Standard forecasting criteria like the mean square error (MSE) compare point forecasts or a location parameter of the forecasting distribution with actual observations. Such criteria are less suited to comparing forecasts of volatile time series. Therefore we use the average predictive ordinate (APOC) criterion which evaluates the ordinate of the predictive distribution. Using the comparison to...

A traffic condition forecasting system using floating car data in conjunction with a data mining method is proposed. A register network is used to describe the congestion model. The register network denotes the dual graph of the actual road link connections. In this forecasting system, estimation and learning agents alternately calculate the results to improve the forecasting accuracy. To forec...

In this paper, the application of neural networks to study the design of short-term load forecasting (STLF) Systems for Illam state located in west of Iran was explored. One important architecture of neural networks named Multi-Layer Perceptron (MLP) to model STLF systems was used. Our study based on MLP was trained and tested using three years (2004-2006) data. The results show that MLP networ...

Short term load forecasting can be made effective and closer to actual demand by applying the suggested multi pronged approach of genetic, fuzzy and statistical method as discussed in this paper. Taking the advantages of global search abilities of evolutionary computing as well as expert inference based on statistical aspects, load forecasting can be made nearly error free. The results were com...

1 S. Singh and E. Stuart. A Pattern Matching Tool for Forecasting, Proc. 14th International Conference on Pattern Recognition (ICPR'98), Brisbane, IEEE Press, vol. 1, pp. 103-105 (August 16-20, 1998) . ABSTRACT In this paper we describe a pattern recognition based tool for forecasting. We compare the results of forecasting with this tool against the Exponential smoothing method on Santa Fe seri...

b a c k g r o u n d & aim: one of the common used models in time series is auto regressive integrated moving  average  (arima)  model.  arima  will  do  modeling  only  linearly.  artificial  neural networks (ann) are modern methods that be used for time series forecasting.  these models can identify non-linear relationships  among data. the breast cancer has the most mortality of cancers among...

In the context of the GEOLAND EC FP6 project the comparison of different remote sensing based approaches for yield forecasting over large areas in Europe are tested and results inter-compared. In particular the methods tested include the ones in use within the MARS-Crop Yield Forecasting System as the results from the Crop Growth Monitoring System model and vegetation indicators derived from Lo...

The purpose – Accurately forecasting the demand for international health tourism is important to newly-emerging markets in the world. The aim of this study was presents a more suitable and accurate model for forecasting the demand for health tourism that should be more theoretically useful. Design – Applying GM(1,1) with adaptive levels of α (hereafter GM(1,1)-α model) to provide a concise pred...

In this paper, we developed a new method to forecast 10minutes ahead wind speed based on Heteroscdastic Gaussian Process and investigated the impacts of this predicting on a mix-mode operated building. The forecasting result shows the mean absolute percentage error (MAPE) of 9.2%. The indoor air temperature, infiltration air change rate and cooling energy consumption varied 25% in average compa...