A new fast forecasting technique using high speed neural networks

Forecasting is an important issue for many different applications. In this paper, a new efficient forecasting technique is presented. Such technique is designed by using fast neural networks (FNNs). The new idea relies on performing cross correlation in the frequency domain between the input data and the input weights of neural networks. It is proved mathematically and practically that the number of computation steps required for the proposed fast forecasting technique is less than that needed by conventional neural-based forecasting. Simulation results using MATLAB confirm the theoretical computations. The proposed fast forecasting technique increases the prediction speed and at the same time does not affect the predication accuracy. It is applied professionally for erythemal ultraviolet irradiance prediction.

[1]  Hazem M. El-Bakry,et al.  A New Implementation for High Speed Normalized Neural Networks in Frequency Space , 2008, KES.

[2]  Qiangfu Zhao,et al.  Sub-Image Detection Using Fast Neural Processors and Image Decomposition , 2005, WEC.

[3]  Teruyuki Nakajima,et al.  Modelling radiation quantities and photolysis frequencies in the troposphere , 1994 .

[4]  Ian Witten,et al.  Data Mining , 2000 .

[5]  Hazem M. El-Bakry A New Implementation of PCA for Fast Face Detection , 2008 .

[6]  Reinhard Klette,et al.  Handbook of image processing operators , 1996 .

[7]  Hazem M. El-Bakry New Fast Principal Component Analysis for Face Detection , 2007, J. Adv. Comput. Intell. Intell. Informatics.

[8]  Uwe Feister,et al.  Reconstruction of daily solar UV irradiation by an artificial neural network (ANN) , 2006, SPIE Remote Sensing.

[9]  P. Bhartia,et al.  UV‐B increases (1979–1992) from decreases in total ozone , 1996 .

[10]  U. Feister,et al.  Parameterization of Daily Solar Global Ultraviolet Irradiation¶ , 2002, Photochemistry and photobiology.

[11]  P. Bhartia,et al.  Nimbus-7 Total Ozone Mapping Spectrometer (TOMS) Data Products User`s Guide , 1993 .

[12]  H.M. El-Bakry Human iris detection using fast cooperative modular neural nets , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[13]  Sensitivity of solar UV radiation to ozone and temperature profiles at Thessaloniki (40.5°N, 23°E), Greece , 2005 .

[14]  Hazem M. El-Bakry,et al.  New faster normalized neural networks for sub-matrix detection using cross correlation in the frequency domain and matrix decomposition , 2008, Appl. Soft Comput..

[15]  Qiangfu Zhao,et al.  A Modified Cross Correlation in the Frequency Domain for Fast Pattern Detection Using Neural Networks , 2007 .

[16]  Qiangfu Zhao,et al.  A Fast Neural Algorithm for Serial Code Detection in a Stream of Sequential Data , 2008 .

[17]  Nikos E. Mastorakis,et al.  New fast normalized neural networks for pattern detection , 2007, Image Vis. Comput..

[18]  Qiangfu Zhao,et al.  Speeding-up normalized neural networks for face/object detection , 2005 .

[19]  B. Mayer,et al.  Estimation of surface actinic flux from satellite (TOMS) ozone and cloud reflectivity measurements , 1998 .

[20]  Y. A. Azzam,et al.  Testing the applicability of artificial intelligence techniques to the subject of erythemal ultraviolet solar radiation. Part two: an intelligent system based on multi-classifier technique. , 2008, Journal of photochemistry and photobiology. B, Biology.

[21]  Ultraviolet radiation in partly snow covered terrain: Observations and three‐dimensional simulations , 2001 .

[22]  Frederick Urbach,et al.  A CLIMATOLOGY OF SUNBURNING ULTRAVIOLET RADIATION , 1982, Photochemistry and photobiology.

[23]  A. J. Miller,et al.  Global and zonal total ozone variations estimated from ground‐based and satellite measurements: 1964–2000 , 2002 .

[24]  Hazem M. El-Bakry,et al.  Fast Normalized Neural Processors for Pattern Detection Based on Cross Correlation Implementation in the Frequency Domain , 2006, J. Res. Pract. Inf. Technol..

[25]  Qiangfu Zhao,et al.  Fast Object/Face Detection Using Neural Networks and Fast Fourier Transform , 2007 .

[26]  Costas A. Varotsos,et al.  Erythemally weighted UV trends over northern latitudes derived from Nimbus 7 TOMS measurements , 2000 .

[27]  Torsten Rohlfing,et al.  Multi-classifier framework for atlas-based image segmentation , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[28]  P. Winkler,et al.  A method to derive long‐term time series and trends of UV‐B radiation (1968–1997) from observations at Hohenpeissenberg (Bavaria) , 2000 .

[29]  J. Moan,et al.  ULTRAVIOLET‐RADIATION and SKIN CANCER. EFFECT OF AN OZONE LAYER DEPLETION , 1990, Photochemistry and photobiology.

[30]  A. Bais,et al.  Measurements and modeling of photolysis rates during the Photochemical Activity and Ultraviolet Radiation (PAUR) II campaign , 2002 .

[31]  HAZEM M. EL-BAKRY,et al.  Fast time delay neural networks , 2005, Int. J. Neural Syst..

[32]  J. Cañada,et al.  Correlation between global ultraviolet (290–385nm) and global irradiation in Valencia and Cordoba (Spain) , 2003 .

[33]  Akira Hirose,et al.  Complex-Valued Neural Networks: Theories and Applications , 2003 .

[34]  Qiangfu Zhao,et al.  Fast Pattern Detection Using Normalized Neural Networks and Cross-Correlation in the Frequency Domain , 2005, EURASIP J. Adv. Signal Process..

[35]  H. Elminir Dependence of urban air pollutants on meteorology. , 2005, The Science of the total environment.

[36]  Jianpei Zhang,et al.  A New Multiple Classifiers Combination Algorithm , 2006, First International Multi-Symposiums on Computer and Computational Sciences (IMSCCS'06).

[37]  D. W. Nelson,et al.  A model to extend spectral and multiwavelength UV irradiances time series: Model development and validation , 2003 .

[38]  Nikos E. Mastorakis,et al.  Fast Code Detection Using High Speed Time Delay Neural Networks , 2007, ISNN.

[39]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[40]  S. M. Robaa A study of ultraviolet solar radiation at Cairo urban area, Egypt , 2004 .

[41]  Philipp Weihs,et al.  Accuracy of spectral UV model calculations: 1. Consideration of uncertainties in input parameters , 1997 .

[42]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[43]  Hazem M. El-Bakry Automatic human face recognition using modular neural networks , 2001 .

[44]  D. W. Nelson,et al.  Estimated and measured DNA, plant-chromosphere and erythemal-weighted irradiances at Barrow and South Pole (1979–2000) , 2003 .

[45]  Qiangfu Zhao,et al.  Modified time delay neural networks for fast data processing , 2005, Proceedings of the Eighth International Symposium on Signal Processing and Its Applications, 2005..

[46]  Hazem M. El-Bakry,et al.  Fast Pattern Detection Using Neural Networks Realized in Frequency Domain , 2005, WEC.

[47]  Hazem M. El-Bakry New Fast Time Delay Neural Networks Using Cross Correlation Performed in the Frequency Domain , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[48]  Hazem M. El-Bakry Face detection using fast neural networks and image decomposition , 2002, Neurocomputing.

[49]  Soteris A. Kalogirou,et al.  Applications of artificial neural networks in energy systems , 1999 .

[50]  Antti Arola,et al.  Long-term erythemal UV doses at Sodankylä estimated using total ozone, sunshine duration, and snow depth , 2003 .

[51]  Sami D. Alaruri The empirical relationship between global radiation and global ultraviolet (0.290–0.385) μm solar radiation components , 1990 .

[52]  Hazem M. El-Bakry New High Speed Normalized Neural Networks for Fast Pattern Discovery on Web Pages , 2006 .

[53]  Yetis Sazi Murat,et al.  Comparison of fuzzy logic and artificial neural networks approaches in vehicle delay modeling , 2006 .

[54]  Torsten Hothorn,et al.  Bundling Classifiers by Bagging Trees , 2002, Comput. Stat. Data Anal..

[55]  Akira Hirose Complex-Valued Neural Networks , 2006, Studies in Computational Intelligence.

[56]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[57]  Weine Josefsson,et al.  Long‐term variations of UV‐B doses at three stations in northern Europe , 2000 .