Information Quality Measures Research Articles

A parallel algorithm for building possibilistic causal networks

Among the several representations of uncertainty, possibility theory allows also for the management of imprecision coming from data. Domain models with inherent uncertainty and imprecision can be represented by means of possibilistic causal networks that, the possibilistic counterpart of Bayesian belief networks. Only recently the definition of possibilistic network has been clearly stated and the corresponding inference algorithms developed. However, and in contrast to the corresponding developments in Bayesian networks, learning methods for possibilistic networks are still few. We present here a new approach that hybridizes two of the most used approaches in uncertain network learning: those methods based on conditional dependency information and those based on information quality measures. The resulting algorithm, POSSCAUSE, admits easily a parallel formulation. In the present paper POSSCAUSE is presented and its main features discussed together with the underlying new concepts used.

Causes of cross-autocorrelation in security returns: Transaction costs versus information quality

We examine empirically the role of transaction costs and information quality as causes of cross-autocorrelations in security returns. Nonsynchronous trading influences are addressed by forming weekly returns based on averages of closing inside bid and ask quotations for NMS securities. Stock return volatility scaled by the bid-ask spread is employed as a proxy for transaction costs and trading volume is used as a measure of information quality. We find evidence that both transaction costs and information quality may contribute to cross-autocorrelations, but that information quality dominates transaction costs in explaining cross-autocorrelations after controlling for autocorrelation influences.

On measures of information quality of knowledge processing systems

The paper is an attempt to give a conceptual framework for quantitative analysis of logic inference parts of knowledge processing systems. Notions under consideration are of both informational and computational complexity flavor. Links with the realm of traditional logic problems have not been touched here. Starting with proof complexity of formulas, there are introduced distance between sets of formulas, degree of similarity of inference rules, entropy of inference system, reliability of provability and characteristics of inconsistency. Structure of proofs and of search space are also discussed as well as concrete ways of inference rules and inference search control representation (e.g., a language of occurrences and substitutions). The main goal of the paper is not to prove theorems about some set of notions but to give a ground for discussions on measuring and obtaining effectiveness of computer knowledge processing.

Image characterization for automatic target recognition algorithm evaluations

Automatic object recognizer algorithms designed to work with imaging sensor inputs require extensive testing before they should be considered robust enough for challenging applications such as military targeting. Testing automatic target recognition (ATR) algorithms in most cases has been limited to a handful of the scenario conditions of interest as represented by imagery collected with a desired imaging sensor. The question naturally arises as to how robust the performance of the ATR is for all scenario conditions of interest, not just for a small set of collected imagery. A way of addressing algorithm robustness is to characterize the input imagery in terms of some common information content or quality measures that can be correlated with ATR performance. This paper addresses the utility of image characterization measures in terms of estimating ATR detection performance by correlation analyses between nine different image measures and the detection responses of two ATR algorithms. Results show that an image measure called target-to-background entropy difference is the best single measure for estimating ATR detection performance, with correlation coefficients as large as 0.60.

A Measure of Reliability and Information Quality in Redundant Systems

In the development of complex military electronic equipment, It is necessary to consider the effects of many interacting operational and design factors. For both the over-all weapon system, and for the electronic subsystems with which we are concerned, optimum trade-offs for such interdependent parameters as reliability, weight, accuracy, maintainability, cost, mission time, and target vulnerability must be determined. Considered individually, these parameters do not adequately describe the operational worth of equipment incorporating multiple redundancies and operating modes. Operational worth is the probability that a system will achieve success in performing its required functions, and is obviously a prime consideration in the planning and selection of systems for military applilcation. The inadequacy in describing operational worth in terms of its individual parameters was encountered in the synthesis of an optimum redundant configuration for the B-58 bombing-navigation system. To resolve this difficulty, operational worth models describing the interaction between parameters were developed and utilized by Sperry Gyroscope Company. These techniques enabled Sperry to design this bombing-navigation system to have a high operational worth and an inherent mission reliability in excess of 95 per cent. In this paper, the model for ``system worth,'' the interaction between reliability and information quality, is discussed.