| In this paper we introduce a parallel , programmable architecture capable of supporting both linear and nonlinear ltering. The proposed architecture consists of a ring of processors which can be conngured to operate like a sorter for order statistic based lters, and like a systolic array for linear lters. Such a structure also supports combination lters that are obtained by cascading linear a...

Time warping allows users to modify timing without affecting poses. It has many applications in animation systems for motion editing, such as refining motions to meet new timing constraints or modifying the acting of animated characters. However, time warping typically requires many manual adjustments to achieve the desired results. We present a technique which simplifies this process by allowi...

An efficient systolic array with the robust concurrent error diagnosis (CED) capability for the multiplication of band matrices is presented. This array is most appropriate for medium-banded matrices. While the corresponding Kung-Leiserson system is shown to be best suited for wide-banded matrices, the associated Huang-Abraham design is demonstrated as optimal for narrow-banded matrices. As it ...

Design of systolic arrays from a set of non-linear and nonuniform recurrence equations is discussed. A systematic method for deriving a systolic design in such cases is presented. A novel architectural idea, termed a tagged systolic array (TSA), is introduced. The design methodology described broadens the class of algorithms amenable for tagged systolic array implementation. The methodology is ...

The slope and intercept of a non-linearmodel of the end-systolic pressure–volume relation (ESPVR) are calculated by using a previously derived mathematical formalism describing the pressure–volume relation (PVR) in the left ventricle. An important feature of this mathematical approach is the inclusion of the peak isovolumic pressure Pisom in the formalism describing the PVR in the left ventricl...

We give a combinatorial interpretation of a matrix identity on Catalan numbers and the sequence (1, 4, 4, 4, . . .) which has been derived by Shapiro, Woan and Getu by using Riordan arrays. By giving a bijection between weighted partial Motzkin paths with an elevation line and weighted free Motzkin paths, we find a matrix identity on the number of weighted Motzkin paths and the sequence (1, k, ...

Patent DD 288911. References[1] G. Reißig and M. Peschel. Systolische Schaltungsanordnung zur Sim-ulation von Systemen in Lotka–Volterra–Darstellung. Patent DD 288911, 3 Nov. 1989. (“Systolic array for the simulation of Lotka–Volterra–Systems”, in German).

Gromov’s universal filling inequalities relate the filling radius and the filling volume of a Riemannian manifold to its volume. The main result of the present article is that in dimensions at least three the optimal constants in the filling inequalities depend only on dimension and orientability, not on the manifold itself. This contrasts with the analogous situation for the optimal systolic i...

This paper addresses the problem of determining geometric and chip area of systolic arrays for one class of nested loop algorithms in advance, before the systolic array synthesis. These parameters are determined only according to a given projection direction and loop boundaries.

Background Echocardiographic examination is currently the gold standard for the non invasive assessment of diastolic dysfunction. Although strain is not load independent, studies have shown that systolic strain rates can assess myocardial contractility and are relatively load independent. It remains to be established if diastolic strain parameters correlate with the degree of diastolic dysfunct...