Artificial neural networks (ANNs) have been widely used as a promising alternative approach for forecast task because of their several distinguishing features. In this paper, we investigate the effect of different sam...Artificial neural networks (ANNs) have been widely used as a promising alternative approach for forecast task because of their several distinguishing features. In this paper, we investigate the effect of different sampling intervals on predictive performance of ANNs in forecasting exchange rate time series. It is shown that selection of an appropriate sampling interval would permit the neural network to model adequately the financial time series. Too short or too long a sampling interval does not provide good forecasting accuracy. In addition, we discuss the effect of forecasting horizons and input nodes on the prediction performance of neural networks.展开更多
Perforated walls and transpiration flow play an important role in aerodynamics due to an increasing interest in application of flow control by means of blowing and/or suction. An experimental study was carried out whi...Perforated walls and transpiration flow play an important role in aerodynamics due to an increasing interest in application of flow control by means of blowing and/or suction. An experimental study was carried out which has led to the determination of a transpiration flow characteristics in the form of a simple formula that is very useful in modelling such flows. In connection to this relation a method of 'aerodynamic porosity' determination has been proposed which is much more reliable than geometric description of the porosity. A theoretical analysis of the flow through a perforation hole was also carried out. The flow was considered as compressible and viscous. The gasdynamic analysis led us to a very similar result to the relation obtained from the experiment. The adequacy of the theoretical result is discussed in respect to the experiment.展开更多
基金This research is Partially supported by NSFC, CAS. MADIS and RGC of Hong Kong.
文摘Artificial neural networks (ANNs) have been widely used as a promising alternative approach for forecast task because of their several distinguishing features. In this paper, we investigate the effect of different sampling intervals on predictive performance of ANNs in forecasting exchange rate time series. It is shown that selection of an appropriate sampling interval would permit the neural network to model adequately the financial time series. Too short or too long a sampling interval does not provide good forecasting accuracy. In addition, we discuss the effect of forecasting horizons and input nodes on the prediction performance of neural networks.
文摘Perforated walls and transpiration flow play an important role in aerodynamics due to an increasing interest in application of flow control by means of blowing and/or suction. An experimental study was carried out which has led to the determination of a transpiration flow characteristics in the form of a simple formula that is very useful in modelling such flows. In connection to this relation a method of 'aerodynamic porosity' determination has been proposed which is much more reliable than geometric description of the porosity. A theoretical analysis of the flow through a perforation hole was also carried out. The flow was considered as compressible and viscous. The gasdynamic analysis led us to a very similar result to the relation obtained from the experiment. The adequacy of the theoretical result is discussed in respect to the experiment.
