Browsing by Type "Report"
Now showing items 120 of 157

The 2nuSVM: A CostSensitive Extension of the nuSVM
(20051201)Standard classification algorithms aim to minimize the probability of making an incorrect classification. In many important applications, however, some kinds of errors are more important than others. In this report we ... 
An Adaptive OrthogonalSeries Estimator for Probability Density Functions
(19780220)Given a sample set X1,...,XN of independent identically distributed realvalued random variables, each with the unknown probability density function f(â ¢), the problem considered is to estimate f from the sample set. The ... 
Adaptive Wavelet Transforms via Lifting
(19990115)This paper develops new algorithms for adapted multiscale analysis and signal adaptive wavelet transforms. We construct our adaptive transforms with the <i>lifting scheme</i>, which decomposes the wavelet transform into ... 
An Algorithm for Extraction of More than One Optimal Linear Feature from Several Gaussian Pattern Classes
(19760420)Two algorithms have been developed at Rice University for optimal linear feature extraction based on the minimization risk (probability) of misclassification under the assumption that the class conditional probability ... 
An Algorithm for Optimal Single Linear Feature Extraction from Several Gaussian Pattern Classes
(19751120)A computational algorithm is presented for the extraction of an optimal single linear feature from several Gaussian pattern classes. The algorithm minimizes the increase in the probability of misclassification in the ... 
An Algorithm to Factor Polynomial Matrices
(19790401)A new algorithm for factoring polynomial matrices, based on concept of elementary factors, is presented in this report. This algorithm does not use numerically unsatisfactory Euclidean type operations. 
Algorithms for Optimal Dynamic Assignment in Distributed Processing Systems
(19790820)The problem of determining an optimal dynamic assignment of a modular program in a loosely coupled distributed processing system is considered. An optimal dynamic assignment minimizes the sum of all module execution costs, ... 
Algorithms for Optimal Numerical Quadrature Based on Signal Class Models
(19791101)A framework is presented for constructing various types of numerical quadrature algorithms which take into account the apriori known or estimated properties of the signal being processed. This is done by appropriately ... 
Ambipolar electronics
(20100302)Ambipolar conduction, characterized by a superposition of electron and hole currents, has been observed in many nextgeneration devices including carbon nanotube, graphene, silicon nanowire, and organic transistors. ... 
Analog Computer Simulation of Maximum Expiratory Flow Limitation
(19750120)This paper extends previous modeling work in our laboratory on the simulation of the panting maneuver executed in a body plethysmograph [Golden, et al. (1973)] to the simulation of a wider range of pulmonary function tests ... 
Analysis of the DCS onestage Greedy Algorothm for Common Sparse Supports
(20051101)Analysis of the DCS onestage Greedy Algorothm for Common Sparse Supports 
APL Programs for Polynomial Matrix Manipulations
(19791201)This report contains descriptions and listings of APL programs. 
APL Programs for Singular Value Decomposition and Generalized Eigenvalue Problems
(19790920)This report contains descriptions and listings of APL functions for singular value decomposition and solution of the generalized eigenvalue problem. 
APL Programs for the Solution of RPIS
(19780820)This report contains the documentaiton for twelve APL functions written to facilitate the solution of the Regulator Problem with Internal Stability (RPIS). These new functions draw on the library of APL functions assembled ... 
Application of a Frequency Domain Prony Method to Wide Bandwidth Radar Signature Classification
(19790920)A frequency domain Prony approach is presented for extracting features of return signals from targets illuminated by wide bandwidth (short pulse) radar. Theoretical details pertaining to this approach are described in a ... 
Blind Algorithms for Channel Estimation and Detection in Wireless Handsets
(20000520)Multiple access is an important consideration in the design and implementation of wireless communications systems. Code division multiple access (CDMA) is one method for providing multiple access in a wireless system. In ... 
Characterization of Iron Doped Lithium Niobate for Holographic Storage Applications
(19760620)A detailed study of eight systematically chosen Fe:LiNb0<sub>3</sub> crystals is presented. Correlation between the photorefractive sensitivity and various chemical properties of Fe:LiNb0<sub>3</sub> is investigated in ... 
Compressing Piecewise Smooth Multidimensional Functions Using Surflets: RateDistortion Analysis
(20040301)Discontinuities in data often represent the key information of interest. Efficient representations for such discontinuities are important for many signal processing applications, including compression, but standard Fourier ... 
Computation of a Unimodular Matrix
(19791201)An algorithm for computing a unimodular matrix U(λ) satisfying the equation [A(λ) B(λ)] U(λ) = [1 0] is presented where A(λ) and B(λ) are relatively left prime polynomial matrices. ... 
Computationally Efficient Estimators for the Bayes Risk
(19780520)A computationally efficient estimator for the Bayes risk is one which achieves a desired accuracy with a minimum of computation. In many problems, for example speech recognition, point evaluations of the class conditional ...