data and three models based on machine learning algorithms. It compares accuracy of these models using different evaluation metrics. The data consist of several measurements and observations related to the electricity market in Turkey from 2011 to 2016. It is available in different time granularities...
This study aims to present time series-based forecasting for Malaysian crude palm oil prices using neural network algorithms. Daily prices of soy bean oil and currency exchange rates are tested as input features, in addition to crude palm oil prices. Efforts are focused on finding the optimal network structures for the modelling of crude palm oil price forecasting. Neural network structures with an...
In a competitive electricity market, an accurate forecasting of energy prices is an important activity for all the market participants. This paper proposes a novel approach based on Neural Networks for forecasting energy prices. Two different architectures of Neural Networks are used. In particular, Multi-Layer Perceptron (MLP) and Fully Connected Neural (FCN) networks are designed, calibrated and...
Seawater chlorophyll-a (Chla) represents algal biomass in ocean and is a major index of eutrophication. In this paper, bootstrapped artificial neural network (BANN) model is developed for predicting the seawater Chla concentration around the north Pacific Rim. Three-layer ANN structure is applied and the modeling is based on comprehensive five-minute interval datasets of water temperature, depth,...
The worldwide increase in the integration of photovoltaic generation has necessitated improvements in the forecasting approaches. Two models are proposed to cater for PV generation forecasts for few minutes to several hours look-ahead times. A very fast and accurate prediction model based on extreme learning machine is deployed for day-ahead prediction. Moreover, an adaptive and sequential model is...
Demand forecasting plays a very important role in retail business. Retail information systems commonly store large amounts of data which are subsequently used by sophisticated data mining tools for building forecasting models. Quality of these models is usually measured through their predictive accuracy as their most important property, followed by other measures which consider average underestimate...
This paper discusses simple methods for forecasting solar irradiation. We use the zenith angle (the angle between sun beam and perpendicular line on horizontal surface) to remove both seasonal and time of day effects. Then we forecast by using least-squares (LS), time-varying least squares (TVLS), exponentially weighted recursive least squares (EWRLS) and one step estimation of second order statistics...
Forecasting the volatility of multivariate asset return is an important issue in financial econometric analysis, where the volatility is represented by a conditional covariance matrix (CCM). Traditional models for predicting CCM such as GARCH(1, 1) models are not capable of dealing with high-dimensional case for there are $N(N+1)/2$ necessary entries in the CCM of $N$-variant asset return. We propose...
Stock price fluctuation in stock markets is a very important issue in financial researches. However, the information in stock markets of China is too much to analysis. Fractal theory is an important modern branch of nonlinear science. Neural network has a strong nonlinear approximation ability and self-organizing, adaptive features. Based on fractal theory, the Shanghai integrated index are chosen...
The per capita ecological footprint (EF) is one of the most-widely recognized measures of environmental sustainability. It tries to quantify the earth's biological capacity required to support human activity. This study at first summarize the previous literature, and then present the five factors which influenced the per capita EF, they are the nation's GDP, urbanization independent of economic development,...
This study proposed a novel HPSO-SVR model that hybridized the particle swarm optimization (PSO) and support vector regression (SVR) to improve the regression accuracy based on the type of kernel function and kernel parameter value optimization with a small and appropriate feature subset, which is then applied to forecast the monthly rainfall. This optimization mechanism combined the discrete PSO...
Inflation is one of the most important macroeconomic variables. However, the behavior of inflation is so complicated that both economists and statisticians have strived to model and forecast inflation for years. In this study, the linear AS-AD model and nonlinear artificial neural network (ANN) technique are both employed to have a better understanding of the inflation behavior in China from 1992...
Based on the real data of a Chinese commercial bank's credit card, in this paper, we classify the credit card customers into four classifications by K-means. Then we built forecasting models separately based on four data mining methods such as C5.0, neural network, chi-squared automatic interaction detector, and classification and regression tree according to the background information of the credit...
Determining of the torpedo's service year reasonably, it is an effective way to reduce the military expenses expenditure, and forecast the torpedo economic life. We can forecast the data of exponential use maintenance cost by using the grey metabolism GM(1,1) model. In order to improve the prediction precision, the data was divided into several groups, and prediction residual was modified by using...
This article presents a new classification approach to inventory risk level of spare parts which based on the support vector machine classification principle. First, a fuzzy evaluation of spare parts is made in terms of their availability of suppliers, importance, predictability of failure, specificity and lead time. Then a one versus one classification machine model is established. Choosing a sample...
At present, research on nonlinear network flows of mobile short message is one hotspot in mobile communications fields. Nonlinear network flows of mobile short message have such essential features varying with time as periodicity, regularity, correlation, randomicity, occasionality. The traditional methods based on linear models are successful relatively in making irregular flow series become more...
In this paper, we propose a novel artificial neural network ensemble rainfall forecasting model based K-nearest neighbor (K-nn) nonparametric estimation of regression. In this model, original data set are partitioned into some different training subsets via Bagging technology. Then using different ANNs algorithms and different network architecture generate diverse individual neural network ensemble...
Nowadays, many researches are made to estimate some of socio-economic variables in which methods such as regression, time series (ARIMA, AR and etc.), Artificial Neural Networks (ANN) and so on are used. In this paper integrated System Approach and ANN are applied for estimating affects of subsidy on electricity consumption and social welfare. Actual electricity price is estimated by ANN, which has...
The accurate and reliable Trip-generation Forecasting Model is the most basic and important part of the traffic forecasting model. This paper focuses on combining the neural network which has a strong fitting capability and genetic algorithm which has an excellent Global search capability with trip-generation forecasting model in order to achieve the purpose of improving the accuracy of prediction...
The tolerance and non-stability in financial indexes make changes to other sub-systems like human resources, economics, factory productions and etc. Having underling knowledge and a model to simulate such systems obtains a fine vision to estimate further and calculate hard-decision making tasks before execution like: dept from banks, cash injecting and insurance services. Using Neuro-fuzzy networks...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.