Issue 10 Volume 41 May 16, 2003
Issue 10 Volume 41 May 16, 2003
Issue 10 Volume 41 May 16, 2003
- TAGS
- volume
- 202.118.250.135
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
<strong>2003</strong>0032957 Silesian Technical Univ., Gliwice<br />
A New Approach to the P-Wave Detection and Classification Based Upon Application of Wavelet Neural Network<br />
Domider, T.; Tkacz, E. J.; Kostka, P.; Wrzesniowski, A.; Oct 2001; 4 pp.; In English<br />
Report No.(s): AD-A4<strong>10</strong>247; No Copyright; Avail: CASI; A01, Hardcopy<br />
Paper presents a new approach to P wave classification problem which is based upon the application of a new recently<br />
develop and widely described tool such as Wavelet Neural Network, The novel idea of classification is based on creation of<br />
own non-standard wavelet exactly as a P wave morphology template and then calculation of wavelet transform being a first<br />
layer of classical multi-layer perceptron. The mentioned first layer works as a feature selector and extractor.<br />
DTIC<br />
Neural Nets; Wavelet Analysis; Electrocardiography<br />
<strong>2003</strong>0032986 Sophia Univ., Tokyo<br />
Reconstruction of Bio-Conductivity Distribution from Tangential Magnet Field Measurements<br />
Sumi, C.; Nagumo, K.; Oct 2001; 7 pp.; In English<br />
Report No.(s): AD-A4<strong>10</strong>5<strong>10</strong>; No Copyright; Avail: CASI; A02, Hardcopy<br />
We proposed a technique for reconstructing bio-electric conductivity distribution from measured tangential magnet field<br />
data. That is, in the 2D ROI with an arbitrary depth two orthogonal tangential components of 3D current vector field were<br />
respectively estimated from the synthetically measured two tangential magnetic fields, from which the 2D conductivity<br />
distribution was estimated. To cope with inevitable measurement errors, a robust numerical solution was developed, in which<br />
the modification method and the regularization method were efficiently utilized. By performing this 2D reconstruction at each<br />
depth, 3D conductivity distribution could be estimated. As typical applications, pathological state and/or bio-electric<br />
conductive path can be evaluated by monitoring the temporal change of the reconstructed 3D conductivity distribution. The<br />
feasibility of this technique was briefly verified by reconstructing a conductivity distribution using simulated noise-filled<br />
magnetic field data, with resultant reconstruction indicating that the approach could provide a practical means for robustly<br />
reconstructing a conductivity distribution.<br />
DTIC<br />
Bioelectricity; Magnetic Fields; Electrical Resistivity; Numerical Analysis; Estimating<br />
<strong>2003</strong>0033<strong>10</strong>1 Aristotle Univ. of Thessaloniki, Greece<br />
Alignment of Serially Acquired Slices Using a Global Energy Function<br />
Krinidis, Stelio; Nikou, Christophoros; Pitas, Ioannis; October 25, 2001; 5 pp.; In English<br />
Report No.(s): AD-A4<strong>10</strong>239; No Copyright; Avail: CASI; A01, Hardcopy<br />
An accurate, computationally efficient and fully-automated algorithm for the alignment of 2D serially acquired sections<br />
forming a 3D volume is presented. The method accounts for the main shortcomings of 3D image alignment: corrupted data<br />
(cuts and tears), dissimilarities or discontinuities between slices, non parallel or missing slices. The approach relies on the<br />
optimization of a global energy function, based on the object shape, measuring the similarity between a slice and its<br />
neighborhood in the 3D volume. Slice similarity is computed using the distance transform measure in both directions. No<br />
particular direction is privileged in the method avoiding global offsets, biases in the estimation and error propagation. The<br />
method was evaluated on real images (medical and biological 3D data) and the experimental results demonstrated the<br />
method’s accuracy as reconstruction errors are less than 1 degree in rotation and less than 1 pixel in translation.<br />
DTIC<br />
Algorithms; Alignment; Autonomy; Numerical Analysis; Optimization<br />
<strong>2003</strong>0033866 Inha Univ., Inchon, Korea, Republic of<br />
A Speckle Reduction Filter Using Wavelet-Based Methods for Medical Imaging Application<br />
Kang, Su Cheol; Hong, Seung Hong; October 25, 2001; 5 pp.; In English<br />
Report No.(s): AD-A4<strong>10</strong>299; No Copyright; Avail: CASI; A01, Hardcopy<br />
One of the most significant features of diagnostic echocardiographic images is to reduce speckle noise and make better<br />
image quality. In this paper we proposed a simple and effective filter design for image denoising and contrast enhancement<br />
based on multiscale wavelet denoising method. Wavelet threshold algorithms replace wavelet coefficients with small<br />
magnitude by zero and keep or shrink the other coefficients. This is basically a local procedure since wavelet coefficients<br />
characterize the local regularity of a function. After we estimate distribution of noise within echocardiographic image then<br />
apply to fitness Wavelet threshold algorithm. A common way of the estimating the speckle noise level in coherent imaging<br />
175