Wavelet Decomposition

In this paper, we investigate the effectiveness of a financial time-series forecasting strategy which exploits the mul- tiresolution property of the wavelet transform. A financial series is decomposed into an over complete, shift invariant scale-related representation. In transform space, each individual wavelet series is modeled by a separate multilayer perceptron (MLP). To better utilize the detailed information in the lower scales of wavelet coef- ficients (high frequencies) and general (trend) information in the higher scales of wavelet coefficients (low frequencies), we applied the Bayesian method of automatic relevance determination (ARD) to choose short past windows (short-term history) for the inputs to the MLPs at lower scales and long past windows (long-term history) at higher scales. To form the overall forecast, the indi- vidual forecasts are then recombined by the linear reconstruction property of the inverse transform with the chosen autocorrelation shell representatio...

... MU-WEI JIAN1, JUN-YU DONG1, JIA-HUA (JERRY) WU 2 ... 2 Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Hinxton Cambridge, United Kingdom E-MAIL: dongjunyu@ouc.edu.cn, jianmuwei@sohu.com, jerry.wu@sanger ... [5] Jian, Muwei; Dong, Junyu; ...

As health care centres have becomes popular, daily monitoring of health-status related parameters is becoming important. An easy, comfortable and patient friendly solution for acquisition, processing and remotely transmitting the information from patient to the centre is therefore an important issue. Phonocardiogram (PCG) is a physiological signal reflecting the cardiovascular status. This paper deals with a Signal Processing Module for the computer-aided analysis of the condition of heart. The module has three main blocks: Data Acquisition, Signal Processing & Remote Monitoring of heart sounds. Data acquired includes the heart sounds. The system integrates embedded internet technology and wireless technology. As the data is being send by internet, it realizes real-time recording and monitoring of physiological parameter of patients at low cost and both at home and in hospital. The analysis can be carried out using computer initially and further by doctor. The tele-monitoring system...

This study is included in the framework of Health Smart Homes which monitor some physiological or not physiological parameters of elderly people living independently at home. In this study we will focus on the walk detection. Walk activity is one parameter to evaluate the health of patient. For example, the total time of walk during a day allows assessing quickly if the subject is mobile rather than immobile. To reach this goal we used a kinematic sensor placed on the chest recording the movements of the subject. The data are analyzed by six algorithms to detect walk phases: two based on Fourier analysis and the others using a wavelet decomposition (DWT and CWT). All algorithms are described and the performances are evaluated on real data recorded with 20 elderly people. Results show that the method using the DWT decomposition is the most efficient (78.5% in sensitivity and 67.6% in specificity).

We present results from a Chandra survey of the nine square degree Bootes field of the NOAO Deep Wide-Field Survey (NDWFS). This XBootes survey consists of 126 separate contiguous ACIS-I observations each of approximately 5000 seconds in duration. These unique Chandra observations allow us to search for large scale structure and to calculate X-ray source statistics o ver a wide,

Present developments in Nuclear Magnetic Resonance (NMR) imaging techniques strive for improved spatial and temporal resolution performances. However, trying to achieve the shortest gradient rising time with high intensity gradients has its drawbacks: It generates high amplitude noises that get superimposed on the simultaneously recorded electrophysiological signals, needed to synchronize moving organ images. Consequently, new strategies have to be developed for processing these collected signals during Magnetic Resonance Imaging (MRI) examinations. The aim of this work is to extract an efficient reference signal, from an electrocardiogram (ECG) that was contaminated by the NMR artefacts. This may be used for image triggering and/or cardiac rhythm monitoring. Our method, based on sub-band decomposition using wavelet filters, is tested on various ECG signals recorded during three imaging sequences: Gradient Echo (GE), Fast Spin Echo (FSE) and Inversion Recovery with Spin Echo (IRSE)....

... a semisupervised oil-slick detection is proposed by using a kernel-based abnormal detection into the wavelet decomposition of ... ENST Bretagne), ITI Department, CNRS UMR 2872 TAMCIC, TIME team, CS 83818, 29238 Brest Cedex, France (e-mail: gregoire.mercier@enst ...

In this paper we expose new method to analyse time series. The method is essentially applied for the prediction of time series among approximation and modelisation. It is based on wavelet decomposition combined with autoregressive models. An iterative procedure is applied and the performance of the estimator is measured by standardized error. Finally, a comparison with some existing models and methods has been pointed out to prove the performance of our’s.

In applications, choices of orthonormal bases in Hilbert space H may come about from the simultaneous diagonalization of some specific abelian algebra of operators. It was noticed recently that there is a certain finite set of non-commuting operators F_i, first introduced by engineers in signal processing, which helps to clarify this connection, and at the same time throws light on decomposition possibilities for wavelet packets used in pyramid algorithms. While the operators F_i were originally intended for quadrature mirror filters of signals, recent papers have shown that they are ubiquitous in a variety of modern wavelet constructions, and in particular in the selection of wavelet packets from libraries of bases. These are constructions which make a selection of a basis with the best frequency concentration in signal or data-compression problems. While the algebra A generated by the F_i-system is non-abelian, and goes under the name "Cuntz algebra" in C*-algebra theory...

This paper deals with the problem of saliency map estimation in computational models of visual attention. In particular, we propose a wavelet based approach for efficient computation of the topographic feature maps. Given that wavelets and multiresolution theory are naturally connected the usage of wavelet decomposition for mimicking the center surround process in humans is an obvious choice. However, our proposal goes further. We utilize the wavelet decomposition for inline computation of the features (such as orientation) that are used to create the topographic feature maps. Topographic feature maps are then combined through a sigmoid function to produce the final saliency map. The computational model we use is based on the Feature Integration Theory of Treisman et al and follows the computational philosophy of this theory proposed by Itti et al. A series of experiments, conducted in a video encoding setup, show that the proposed method compares well against other implementations found in the literature both in terms of visual trials and computational complexity.