In our research, we introduce the wavelet transform, WT, to establish the regression. Owning to the ability of handling noise signal, we decided to choose WT as the data-preprocessor. Allpying the multi-resolution analysis, MRA, of WT to decompose every factor into different scaled series. After that, we take the reconstructed series to be new regression model. The proposed method is evaluated via TAIEX¤Îeconomical factors. The result shows that the WT is better explaining the economical factors than the traditional regression model.

Marburg, Univ., Diss., 2002. / Computerdatei im Fernzugriff.

Duisburg, Universiẗat, Diss., 1999. / Dateiformat: zip, Dateien im PDF-Format.

Marburg, Universiẗat, Diss., 2002.

Bremen, Univ., Diss., 2006

Mannheim, Univ., Diss., 2005.

In recent years wavelet image compression technology has rapidly reached its maturity, and become a method of choice for still image compression. Integer reversible wavelet transforms allow both lossless and lossy decoding using a single bitstream. We present a new fully progressive image coder and investigate the lossless and near-lossless performance of these transforms in the propose coder. In this thesis, we studied the architecture and theories of the more and more important function, progressive transmission, in the image compression. The theory of wavelet transform is discussed and the implementation method using filter is explained. After doing wavelet transform, the codec transmit the wavelet coefficient to our proposed method call I-LOCO-I to compression. Here, the proposed I-LOCO-I near-lossless compression is provided by a simple quantization of the image prior to lossless or near-lossless coding and with high compression ratio and has fairly good PSNR 51.6. It will first present a preview image after error correction. That compression ratio of I-LOCO-I with Doubaches 5/3 wavelet transform is better than LOCO-I about 15%. If I-LOCO-I without wavelet transform, its compression ratio can achieve 23%.

An electrocardiogram (ECG) is a bioelectrical signal which records the heart’s electrical activity versus time on the body surface via contact electrodes. The recorded ECG signal is often contaminated by noise and artifacts that can be within the frequency band of interest. This noise can hide some important features of the ECG signal. The focus of this thesis is the application of new modified versions of the Universal threshold to allow additional enhancements in the reduction of ECG noise. Despite the fact that there are many types of contaminating noises in ECG signals, only white noise and baseline wandering will be considered. This type of noise is undesirable and needs to be removed prior to any additional signal processing for proper analysis and display of the ECG signal.

Stuttgart, Univ., Diss., 2005.

University, Diss., 2002--Mannheim. / Erscheinungsjahr an der Haupttitelstelle: 2001.