Forecasting By Neural Networks In The Wavelet Domain
Journal Title: Acta Technica Napocensis- Electronica-Telecomunicatii (Electronics and Telecommunications) - Year 2009, Vol 50, Issue 4
Abstract
This paper presents a forecasting method for time series. This method combines the wavelet analysis and several forecasting techniques such as Artificial Neural Networks (ANN), linear regression and random walk. The proposed method is tested using three real time series: the first contains historical data recorded during eight weeks from a WiMAX network and the other two are based on financial series. It is shown that AI with wavelet analysis can be an efficient and versatile approach in time series prediction for small periods time interval (up to 1 month). For long time interval, the best method used is Linear Regression technique. Also we compared the results obtained using various types of wavelets. The results show that Daubechies 1 (db1) and Reverse biorthogonal 1 (rbio1.1) give the best results.
Authors and Affiliations
Ion RĂILEAN, Sorin MOGA, Monica BORDA
Keywords
Related Articles
- EP ID EP113236
- DOI -
- Views 115
- Downloads 0
Comparison of LMS algorithm derivatives using LabVIEW FPGA
The LMS algorithm derivatives have found wide application in many areas of adaptive signal processing and control. In this paper we study the tracking performance of the LMS derivatives in adaptive noise cancellation for...
3D Surface Recunstruction and Comparaison System Used For Marking Local Defects of Tested Objects
Nowadays automatic 3D acquisition systems allow building accurate models of real 3D objects in a cost- and time-effective manner. This technology was used in a particular application context: shape defects detection. Sp...
TLS Protocol: Secure Protocol With Client Puzzles
Client puzzles are commonly proposed as a solution to denial-of-service attacks. We analyzed the TLS protocol and implement Client Puzzles algorithm. We pursued the following objectives: analyze TLS handshake protocol...
Overview of the Cross-Layer Paradigm Evolving Towards Future Internet
The spectacular evolution of Internet services has requested significant improvements of the performances in communications networks. Cross-layering techniques have been selected as one of the most important issues in re...
A New Approach To Signal Reflections Analysis On PCB Transmission Lines Terminated On Nonlinear Impedances
A novel approach for analyzing signal reflections on transmission lines terminated on non-linear impedances is presented. The starting point of this new method is the Bergeron diagram method. The results obtained by the...