Issue 10 Volume 41 May 16, 2003

This paper presents a new QRS complex detection algorithm that can be applied in various on-line FCC processing
systems. The algorithm is performed in two steps: first a wavelet transform filtering is applied to the signal, then QRS complex
localization is performed using a maximum detection and peak classification algorithm The algorithm has been tested in two
phases, First the QRS detection in FCC registrations from the MIT-BIH database has been performed, which led to an average
detection ratio of 99,50\%, Then, the algorithm has been implemented into a microcontroller-driven portable Holter device.
DTIC
Electrocardiography; Wavelet Analysis
20030034655 Dicle Univ., Diyarbakir, Turkey
A New Approach for Diagnosing Epilepsy by Using Wavelet Transform and Neural Networks
Akin, M.; Arserim, M. A.; Kiymik, M. K.; Turkoglu, I.; October 25, 2001; 5 pp.; In English
Report No.(s): AD-A410462; No Copyright; Avail: CASI; A01, Hardcopy
Today, epilepsy keeps its importance as a major brain disorder. However, although some devices such as magnetic
resonance (MR), brain tomography (BT) are used to diagnose the structural disorders of brain, for observing some special
illnesses especially such as epilepsy, EEG is routinely used for observing the epileptic seizures, in neurology clinics. In our
study, we aimed to classify the EEG signals and diagnose the epileptic seizures directly by using wavelet transform and an
artificial neural network model. EEG signals are separated into delta, theta, alpha, and beta spectral components by using
wavelet transform. These spectral components are applied to the inputs of the neural network. Then, neural network is trained
to give three outputs to signify the health situation of the patients
DTIC
Neural Nets; Electroencephalography; Wavelet Analysis; Signal Processing
20030034658 Ecole Nationale Superieure des Telecommunications, Brest, France
Medical Image Indexing and Compression Based on Vector Quantization: Image Retrieval Efficiency Evaluation
Ordonez, J. R.; Cazuguel, G.; Puentes, J.; Solaiman, B.; Cauvin, J. M.; October 25, 2001; 5 pp.; In English; Original contains
color illustrations
Report No.(s): AD-A410470; X5-X5; No Copyright; Avail: CASI; A01, Hardcopy
This paper addresses the problem of efficient image retrieval from a compressed image database, using information
derived from the compression process. Images in the database are compressed applying two approaches: Vector Quantization
(VQ) and Quadtree image decomposition. Both are based on Konohen’s Self-Organizing Feature Maps (SOFM) for creating
vector quantization codebooks. However, while VQ uses one codebook of one resolution to compress the images, Quadtree
decomposition uses simultaneously 4 codebooks of four different resolutions. Image indexing is implemented by generating
a Feature Vector (FV) for each compressed image. Accordingly, images are retrieved by means of FVs similarity evaluation
between the query image and the images in the database, depending on a distance measure. Three distance measures have been
analyzed to assess FV index similarity: Euclidean, Intersection and Correlation distances. Distance measures efficiency
retrieval is evaluated for different VQ resolutions and different Quadtree image descriptors. Experimental results using real
data, esophageal ultrasound and eye angiography images, are presented.
DTIC
Vector Quantization; Angiography; Ultrasonics; Image Processing
20030034661 Air Force Research Lab., Edwards AFB, CA
The Accuracy of Remapping Irregularly Spaced Velocity Data onto a Regular Grid and the Computation of Vorticity
Cohn, Richard K.; Koochesfahani, Manoochehr M.; March 15, 1999; 4 pp.; In English
Contract(s)/Grant(s): AF Proj. 3058
Report No.(s): AD-A410461; AFRL-PR-ED-TP-FY99-0060; No Copyright; Avail: CASI; A01, Hardcopy
The velocity data obtained from Molecular Tagging Velocimetry (MTV) are typically located on an irregularly spaced
measurement grid. In this method of velocimetry, the flowing medium is premixed with a molecular complex that can be
turned into a long life-time tracer upon excitation by photons. The velocity vector is determined from the displacement of
small regions ‘tagged’ by a pulsed laser that are imaged at two successive times within the lifetime of the tracer. This technique
may be viewed as the molecular counterpart of PIV. To take advantage of standard data processing techniques, the MTV data
need to be remapped onto a regular grid with a uniform spacing. This study examined the accuracy and noise issues related
to the use of various low-order polynomial least-square fits for remapping and the subsequent computation of vorticity from
these data. The information obtained has relevance to PIV data processing as well. As noted by Spedding and Rignot, the best
178