An algorithm is described for fitting the DEDICOM model (proposed by R. A. Harshman in 1978) for the analysis of asymmetric data matrices. The method modifies a procedure proposed by Y. Takane (1985) to provide guaranteed monotonic convergence. The algorithm is based on a technique known as majorization. (SLD)

Gulliksen's matched random subtests method is a graphical method to split a test into parallel test halves, allowing maximization of coefficient alpha as a lower bound to the classical test reliability coefficient. This problem is formulated as a zero-one programing problem solvable by algorithms that already exist. (TJH)

This study develops an integrated conceptual representation scheme for multimedia documents that are viewed to comprise an object-oriented database; the necessary abstractions for the conceptual model and extensions to the relational model used as the search structure; a retrieval model that includes associative, semantic and media-specific…

Monotonically convergent algorithms are described for maximizing sums of quotients of quadratic forms. Six (constrained) functions are investigated. The general formulation of the functions and the algorithms allow for application of the algorithms in various situations in multivariate analysis. (SLD)

Presents a class of distortion controlled vector quantizers that are capable of compressing images so they comply with certain distortion requirements. Highlights include tree-structured vector quantizers; multiresolution vector quantization; error coding vector quantizer; error coding multiresolution algorithm; and Huffman coding of the quad-tree…

The TETRAD for constraint-based aids to causal model specification project and related work in computer science aims to apply standards of rigor and precision to the problem of using data and background knowledge to make inferences about a model's specifications. Several algorithms that are implemented in the TETRAD II program are presented. (SLD)

An iterative majorization algorithm is proposed for orthogonal congruence rotation that is guaranteed to converge from every starting point. In addition, the algorithm is easier to program than the algorithm proposed by F. B. Brokken, which is not guaranteed to converge. The derivation of the algorithm is traced in detail. (SLD)

Discusses vectors used in information retrieval and the algorithms used to manipulate them. Uses the Kohonen neural algorithm and a fuzzification model to perform a fuzzy clustering of document terms to reduce the high dimension and presents results from a test database. (Author/LRW)

Presents two binary programming models with a special network structure that can be explored computationally for simultaneous test construction. Uses an efficient special purpose network algorithm to solve these models. An empirical study illustrates the approach. (SLD)

Examines how a domain ontology can be reused by different knowledge representation systems. Describes a meta-language which allows a declarative description of any model based on frames, objects, relations, or description logics. Discusses the meta-relation concept which, associated to a definition, represents the signification of the construct…

Although today's computers can perform as many as one million operations per second, there are many problems that are still too large to be solved in a straightforward manner. Recent work indicates that many approximate solutions are useful and more efficient than exact solutions. (Author/RH)

The binary vector is suggested as an alternative to the usual method of storing document pointers in an inverted index file. (Author)

The report is a collection of internal reports dealing with the library management. The preliminary design details the anticipated system. The structure of data base reveals the implementation scheme on an IBM 2314 Disk Facility. Various algorithms are presented to document the actual system conditioned by using XPL and OS/MVT/HASP. Finally a…

A clustering technique is described, the objective of which is to detect deviant subpopulations which deviate from a primary subpopulation in a well defined direction. (Author/DEP)

A general factor analysis computer algorithm is briefly discussed. The algorithm is highly transportable with minimum limitations on the number of observations. Both singular and non-singular data can be analyzed. (Author/JKS)